@uipath/delegate-sdk 1.203.0 → 1.203.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +41 -3
- package/dist/index.mjs +2 -2
- package/dist/skills/business-analysis/SKILL.md +722 -0
- package/dist/skills/business-analysis/as-is-capture.md +440 -0
- package/dist/skills/business-analysis/assets/progress.yaml +19 -0
- package/dist/skills/business-analysis/assets/task-list.md +34 -0
- package/dist/skills/business-analysis/automation-hub-publishing.md +47 -0
- package/dist/skills/business-analysis/bpmn-to-be-design.md +274 -0
- package/dist/skills/business-analysis/case-to-be-design.md +223 -0
- package/dist/skills/business-analysis/diagram-authoring.md +215 -0
- package/dist/skills/business-analysis/industry-gaps.md +134 -0
- package/dist/skills/business-analysis/interview-spine.md +297 -0
- package/dist/skills/business-analysis/locales/de.json +54 -0
- package/dist/skills/business-analysis/locales/en.json +54 -0
- package/dist/skills/business-analysis/locales/es-MX.json +54 -0
- package/dist/skills/business-analysis/locales/es.json +54 -0
- package/dist/skills/business-analysis/locales/fr.json +54 -0
- package/dist/skills/business-analysis/locales/ja.json +54 -0
- package/dist/skills/business-analysis/locales/ko.json +54 -0
- package/dist/skills/business-analysis/locales/pt-BR.json +54 -0
- package/dist/skills/business-analysis/locales/pt.json +54 -0
- package/dist/skills/business-analysis/locales/ro.json +54 -0
- package/dist/skills/business-analysis/locales/tr.json +54 -0
- package/dist/skills/business-analysis/locales/zh-CN.json +54 -0
- package/dist/skills/business-analysis/locales/zh-TW.json +54 -0
- package/dist/skills/business-analysis/pdd-generation.md +204 -0
- package/dist/skills/business-analysis/pdd-template.md +562 -0
- package/dist/skills/business-analysis/progress-presentation.json +13 -0
- package/dist/skills/business-analysis/recording-first.md +19 -0
- package/dist/skills/business-analysis/recording-processing.md +152 -0
- package/dist/skills/business-analysis/references/automation-hub-open-api.md +57 -0
- package/dist/skills/business-analysis/references/case-definition-spec.md +90 -0
- package/dist/skills/business-analysis/references/case-design-patterns/loan-origination-spec.md +86 -0
- package/dist/skills/business-analysis/references/component-type-mapping.md +52 -0
- package/dist/skills/business-analysis/references/uipath-products/case-management-schema.md +62 -0
- package/dist/skills/business-analysis/references/uipath-products/maestro-case-framework.md +65 -0
- package/dist/skills/business-analysis/references/uipath-products/maestro-case-management.md +49 -0
- package/dist/skills/business-analysis/research-offer.md +104 -0
- package/dist/skills/business-analysis/research-pass.md +149 -0
- package/dist/skills/business-analysis/scripts/assemble-pdd.ps1 +294 -0
- package/dist/skills/business-analysis/scripts/assemble-pdd.sh +453 -0
- package/dist/skills/business-analysis/scripts/check-phase-ready.ps1 +72 -0
- package/dist/skills/business-analysis/scripts/check-phase-ready.sh +98 -0
- package/dist/skills/business-analysis/scripts/lint-diagram.ps1 +524 -0
- package/dist/skills/business-analysis/scripts/lint-diagram.sh +519 -0
- package/dist/skills/business-analysis/scripts/stamp-pages.ps1 +363 -0
- package/dist/skills/business-analysis/scripts/stamp-pages.sh +360 -0
- package/dist/skills/business-analysis/to-be-design.md +199 -0
- package/dist/skills/confluence/SKILL.md +386 -0
- package/dist/skills/doc-coauthoring/SKILL.md +295 -0
- package/dist/skills/excel-architect/SKILL.macos.md +161 -0
- package/dist/skills/excel-architect/SKILL.md +180 -0
- package/dist/skills/excel-architect/SKILL.windows.md +61 -0
- package/dist/skills/excel-architect/archetypes/01-financial-model-advanced.md +332 -0
- package/dist/skills/excel-architect/archetypes/01-financial-model.md +248 -0
- package/dist/skills/excel-architect/archetypes/02-data-analysis.md +171 -0
- package/dist/skills/excel-architect/archetypes/03-tracking-dashboard.md +160 -0
- package/dist/skills/excel-architect/archetypes/04-project-planning.md +193 -0
- package/dist/skills/excel-architect/archetypes/05-simple-table.md +111 -0
- package/dist/skills/excel-architect/building.md +279 -0
- package/dist/skills/excel-architect/create.md +64 -0
- package/dist/skills/excel-architect/data-and-formulas.md +186 -0
- package/dist/skills/excel-architect/generator.md +272 -0
- package/dist/skills/excel-architect/macos/scripts/add-data-validation.applescript +242 -0
- package/dist/skills/excel-architect/macos/scripts/append-rows.applescript +310 -0
- package/dist/skills/excel-architect/macos/scripts/apply-conditional-format.applescript +565 -0
- package/dist/skills/excel-architect/macos/scripts/autofit-columns.applescript +79 -0
- package/dist/skills/excel-architect/macos/scripts/benchmark.sh +135 -0
- package/dist/skills/excel-architect/macos/scripts/check-compile.sh +30 -0
- package/dist/skills/excel-architect/macos/scripts/clear-range.applescript +152 -0
- package/dist/skills/excel-architect/macos/scripts/copy-paste.applescript +179 -0
- package/dist/skills/excel-architect/macos/scripts/create-chart.applescript +531 -0
- package/dist/skills/excel-architect/macos/scripts/create-pivot.applescript +443 -0
- package/dist/skills/excel-architect/macos/scripts/create-sheets.applescript +264 -0
- package/dist/skills/excel-architect/macos/scripts/create-workbook.applescript +92 -0
- package/dist/skills/excel-architect/macos/scripts/delete-chart.applescript +105 -0
- package/dist/skills/excel-architect/macos/scripts/delete-sheet.applescript +127 -0
- package/dist/skills/excel-architect/macos/scripts/filter-data.applescript +213 -0
- package/dist/skills/excel-architect/macos/scripts/find-replace.applescript +238 -0
- package/dist/skills/excel-architect/macos/scripts/format-range.applescript +531 -0
- package/dist/skills/excel-architect/macos/scripts/freeze-panes.applescript +133 -0
- package/dist/skills/excel-architect/macos/scripts/get-current-file.applescript +24 -0
- package/dist/skills/excel-architect/macos/scripts/get-sheet-dimensions.applescript +115 -0
- package/dist/skills/excel-architect/macos/scripts/health-check.applescript +704 -0
- package/dist/skills/excel-architect/macos/scripts/list-open-workbooks.applescript +80 -0
- package/dist/skills/excel-architect/macos/scripts/maximize-window.applescript +47 -0
- package/dist/skills/excel-architect/macos/scripts/merge-cells.applescript +227 -0
- package/dist/skills/excel-architect/macos/scripts/open-workbook.applescript +139 -0
- package/dist/skills/excel-architect/macos/scripts/read-range.applescript +267 -0
- package/dist/skills/excel-architect/macos/scripts/rename-sheet.applescript +231 -0
- package/dist/skills/excel-architect/macos/scripts/select-sheet.applescript +133 -0
- package/dist/skills/excel-architect/macos/scripts/set-tab-color.applescript +109 -0
- package/dist/skills/excel-architect/macos/scripts/sort-data.applescript +136 -0
- package/dist/skills/excel-architect/macos/scripts/undo.applescript +59 -0
- package/dist/skills/excel-architect/macos/scripts/workbook-lifecycle.applescript +149 -0
- package/dist/skills/excel-architect/macos/scripts/write-formula.applescript +225 -0
- package/dist/skills/excel-architect/macos/scripts/write-range.applescript +351 -0
- package/dist/skills/excel-architect/reference/api/advanced.md +381 -0
- package/dist/skills/excel-architect/reference/api/basic.md +747 -0
- package/dist/skills/excel-architect/reference/guides.md +348 -0
- package/dist/skills/excel-architect/reference/repair.md +174 -0
- package/dist/skills/excel-architect/reference/troubleshooting.md +46 -0
- package/dist/skills/excel-architect/scripting.md +266 -0
- package/dist/skills/excel-architect/styling-and-features.md +433 -0
- package/dist/skills/excel-architect/windows/api/composites.md +337 -0
- package/dist/skills/excel-architect/windows/api/scripting.md +139 -0
- package/dist/skills/excel-architect/windows/examples/level-1-workflows.md +485 -0
- package/dist/skills/excel-architect/windows/examples/level-2-advanced.md +690 -0
- package/dist/skills/excel-architect/windows/examples/level-3-scripting.md +337 -0
- package/dist/skills/github/SKILL.md +446 -0
- package/dist/skills/github/recipes/add-comment.md +85 -0
- package/dist/skills/github/recipes/check-pr-status.md +122 -0
- package/dist/skills/github/recipes/compare-branches.md +79 -0
- package/dist/skills/github/recipes/create-issue.md +103 -0
- package/dist/skills/github/recipes/create-pr.md +97 -0
- package/dist/skills/github/recipes/get-file-contents.md +76 -0
- package/dist/skills/github/recipes/get-last-commit.md +128 -0
- package/dist/skills/github/recipes/list-my-open-prs.md +105 -0
- package/dist/skills/github/recipes/list-recent-commits.md +84 -0
- package/dist/skills/github/recipes/search-issues.md +115 -0
- package/dist/skills/google-workspace/SKILL.md +217 -0
- package/dist/skills/google-workspace/services/calendar.md +311 -0
- package/dist/skills/google-workspace/services/docs.md +426 -0
- package/dist/skills/google-workspace/services/drive.md +504 -0
- package/dist/skills/google-workspace/services/gmail.md +466 -0
- package/dist/skills/google-workspace/services/sheets.md +370 -0
- package/dist/skills/internal-comms/SKILL.md +35 -0
- package/dist/skills/internal-comms/examples/3p-updates.md +47 -0
- package/dist/skills/internal-comms/examples/company-newsletter.md +65 -0
- package/dist/skills/internal-comms/examples/faq-answers.md +30 -0
- package/dist/skills/internal-comms/examples/general-comms.md +15 -0
- package/dist/skills/jira/SKILL.md +397 -0
- package/dist/skills/jira/recipes/add-comment.md +123 -0
- package/dist/skills/jira/recipes/assign-issue.md +157 -0
- package/dist/skills/jira/recipes/create-issue.md +274 -0
- package/dist/skills/jira/recipes/get-issue-details.md +154 -0
- package/dist/skills/jira/recipes/list-projects.md +151 -0
- package/dist/skills/jira/recipes/my-issues.md +180 -0
- package/dist/skills/jira/recipes/search-issues.md +215 -0
- package/dist/skills/jira/recipes/transition-issue.md +154 -0
- package/dist/skills/jira/recipes/troubleshooting.md +387 -0
- package/dist/skills/knowledge-base/SKILL.md +289 -0
- package/dist/skills/media-tools/SKILL.md +204 -0
- package/dist/skills/media-tools/references/encode-runbook.md +24 -0
- package/dist/skills/media-tools/references/resolve-binaries.md +81 -0
- package/dist/skills/media-tools/scripts/macos/ff-launch.sh +22 -0
- package/dist/skills/media-tools/scripts/macos/ff-poll.sh +10 -0
- package/dist/skills/media-tools/scripts/windows/ff-launch.ps1 +34 -0
- package/dist/skills/media-tools/scripts/windows/ff-poll.ps1 +20 -0
- package/dist/skills/office-download/SKILL.md +161 -0
- package/dist/skills/outlook-365/SKILL.macos.md +331 -0
- package/dist/skills/outlook-365/SKILL.md +171 -0
- package/dist/skills/outlook-365/SKILL.windows.md +124 -0
- package/dist/skills/outlook-365/api/bulk-email-operations.md +178 -0
- package/dist/skills/outlook-365/api/check-availability.md +87 -0
- package/dist/skills/outlook-365/api/create-inbox-rule.md +182 -0
- package/dist/skills/outlook-365/api/download-attachments.md +149 -0
- package/dist/skills/outlook-365/api/find-and-email-contact.md +185 -0
- package/dist/skills/outlook-365/api/manage-calendar-events.md +189 -0
- package/dist/skills/outlook-365/api/organize-with-folders.md +178 -0
- package/dist/skills/outlook-365/api/reply-to-conversation.md +68 -0
- package/dist/skills/outlook-365/api/schedule-meeting.md +73 -0
- package/dist/skills/outlook-365/api/search-and-read-email.md +93 -0
- package/dist/skills/outlook-365/api/send-email-with-attachments.md +94 -0
- package/dist/skills/outlook-365/api/send-email.md +396 -0
- package/dist/skills/outlook-365/api/set-out-of-office.md +196 -0
- package/dist/skills/outlook-365/macos/scripts/bulk-operations.applescript +429 -0
- package/dist/skills/outlook-365/macos/scripts/calendar.applescript +642 -0
- package/dist/skills/outlook-365/macos/scripts/contacts.applescript +635 -0
- package/dist/skills/outlook-365/macos/scripts/helpers.applescript +227 -0
- package/dist/skills/outlook-365/macos/scripts/read-emails.applescript +299 -0
- package/dist/skills/outlook-365/macos/scripts/search-emails.applescript +339 -0
- package/dist/skills/outlook-365/macos/scripts/send-email.applescript +245 -0
- package/dist/skills/outlook-365/uia/BASIC_OPERATIONS.md +278 -0
- package/dist/skills/outlook-365/uia/CALENDAR_OPERATIONS.md +386 -0
- package/dist/skills/outlook-365/uia/COMPOSE_EMAIL.md +426 -0
- package/dist/skills/outlook-365/uia/README.md +75 -0
- package/dist/skills/outlook-365/windows/com/bulk-operations.ps1 +241 -0
- package/dist/skills/outlook-365/windows/com/calendar.ps1 +227 -0
- package/dist/skills/outlook-365/windows/com/contacts.ps1 +270 -0
- package/dist/skills/outlook-365/windows/com/helpers.ps1 +158 -0
- package/dist/skills/outlook-365/windows/com/read-emails.ps1 +115 -0
- package/dist/skills/outlook-365/windows/com/search-emails.ps1 +141 -0
- package/dist/skills/outlook-365/windows/com/send-email.ps1 +121 -0
- package/dist/skills/pdf-architect/SKILL.md +640 -0
- package/dist/skills/powerpoint-architect/SKILL.macos.md +271 -0
- package/dist/skills/powerpoint-architect/SKILL.md +853 -0
- package/dist/skills/powerpoint-architect/SKILL.windows.md +458 -0
- package/dist/skills/powerpoint-architect/custom_themes.md +141 -0
- package/dist/skills/powerpoint-architect/editing-guide.md +424 -0
- package/dist/skills/powerpoint-architect/generator-reference.md +668 -0
- package/dist/skills/powerpoint-architect/images-guide.md +207 -0
- package/dist/skills/powerpoint-architect/issue-fix-mapping.md +768 -0
- package/dist/skills/powerpoint-architect/macos/scripts/add-html-to-slide.applescript +389 -0
- package/dist/skills/powerpoint-architect/macos/scripts/add-slide.applescript +255 -0
- package/dist/skills/powerpoint-architect/macos/scripts/add-speaker-notes.applescript +132 -0
- package/dist/skills/powerpoint-architect/macos/scripts/add-text.applescript +245 -0
- package/dist/skills/powerpoint-architect/macos/scripts/apply-slide-layout.applescript +80 -0
- package/dist/skills/powerpoint-architect/macos/scripts/apply-theme.applescript +122 -0
- package/dist/skills/powerpoint-architect/macos/scripts/autofit-placeholders.applescript +62 -0
- package/dist/skills/powerpoint-architect/macos/scripts/close-presentation.applescript +24 -0
- package/dist/skills/powerpoint-architect/macos/scripts/copy-slides.applescript +303 -0
- package/dist/skills/powerpoint-architect/macos/scripts/create-chart-with-data.applescript +305 -0
- package/dist/skills/powerpoint-architect/macos/scripts/create-with-theme.applescript +56 -0
- package/dist/skills/powerpoint-architect/macos/scripts/delete-slides.applescript +137 -0
- package/dist/skills/powerpoint-architect/macos/scripts/export-presentation.applescript +100 -0
- package/dist/skills/powerpoint-architect/macos/scripts/extract-slide-data.applescript +138 -0
- package/dist/skills/powerpoint-architect/macos/scripts/format-shape.applescript +192 -0
- package/dist/skills/powerpoint-architect/macos/scripts/format-slide-content.applescript +336 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-current-slide-number.applescript +38 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-file-path.applescript +94 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-layout-elements.applescript +141 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-layouts.applescript +58 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-opened-files.applescript +50 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-presentation-info.applescript +150 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-recent-files.applescript +68 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-slide-count.applescript +37 -0
- package/dist/skills/powerpoint-architect/macos/scripts/get-slide-info.applescript +105 -0
- package/dist/skills/powerpoint-architect/macos/scripts/health-check.applescript +690 -0
- package/dist/skills/powerpoint-architect/macos/scripts/insert-shape.applescript +188 -0
- package/dist/skills/powerpoint-architect/macos/scripts/insert-table.applescript +112 -0
- package/dist/skills/powerpoint-architect/macos/scripts/insert-text-box.applescript +225 -0
- package/dist/skills/powerpoint-architect/macos/scripts/manage-image.applescript +486 -0
- package/dist/skills/powerpoint-architect/macos/scripts/maximize-window.applescript +48 -0
- package/dist/skills/powerpoint-architect/macos/scripts/navigate-to-slide.applescript +84 -0
- package/dist/skills/powerpoint-architect/macos/scripts/open-presentation.applescript +38 -0
- package/dist/skills/powerpoint-architect/macos/scripts/reorder-slides.applescript +106 -0
- package/dist/skills/powerpoint-architect/macos/scripts/replace-text.applescript +193 -0
- package/dist/skills/powerpoint-architect/macos/scripts/save-presentation.applescript +54 -0
- package/dist/skills/powerpoint-architect/macos/scripts/set-animation.applescript +203 -0
- package/dist/skills/powerpoint-architect/macos/scripts/set-transition.applescript +130 -0
- package/dist/skills/powerpoint-architect/visual-styling-guide.md +206 -0
- package/dist/skills/powerpoint-architect/windows/api/advanced.md +317 -0
- package/dist/skills/powerpoint-architect/windows/api/basic.md +392 -0
- package/dist/skills/powerpoint-architect/windows/examples/10-slide-presentation.md +140 -0
- package/dist/skills/powerpoint-architect/windows/examples/custom-theme-workflow.md +219 -0
- package/dist/skills/powerpoint-architect/windows/examples/level-1-workflows.md +531 -0
- package/dist/skills/powerpoint-architect/windows/examples/level-2-scripting.md +239 -0
- package/dist/skills/powerpoint-architect/windows/scripts/create-with-theme.ps1 +81 -0
- package/dist/skills/project-task-list/SKILL.md +174 -0
- package/dist/skills/slack-operation/SKILL.md +97 -0
- package/dist/skills/slack-operation/api/advanced-api/GUIDE.md +277 -0
- package/dist/skills/slack-operation/api/search-and-read/EXAMPLE.md +75 -0
- package/dist/skills/slack-operation/api/search-and-read/GUIDE.md +108 -0
- package/dist/skills/slack-operation/api/send-message/EXAMPLE.md +112 -0
- package/dist/skills/slack-operation/api/send-message/GUIDE.md +63 -0
- package/dist/skills/slack-operation/api/share-files/EXAMPLE.md +94 -0
- package/dist/skills/slack-operation/api/share-files/GUIDE.md +63 -0
- package/dist/skills/slack-operation/ui/desktop-automation/GUIDE.md +55 -0
- package/dist/skills/system-diagnostics/SKILL.md +263 -0
- package/dist/skills/teams-operation/SKILL.md +79 -0
- package/dist/skills/teams-operation/api/advanced-api/GUIDE.md +234 -0
- package/dist/skills/teams-operation/api/meetings/EXAMPLE.md +63 -0
- package/dist/skills/teams-operation/api/meetings/GUIDE.md +52 -0
- package/dist/skills/teams-operation/api/search-and-read/EXAMPLE.md +72 -0
- package/dist/skills/teams-operation/api/search-and-read/GUIDE.md +54 -0
- package/dist/skills/teams-operation/api/send-message/EXAMPLE.md +92 -0
- package/dist/skills/teams-operation/api/send-message/GUIDE.md +60 -0
- package/dist/skills/teams-operation/ui/desktop-automation/GUIDE.md +66 -0
- package/dist/skills/transcribe-media/SKILL.md +142 -0
- package/dist/skills/uipath-integrations/SKILL.md +370 -0
- package/dist/skills/uipath-integrations/reference/connectors.md +331 -0
- package/dist/skills/uipath-integrations/reference/endpoints.md +220 -0
- package/dist/skills/uipath-integrations/reference/errors.md +211 -0
- package/dist/skills/uipath-integrations/reference/metadata.md +317 -0
- package/dist/skills/uipath-integrations/reference/operations.md +297 -0
- package/dist/skills/uipath-orchestrator/SKILL.md +312 -0
- package/dist/skills/uipath-orchestrator/recipes/assets.md +282 -0
- package/dist/skills/uipath-orchestrator/recipes/audit-logs.md +215 -0
- package/dist/skills/uipath-orchestrator/recipes/buckets.md +205 -0
- package/dist/skills/uipath-orchestrator/recipes/jobs.md +286 -0
- package/dist/skills/uipath-orchestrator/recipes/list-folders.md +207 -0
- package/dist/skills/uipath-orchestrator/recipes/queue-items.md +292 -0
- package/dist/skills/uipath-orchestrator/recipes/queues.md +232 -0
- package/dist/skills/uipath-orchestrator/recipes/releases.md +212 -0
- package/dist/skills/uipath-orchestrator/recipes/robots-sessions.md +274 -0
- package/dist/skills/uipath-orchestrator/recipes/schedules.md +280 -0
- package/dist/skills/uipath-orchestrator/reference/endpoints.md +85 -0
- package/dist/skills/uipath-orchestrator/reference/schemas.md +153 -0
- package/dist/skills/uipath-taskautomation/SKILL.md +310 -0
- package/dist/skills/uipath-taskautomation/assets/CodedWorkflow.template.cs +98 -0
- package/dist/skills/uipath-taskautomation/assets/ExampleWorkflow.cs +146 -0
- package/dist/skills/uipath-taskautomation/references/action-activity-map.json +32 -0
- package/dist/skills/uipath-taskautomation/references/action-activity-map.md +44 -0
- package/dist/skills/uipath-taskautomation/references/app-profiles.md +63 -0
- package/dist/skills/uipath-taskautomation/references/automation-spec.md +88 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/assets/before-after-hooks-template.md +115 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/assets/codedworkflow-template.md +186 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/assets/helper-utility-template.md +22 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/assets/json-template.md +91 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/assets/testcase-template.md +92 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/cli-reference.md +249 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/coded/codedworkflow-reference.md +275 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/coded/coding-guidelines.md +229 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/coded/inspect-package-guide.md +81 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/coded/integration-service-guide.md +507 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/coded/operations-guide.md +410 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/coded/third-party-packages-guide.md +67 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/data-manipulation-guide.md +110 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/environment-setup.md +194 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/error-handling-guide.md +195 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/powershell-interop-guide.md +57 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/project-structure-guide.md +114 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/project-structure.md +126 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/uia-elements-interaction-guide.md +109 -0
- package/dist/skills/uipath-taskautomation/references/coded-reference/validation-guide.md +147 -0
- package/dist/skills/uipath-taskautomation/references/coded-workflow-authoring.md +219 -0
- package/dist/skills/uipath-taskautomation/references/profiling-output.md +80 -0
- package/dist/skills/uipath-taskautomation/references/reliability-guide.md +83 -0
- package/dist/skills/uipath-taskautomation/references/task-automation-cheatsheet.md +272 -0
- package/dist/skills/uipath-taskautomation/references/template-preflight.md +17 -0
- package/dist/skills/uipath-workflow-documenter/SKILL.md +430 -0
- package/dist/skills/uipath-workflow-documenter/layouts/pdd-template.md +265 -0
- package/dist/skills/uipath-workflow-documenter/routines/from-orchestrator.md +11 -0
- package/dist/skills/uipath-workflow-documenter/routines/from-workflow.md +11 -0
- package/dist/skills/word-architect/SKILL.macos.md +147 -0
- package/dist/skills/word-architect/SKILL.md +502 -0
- package/dist/skills/word-architect/SKILL.windows.md +55 -0
- package/dist/skills/word-architect/api/advanced.md +522 -0
- package/dist/skills/word-architect/api/basic.md +378 -0
- package/dist/skills/word-architect/api/expert.md +302 -0
- package/dist/skills/word-architect/generation.md +308 -0
- package/dist/skills/word-architect/layouts/01-professional.md +168 -0
- package/dist/skills/word-architect/layouts/02-educational-kids.md +354 -0
- package/dist/skills/word-architect/layouts/03-academic.md +83 -0
- package/dist/skills/word-architect/layouts/04-creative.md +242 -0
- package/dist/skills/word-architect/layouts/05-operational.md +94 -0
- package/dist/skills/word-architect/macos/scripts/apply-heading-style.applescript +215 -0
- package/dist/skills/word-architect/macos/scripts/apply-style.applescript +272 -0
- package/dist/skills/word-architect/macos/scripts/autofit-tables.applescript +53 -0
- package/dist/skills/word-architect/macos/scripts/close-document.applescript +287 -0
- package/dist/skills/word-architect/macos/scripts/create-chart-with-data.applescript +379 -0
- package/dist/skills/word-architect/macos/scripts/create-chart.applescript +191 -0
- package/dist/skills/word-architect/macos/scripts/delete-selection.applescript +223 -0
- package/dist/skills/word-architect/macos/scripts/export-document.applescript +167 -0
- package/dist/skills/word-architect/macos/scripts/extract-table.applescript +168 -0
- package/dist/skills/word-architect/macos/scripts/find-by-style.applescript +173 -0
- package/dist/skills/word-architect/macos/scripts/find-text.applescript +199 -0
- package/dist/skills/word-architect/macos/scripts/format-table.applescript +234 -0
- package/dist/skills/word-architect/macos/scripts/format-text.applescript +431 -0
- package/dist/skills/word-architect/macos/scripts/get-document-properties.applescript +95 -0
- package/dist/skills/word-architect/macos/scripts/get-document-structure.applescript +371 -0
- package/dist/skills/word-architect/macos/scripts/get-header-footer-text.applescript +106 -0
- package/dist/skills/word-architect/macos/scripts/get-images.applescript +166 -0
- package/dist/skills/word-architect/macos/scripts/get-opened-files.applescript +103 -0
- package/dist/skills/word-architect/macos/scripts/get-paragraph-bounds.applescript +133 -0
- package/dist/skills/word-architect/macos/scripts/get-paragraph-format.applescript +134 -0
- package/dist/skills/word-architect/macos/scripts/get-recent-files.applescript +82 -0
- package/dist/skills/word-architect/macos/scripts/get-styled-text.applescript +256 -0
- package/dist/skills/word-architect/macos/scripts/get-tables.applescript +126 -0
- package/dist/skills/word-architect/macos/scripts/get-text-formatting.applescript +224 -0
- package/dist/skills/word-architect/macos/scripts/get-text.applescript +383 -0
- package/dist/skills/word-architect/macos/scripts/get-theme-colors.applescript +123 -0
- package/dist/skills/word-architect/macos/scripts/health-check.applescript +606 -0
- package/dist/skills/word-architect/macos/scripts/insert-cover-page.applescript +77 -0
- package/dist/skills/word-architect/macos/scripts/insert-header-footer.applescript +87 -0
- package/dist/skills/word-architect/macos/scripts/insert-horizontal-line.applescript +112 -0
- package/dist/skills/word-architect/macos/scripts/insert-html.applescript +440 -0
- package/dist/skills/word-architect/macos/scripts/insert-hyperlink.applescript +191 -0
- package/dist/skills/word-architect/macos/scripts/insert-image.applescript +320 -0
- package/dist/skills/word-architect/macos/scripts/insert-list.applescript +317 -0
- package/dist/skills/word-architect/macos/scripts/insert-pagebreak.applescript +181 -0
- package/dist/skills/word-architect/macos/scripts/insert-smartart.applescript +104 -0
- package/dist/skills/word-architect/macos/scripts/insert-table.applescript +238 -0
- package/dist/skills/word-architect/macos/scripts/insert-text.applescript +677 -0
- package/dist/skills/word-architect/macos/scripts/insert-textbox.applescript +261 -0
- package/dist/skills/word-architect/macos/scripts/maximize-window.applescript +67 -0
- package/dist/skills/word-architect/macos/scripts/normalize-formatting.applescript +56 -0
- package/dist/skills/word-architect/macos/scripts/open-document.applescript +222 -0
- package/dist/skills/word-architect/macos/scripts/replace-text.applescript +390 -0
- package/dist/skills/word-architect/macos/scripts/save-document.applescript +230 -0
- package/dist/skills/word-architect/macos/scripts/select-range.applescript +142 -0
- package/dist/skills/word-architect/macos/scripts/set-document-properties.applescript +195 -0
- package/dist/skills/word-architect/macos/scripts/set-page-layout.applescript +273 -0
- package/dist/skills/word-architect/macos/scripts/set-theme-colors.applescript +264 -0
- package/dist/skills/word-architect/macos/scripts/undo-redo.applescript +61 -0
- package/dist/skills/word-architect/macos/scripts/update-toc.applescript +112 -0
- package/dist/skills/word-architect/reference/formatting.md +119 -0
- package/dist/skills/word-architect/reference/html-layouts/01-executive-summary-box.md +36 -0
- package/dist/skills/word-architect/reference/html-layouts/02-kpi-summary-table.md +68 -0
- package/dist/skills/word-architect/reference/html-layouts/03-comparison-table.md +63 -0
- package/dist/skills/word-architect/reference/html-layouts/04-pros-cons-table.md +86 -0
- package/dist/skills/word-architect/reference/html-layouts/05-timeline-table.md +114 -0
- package/dist/skills/word-architect/reference/html-layouts/06-raci-matrix.md +95 -0
- package/dist/skills/word-architect/reference/html-layouts/07-data-table-alternating.md +84 -0
- package/dist/skills/word-architect/reference/html-layouts/08-callout-box.md +102 -0
- package/dist/skills/word-architect/reference/html-layouts/09-vertical-milestone.md +100 -0
- package/dist/skills/word-architect/reference/quality-assurance.md +102 -0
- package/dist/skills/word-architect/reference/tables.md +62 -0
- package/dist/skills/word-architect/reference/tracked-changes.md +34 -0
- package/dist/skills/word-architect/reference/uia-fallback.md +231 -0
- package/dist/skills/word-architect/reference/visual-elements.md +82 -0
- package/dist/skills/word-architect/windows/scripts/apply-heading-style.ps1 +190 -0
- package/dist/skills/word-architect/windows/scripts/autofit-tables.ps1 +64 -0
- package/dist/skills/word-architect/windows/scripts/create-chart-with-data.ps1 +133 -0
- package/dist/skills/word-architect/windows/scripts/create-chart.ps1 +73 -0
- package/dist/skills/word-architect/windows/scripts/export-document.ps1 +86 -0
- package/dist/skills/word-architect/windows/scripts/get-current-file.ps1 +27 -0
- package/dist/skills/word-architect/windows/scripts/insert-cover-page.ps1 +79 -0
- package/dist/skills/word-architect/windows/scripts/insert-horizontal-line.ps1 +74 -0
- package/dist/skills/word-architect/windows/scripts/insert-image.ps1 +98 -0
- package/dist/skills/word-architect/windows/scripts/insert-smartart.ps1 +118 -0
- package/dist/skills/word-architect/windows/scripts/insert-text-box.ps1 +90 -0
- package/dist/skills/word-architect/windows/scripts/normalize-formatting.ps1 +63 -0
- package/package.json +5 -4
|
@@ -0,0 +1,440 @@
|
|
|
1
|
+
# Phase 1 — AS-IS Capture
|
|
2
|
+
|
|
3
|
+
User-facing wording: business terms only (current process, future process, process map, completeness check). Internal labels in this guide (AS-IS, wiki, funnel, Mermaid) are for you, never spoken to the user.
|
|
4
|
+
|
|
5
|
+
Populates `entities/`, `as-is/`, and produces an AS-IS process artifact. Drive via conversational funnel, not a stepper — but when sources exist, the funnel mostly answers itself.
|
|
6
|
+
|
|
7
|
+
**Silent capture, one checkpoint.** When the user supplied sources (docs, recordings, a described process), the whole capture runs silently: read, extract, retrieve Process Knowledge, write the wiki, sync the task list, produce and validate the process artifact — with no narration and no interim questions. The user's next contact with this phase is the **Process Snapshot** (below), the phase's single checkpoint. Silent means no narration and no interim *questions of your own devising* — it never suppresses a gate the skill mandates. Chat between the opener and the snapshot happens for exactly two reasons: the capture-format question below (unless one of its three inputs-decide conditions holds — supplied sources are not one of them), and a blocking gap the sources cannot answer. Sequence both by what they touch: the capture-format question and any gap that changes the process map are asked in one small batch BEFORE the model is drawn (plain sentences, with the "Take your best assumption" option); everything else waits and rides along with the snapshot. The snapshot itself is never sent without the validated model already in the panel.
|
|
8
|
+
|
|
9
|
+
**Best-assumption capture.** The user's documents, recordings, and opener are the primary answer source; the user's time is the scarce resource. For every FACTS item, decide from evidence first and classify per `interview-spine.md`: `known` (stated in a source) → capture with provenance; `safe assumption` (clearly implied by a source) → capture it, mark the task list row `needs confirmation`, and disclose it in the snapshot's assumption ledger — never turn it into a question; `blocking` (shape-changing and no source evidence, or sources conflict) → ask, batched: map-changing gaps in one pre-drawing batch, the rest with the snapshot. Ask the user only what the sources genuinely cannot answer. Checkpoints present what you decided and ask what should change — they are confirm-or-correct surfaces, not question lists.
|
|
10
|
+
|
|
11
|
+
**Write each fact to its page in the turn it is confirmed.** One page, one `WriteFile`, composed from that page's own facts. Do not hold a coherent picture in conversation and flush it later, and never produce a page body from a shell loop, a heredoc or a `printf` — sets written that way come out as identical stubs, and the literal `\n` defect comes from the same place. There is no background execution: a turn that ends without a write has produced nothing, conversation does not survive compaction, and every grader reads files rather than chat. End each turn by naming what is now on disk. Every page a write creates or substantially rewrites carries the OKF trust stamps (SKILL.md Page Trust Stamps). After each completed factual write round, make FACTS-row synchronization the next mutation. If a run of writes spans multiple tool-call rounds, synchronize after each completed round. Do not generate the AS-IS process map, perform an unrelated write, advance the phase, or send a phase recap while affected FACTS rows are stale (see SKILL.md Project TaskList).
|
|
12
|
+
|
|
13
|
+
## What This Phase Produces
|
|
14
|
+
|
|
15
|
+
```
|
|
16
|
+
entities/{people,applications,artifacts}/ # one MD per entity
|
|
17
|
+
as-is/overview.md # current-state framing prose
|
|
18
|
+
as-is/process.bpmn # current-state BPMN 2.0 XML — when the capture format is BPMN (or user-supplied verbatim); BPMNDI optional
|
|
19
|
+
as-is/diagram.md # case-design or generic Mermaid fragment — when the capture format is a case map or simple flow
|
|
20
|
+
as-is/steps/ # one MD per step, 01-..., 02-...
|
|
21
|
+
as-is/stages/ # Case route only: one MD per stage (allowed activities, entry/exit, owners, SLA, subcases)
|
|
22
|
+
as-is/stages.md # Case route only: the case object, its lifecycle states, index of stages
|
|
23
|
+
as-is/attachments.md # every route: evidence/notes sidecar (frontmatter map of stage id, item or step node id, or BPMN element key -> refs)
|
|
24
|
+
as-is/{metrics,data-inputs-outputs,business-rules,exception-handling,scheduling-and-triggers,pain-points,compliance}.md
|
|
25
|
+
queries/open-questions.md # open gaps and carried assumptions, persisted at phase close
|
|
26
|
+
as-is/scope.md # only when explicitly discussed before TO-BE
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
**What marks this phase successful.** Every page above exists on disk when the phase closes. Nothing reads the conversation, so a fact that reached only chat has not been captured. On the Case route the current state is captured when `as-is/stages.md` exists and every stage it lists has its own `as-is/stages/<stage-id>.md` page; a stage in the ledger with no page behind it leaves the capture half done. The current-process map carries a node for every step or stage its pages define. Deadlines, thresholds, system names and regulators appear in the source bundle's own wording, which is why the fields below carry figures and clock units verbatim rather than converted.
|
|
30
|
+
|
|
31
|
+
## FACTS checkpoint
|
|
32
|
+
|
|
33
|
+
Before presenting the Process Snapshot, make sure the FACTS checkpoint is satisfied or has explicit open gaps. Do not treat the task list as complete because statuses were set; the wiki must hold the answer and the task list row must point to it.
|
|
34
|
+
|
|
35
|
+
Required current-state facts:
|
|
36
|
+
- business problem and desired outcome
|
|
37
|
+
- current trigger
|
|
38
|
+
- current flow, lifecycle, or task sequence
|
|
39
|
+
- systems touched
|
|
40
|
+
- source of truth
|
|
41
|
+
- actors / owners
|
|
42
|
+
- inputs, outputs, documents, and data
|
|
43
|
+
- volume / frequency / backlog
|
|
44
|
+
- cycle time / SLA
|
|
45
|
+
- exceptions / rework / escalations
|
|
46
|
+
- compliance / audit constraints
|
|
47
|
+
- pain points
|
|
48
|
+
|
|
49
|
+
If a missing fact changes the current process map, ask one focused question before drawing (route questions wait for the TO-BE routing ask — never pull them into AS-IS). Every other missing fact does not block and does not get its own question: capture the best-assumption value from sources when one is implied (row `needs confirmation`, disclosed in the ledger), or record the item as `missing` with an explicit open gap. If the missing fact is a future-state design detail, record it as a TO-BE question instead of blocking AS-IS.
|
|
50
|
+
|
|
51
|
+
## Opening Funnel
|
|
52
|
+
|
|
53
|
+
The funnel establishes intake, not completion. Its steps are coverage items, not questions to fire: each is asked **only when neither the opener, the attached sources, nor the wiki already answers or clearly implies it**. If an answer is vague but not shape-changing, keep moving; step 4 collects detail via docs/recording. If an answer affects route, trigger, main path, ownership, systems, exception path, SLA, compliance, or terminal outcome, ask one targeted clarification before mapping. Persist answers to `as-is/overview.md`.
|
|
54
|
+
|
|
55
|
+
**Sources first.** If the user attached documents or recordings with the opener (or the project already carries them), read them before asking anything — they usually answer steps 1–3 outright. Derived and implied answers go into the Process Snapshot as decided values to confirm, not back to the user as questions.
|
|
56
|
+
|
|
57
|
+
1. **Industry, business area, department, role** — each must be covered: inferred from the opener/sources, or asked. When asking, max 2 per AskUser call, **all four use `options:` with `{"kind":"userinput"}`** — never `options: []`. Skip any that a source or the user already gave or implies (an HR onboarding SOP implies HR — infer it, disclose it, don't ask).
|
|
58
|
+
2. **Applications and systems.** Ask only when no source names the systems. When sources name them, adopt the list and confirm it inside the Process Snapshot ("Systems I found: X, Y, Z — any missing?" as part of that single surface). When asking: `options:` with `multiSelect: true` and `{"kind":"userinput"}`.
|
|
59
|
+
3. **Short process description**, 2-3 sentences (trigger, output, steps). Derive from sources when present. Accept rough non-shape detail as intake; clarify only what would change route or process shape.
|
|
60
|
+
4. **The docs/recording ask.** If no sources arrived with the opener, fire the AskUser media question (`recordable: true`, `attachable: true`) — "Got existing docs/recordings for this, want to record a walkthrough, or just tell me and I'll work from that?". This gives the user the Record + Attach widget with its comment box; always offer it rather than asking a separate text question first — a typed reply in that box (declining, or describing the process) is itself a complete answer. **Skip this step entirely when the user already attached sources**; more material can always arrive later. Branches the flow.
|
|
61
|
+
|
|
62
|
+
If a recording arrives (live via AskUser or an existing video file), read `recording-processing.md` and follow it. Don't ask follow-up questions about anything visible in a frame.
|
|
63
|
+
|
|
64
|
+
## Progressive Process Knowledge During AS-IS
|
|
65
|
+
|
|
66
|
+
Latched run first (SKILL.md, The latch): `{WikiPath}/research-pass.md` records `Process Knowledge state:` `closed` or `opted-out` → make none of the calls below, log `Phase: AS-IS — skipped` once in `process-knowledge.md`, and this phase's checkpoint is complete. Never send a decision to unlock them.
|
|
67
|
+
|
|
68
|
+
Use Process Knowledge to improve the questions you ask, not to fill in the current process without confirmation.
|
|
69
|
+
|
|
70
|
+
Call it at these AS-IS checkpoints:
|
|
71
|
+
|
|
72
|
+
1. **After Opening Funnel step 3.** Ask for likely current-state stages, actors, systems, artifacts, controls, KPIs, and exceptions for this industry/process. If matched process display names are returned, write only those names and the retrieval focus to `process-knowledge.md`.
|
|
73
|
+
2. **After docs/recordings are summarized.** Include the matched process display names from `process-knowledge.md`, the extracted facts, and ask for missing current-state probes. Check the returned probes against the sources first; ask the user only the most-specific gap that is blocking, and record the rest as assumptions or open items.
|
|
74
|
+
3. **When a new process area appears.** If the user introduces a materially different subprocess, system family, region, product, or exception family, call again with the matched names plus the new context.
|
|
75
|
+
4. **Before the industry gap pass.** Ask specifically for missing current-state probes, likely controls, exception paths, KPIs, and artifacts. This complements `industry-gaps.md`; it does not replace it.
|
|
76
|
+
5. **Before AS-IS map generation.** Ask for a completeness check against the confirmed wiki facts and matched process display names. Do not introduce TO-BE improvements into the current-process map.
|
|
77
|
+
|
|
78
|
+
For follow-up calls, keep the same API shape and put the context into the `description`:
|
|
79
|
+
|
|
80
|
+
```text
|
|
81
|
+
Continue using these matched process references: <display names from process-knowledge.md>.
|
|
82
|
+
Current confirmed facts: <brief AS-IS summary from wiki/conversation>.
|
|
83
|
+
Need now: missing AS-IS probes for stages, roles, systems, artifacts, controls, KPIs, and exception handling.
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
Retrieved best practices are future-state candidates. In AS-IS, turn them into probes ("Do you do X today?"). If the user says yes, write the current behavior to `as-is/`. If the user says no but the idea is useful, write it to `to-be/seeds.md`.
|
|
87
|
+
|
|
88
|
+
Phase gate: follow the Gate's fit judgment (SKILL.md) for whether to call again here, never while the latch holds. When you do, append to `process-knowledge.md` a new entry with `Phase: AS-IS` and the result status before writing `entities/`, `as-is/`, an AS-IS recap, or a current-process map. If the call errors, retry once; if the retry also errors, record the error in `process-knowledge.md` and ask the user whether to continue from confirmed source facts.
|
|
89
|
+
|
|
90
|
+
## After Step 4 — Branch on the Result
|
|
91
|
+
|
|
92
|
+
### Intake Docs / Recordings Branch
|
|
93
|
+
|
|
94
|
+
When the user attached docs or submitted a recording, the sources become the primary interview: extract everything, assume the rest where safely implied, and spend the user's attention only on blocking gaps.
|
|
95
|
+
|
|
96
|
+
- Copy into `<wiki>/raw/` (preserve filenames).
|
|
97
|
+
- If a recording lands, read `recording-processing.md` and follow it.
|
|
98
|
+
- Read all source material before asking anything.
|
|
99
|
+
- **Fill every FACTS item best-assumption from the sources.** Stated → `known` with provenance. Clearly implied (the SOP shows an approval step → an approver role exists; the export is monthly → frequency is monthly) → capture the value as a `safe assumption` with its source. Not evidenced and not shape-changing → `missing` with an explicit open gap. Do not leave an item blank because no one asked the user about it, and do not queue a question for anything a source answers.
|
|
100
|
+
- **The Process Snapshot is the extraction checkpoint.** There is no separate mid-capture review: capture everything silently, run the closing sequence, and present the snapshot. Its **assumption ledger** ("What I assumed from your documents", one line per safe assumption with its source) discloses every inference; it ends with one explicit decision: "Confirm / Change / Attach or record more evidence?".
|
|
101
|
+
- **Batch the blocking gaps.** Whatever the sources genuinely cannot answer AND is shape-changing (route, trigger, main path, ownership, systems, exception path, SLA, compliance, terminal outcome) goes into the snapshot turn as one batched AskUser — few questions, finite options where enumerable. If nothing is blocking, ask nothing beyond the snapshot's explicit decision.
|
|
102
|
+
- Reconcile source scope before AS-IS drafting. If the documents cover a narrower subprocess, adjacent workstream, region, product, or demo scope than the user's opener, stop and ask the user to confirm whether the PDD should use the source-bounded scope or wait for more source material. Do not use Process Knowledge or general industry patterns to fill a broader lifecycle not documented in the source bundle. This is the one question allowed to precede the snapshot.
|
|
103
|
+
- If documents conflict with each other or with what the user just said, that conflict is blocking — surface both and ask which is real: "The SOP is from 2022 — still current?". Never silently pick a side.
|
|
104
|
+
- Do not treat the current process as validated until the user confirms the snapshot — the confirmed Process Snapshot is that validation.
|
|
105
|
+
|
|
106
|
+
### No Docs Branch
|
|
107
|
+
|
|
108
|
+
When the user submitted nothing or said they have no docs:
|
|
109
|
+
|
|
110
|
+
- Fall through to verbal capture using `interview-spine.md`.
|
|
111
|
+
- Build the current process in layers: trigger -> outcome -> main path -> decisions -> exceptions -> systems/data -> volume/SLA -> pain points.
|
|
112
|
+
- Summarize back as you go: "So I'm hearing: [step 1], [decision], [step 2]. Roughly the shape?"
|
|
113
|
+
- Ask only the highest-value missing or blocking question at a time. Never ask bare questions without a summary preamble.
|
|
114
|
+
- Suggest industry-typical missing steps proactively ("most Finance AP has a 3-way PO match — is that part of yours?").
|
|
115
|
+
- When the user describes a UI-touching step without enough detail, fire the per-step recordable AskUser (see *Step Gaps* below) — second chance to record.
|
|
116
|
+
- Reflect the shape back before writing the map.
|
|
117
|
+
|
|
118
|
+
## During Capture (no fixed order)
|
|
119
|
+
|
|
120
|
+
### Entities (apps, people, artifacts)
|
|
121
|
+
|
|
122
|
+
Only write an entity MD when you have purpose + how-used. No "to be confirmed" placeholders.
|
|
123
|
+
A system, person or artifact the sources name but do not explain is not dropped for failing that
|
|
124
|
+
bar: write one line to `queries/open-questions.md` — the name exactly as the source spells it, where
|
|
125
|
+
it appeared, and what is unknown about it — and carry it into the snapshot's open gaps. The page has
|
|
126
|
+
a bar; the name has none. A system the sources mention and the document never does reads to the
|
|
127
|
+
reader as one that is not part of the process, which is a claim nobody checked.
|
|
128
|
+
|
|
129
|
+
One MD per entity, in the matching folder.
|
|
130
|
+
|
|
131
|
+
| Folder | Trigger | Required fields |
|
|
132
|
+
|---|---|---|
|
|
133
|
+
| `entities/applications/<app>.md` | any app, system, or tool | name (as the user says it), purpose, owner/team, integration method (API/UI/file/manual) if known, login (SSO/local/shared) if mentioned |
|
|
134
|
+
| `entities/people/<role-or-name>.md` | any person, title, or team | name or role title, team/dept, involvement (initiates/approves/executes/receives/escalates), availability/timezone if relevant |
|
|
135
|
+
| `entities/artifacts/<artifact>.md` | any file, export, report, spreadsheet, form | name + format (xlsx, pdf, csv, …), source system, producer/consumer, frequency |
|
|
136
|
+
|
|
137
|
+
For artifacts, when the user has shared a sample file, append a light schema (column names, key field, one sample row). No confirmation table. A field the process only carries through stays at that light schema.
|
|
138
|
+
|
|
139
|
+
**A decision-driving data field gets a full row instead.** When a field decides a route, sets a binding, or satisfies a compliance check, record it with the six columns PDD §6.3 projects:
|
|
140
|
+
|
|
141
|
+
| Field | Type | Format / pattern | Valid values / range | Mandatory | Privacy class |
|
|
142
|
+
|---|---|---|---|---|---|
|
|
143
|
+
| [name as the source calls it] | [text / number / date / boolean / enum] | [pattern, unit, or currency] | [the enumerated values, or the range] | [yes / no] | [PII / Tokenized / Sensitive / None] |
|
|
144
|
+
|
|
145
|
+
Read each cell off the sample file or the source document where it is visible. Where you inferred a cell rather than read it, keep the cell filled and mark it as an assumption, and carry the row into the snapshot's assumption ledger — an inferred type is still a captured type; a blank cell is not. Privacy class is stated for every such field and never left blank, because a field with no privacy class reaches the document with no masking or retention decision behind it.
|
|
146
|
+
|
|
147
|
+
### Artifact Samples — Batched Ask
|
|
148
|
+
|
|
149
|
+
If artifacts surface and samples aren't covered by the opening funnel's recording/docs, batch ONE multi-question AskUser with a media question per artifact (`attachable: true`). Don't ask per-artifact during capture.
|
|
150
|
+
|
|
151
|
+
On attach: copy into `{WikiPath}/raw/` and run schema capture (see the Entities table above).
|
|
152
|
+
|
|
153
|
+
### Step Gaps — Recordable AskUser
|
|
154
|
+
|
|
155
|
+
When the user describes a step without sufficient detail (e.g. "we go into Application X and pull a report" with no nav/filter/export specifics), fire one AskUser media question with both `recordable: true` and `attachable: true` ("How exactly do you download the report from Application X? Show me, share a recording, or attach docs."). Any mode is fine: record live, drop an existing video, drop a doc, or type.
|
|
156
|
+
|
|
157
|
+
- On recording or attached video: read `recording-processing.md` and follow it.
|
|
158
|
+
- On attached doc (SOP, screenshot pack): copy into `{WikiPath}/raw/`, read it, fold extracted steps/entities into the wiki.
|
|
159
|
+
- On typed answer: persist to the relevant step MD.
|
|
160
|
+
|
|
161
|
+
### Metrics and Volumetrics
|
|
162
|
+
|
|
163
|
+
Weave into step discussion; never a separate metrics questionnaire. Cover frequency, per-step duration, headcount, peaks (month-/quarter-/year-end), backlog, aging, and measurement method. Directional estimates are fine, but label them as estimates.
|
|
164
|
+
|
|
165
|
+
Persist to `as-is/metrics.md`:
|
|
166
|
+
|
|
167
|
+
```
|
|
168
|
+
| Metric | Current signal | Measurement method |
|
|
169
|
+
|---|---|---|
|
|
170
|
+
| Daily / Monthly Volume | [N per day / N per month] | [system report / SME estimate / sample period] |
|
|
171
|
+
| Time per Transaction | [N minutes per unit] | [timed walkthrough / SME estimate / process mining] |
|
|
172
|
+
| FTE Count | [N FTEs] | [team roster / SME estimate] |
|
|
173
|
+
| Backlog / Aging | [N open / oldest age] | [queue report / SME estimate] |
|
|
174
|
+
| Peak Periods | [month-end / year-end / none] | [calendar pattern / SME estimate] |
|
|
175
|
+
```
|
|
176
|
+
|
|
177
|
+
### Steps
|
|
178
|
+
|
|
179
|
+
Capture in `as-is/steps/` — one MD per step or natural step group.
|
|
180
|
+
|
|
181
|
+
- Group when steps cluster tightly (a 3-tap form fill is one step, not three).
|
|
182
|
+
- Do not enforce strict 1:1 with conversation turns.
|
|
183
|
+
- Filename pattern: `01-<short-name>.md`, `02-<short-name>.md`, etc.
|
|
184
|
+
- Each step MD should include: step name, actor, application(s) used, **specific screens / UI surfaces touched** (e.g. "Salesforce → Account Details → Contact section"), inputs, outputs, decision points, exceptions noted, estimated time.
|
|
185
|
+
- On the Case route, each step MD also names the stage it belongs to (`Stage: <stage id>`), because there the stage — not the step order — carries the structure.
|
|
186
|
+
- Recording-sourced step MD also carries `Sub-process: <name>` (Case route: `Stage:` serves), `Recording: mm:ss–mm:ss` from the transcript `[mm:ss]` lines or trace `tMs`, every field, value, filter and button it touches named exactly as on screen, and its frame paths. Every rule, decision and exception seen in the recording names its step page (number and name): `as-is/business-rules.md` rules as `Rule ID | Step | Rule | Recording`, decision points under its `## Decision points` heading as `Step | Condition | Action`, `as-is/exception-handling.md` as `Step | Exception | Current handling`. These feed the PDD §3.2 recording layout.
|
|
187
|
+
- Include screenshots, if available
|
|
188
|
+
|
|
189
|
+
Run the Decision pass (below) once the steps are captured. Before closing this phase, compare the step count in `as-is/steps/` against the source material's actual granularity — materially more distinct actions or branches in the source than captured is a coverage defect; split under-captured steps before the snapshot.
|
|
190
|
+
|
|
191
|
+
### Business Rules
|
|
192
|
+
|
|
193
|
+
When the user states a condition that governs the process (approval thresholds, routing rules, eligibility criteria) → append to `as-is/business-rules.md` (step-level conditions go in its Decision points table — see the Decision pass):
|
|
194
|
+
|
|
195
|
+
| Rule ID | Description | Enforced at | Threshold or value |
|
|
196
|
+
|---|---|---|---|
|
|
197
|
+
| BR-001 | [rule as stated] | [the step, and the system that blocks it] | [the figure, as the source states it] |
|
|
198
|
+
|
|
199
|
+
Assign sequential IDs. Exact wording matters — quote the user where possible.
|
|
200
|
+
|
|
201
|
+
`Enforced at` names the step **and** the system that actually blocks the work, because PDD §9.1 maps every rule to its enforcement point and the evidence retained; a rule with no enforcement point arrives in the document as an unenforceable sentence. `Threshold or value` carries the figure numerically — `> 50,000 EUR`, `< 0.88 confidence`, `3 attempts`, `over 90 days` — never "high value", "large", or "low confidence". When the user states the rule without its figure, keep their wording in `Description` and write the missing figure into the cell as a concrete open question rather than leaving it blank.
|
|
202
|
+
|
|
203
|
+
### Exception Handling
|
|
204
|
+
|
|
205
|
+
When the user describes an error path, edge case, or escalation → append to `as-is/exception-handling.md` (the Decision pass table `Step | Exception | Current handling`). Include: trigger condition, who handles it, resolution path, SLA impact if any, and **how often it fires**.
|
|
206
|
+
|
|
207
|
+
Frequency is a count per period or a share of volume — `~40 a month`, `12% of applications`, `2 a quarter` — with the measurement method beside it (system report, team estimate, sampled). It is what separates the exception the future design must handle from the one worth only naming, and no route asks for it anywhere else. Ask for it when the sources are silent and the exception sits on the main path; where it is genuinely not tracked, write `frequency not measured` rather than a guess.
|
|
208
|
+
|
|
209
|
+
### Decision pass — before drawing
|
|
210
|
+
|
|
211
|
+
Run once after the steps are captured and before any process map is drawn. A map drawn straight from the step list is linear; the branches live in what people say and show.
|
|
212
|
+
|
|
213
|
+
1. Read the whole transcript and the chosen frames for conditions. Cues: "only when", "if … then", "unless", "otherwise", "we don't do X for Y", "except", "in parallel", "at the same time", "meanwhile", "while that runs", plus branches visible on screen (a status that routes the item, a filter, a dialog with alternatives).
|
|
214
|
+
2. Record every condition in `as-is/business-rules.md` under a `## Decision points` heading, one row per condition, keyed by the step it belongs to (the step doc's number and name): `Step | Condition | Action`. Quote the speaker's wording; mark transcript-only facts. A condition with several outcomes gets one row per outcome.
|
|
215
|
+
3. Record every error path, edge case, and escalation in `as-is/exception-handling.md` as `Step | Exception | Current handling`.
|
|
216
|
+
4. Write each decision and exception into its step doc too (decision points / exceptions fields), pointing to the table row.
|
|
217
|
+
5. A condition that is ambiguous (unclear trigger, outcome, or scope) goes to the snapshot's Open gaps and `queries/open-questions.md`. Never ask a separate question for it.
|
|
218
|
+
|
|
219
|
+
Then draw the gateways from the tables, in whichever format was confirmed:
|
|
220
|
+
|
|
221
|
+
- Each decision-table condition is an exclusive gateway with every outcome labelled; a condition with a default outcome marks it as the default.
|
|
222
|
+
- Two things happening independently (one file goes to SharePoint while another goes to an import folder; "at the same time", "meanwhile") are a parallel (AND) gateway: split, one branch per activity, then a join where the work converges. Never chain them in sequence.
|
|
223
|
+
- Distinct outcomes are distinct nodes. "Settle" and "leave unapplied and escalate" are two nodes with their own downstream path, never one node with a combined label.
|
|
224
|
+
- An exceptions-table row becomes a branch off its step, or a boundary/secondary route on BPMN and case maps.
|
|
225
|
+
- Before presenting, check that every decision-table row and exceptions-table row appears in the map or is named as out of map scope in the step doc.
|
|
226
|
+
|
|
227
|
+
`as-is/business-rules.md` and `as-is/exception-handling.md` stay the PDD sources (§5 and §8), so the PDD's Decision points and Exceptions tables are built from these two tables.
|
|
228
|
+
|
|
229
|
+
### Scheduling and Triggers
|
|
230
|
+
|
|
231
|
+
When the user describes what starts the process, how often it runs, or SLA windows → append to `as-is/scheduling-and-triggers.md`. Include: trigger type (time-based / event-based / manual), schedule, SLA, source system for trigger.
|
|
232
|
+
|
|
233
|
+
Every deadline or SLA carries three more fields, because a duration without them is not a deadline:
|
|
234
|
+
|
|
235
|
+
- **The clock unit, verbatim from the source** — `3 WD`, `3 working days`, `2 business days`, `15 calendar days`, `4 hours`. Working days, business days and calendar days are three different clocks: carry the source's own wording through, and never convert one into another or normalize `3 WD` to `3 days`. The document is read back against the source bundle, so the converted form scores as a missing detail even when the arithmetic is right.
|
|
236
|
+
- **The event that starts the clock** — the named step or system event the count runs from, not "on receipt". A duration with no start event cannot be measured or automated.
|
|
237
|
+
- **Any pause condition** that stops the clock — awaiting a customer response, weekends and public holidays, a hold or suspended state. Write `no pauses` when the clock genuinely runs continuously.
|
|
238
|
+
|
|
239
|
+
When a source gives the duration but names no start event, record the duration and write the start event into the row as an open question.
|
|
240
|
+
|
|
241
|
+
### Data Inputs and Outputs
|
|
242
|
+
|
|
243
|
+
Maintain `as-is/data-inputs-outputs.md` as a running list — one subsection per artifact, five fields, always in this order (too many fields for a table; see Table Width). Add a subsection whenever a new artifact enters or exits the process:
|
|
244
|
+
|
|
245
|
+
### [artifact name]
|
|
246
|
+
|
|
247
|
+
**Source / Destination:** [system or team]
|
|
248
|
+
**Format:** [format]
|
|
249
|
+
**Transformation:** [what changes between consumption and production — mapping, calculation, enrichment; "none" if unchanged]
|
|
250
|
+
**Consumed / Produced By:** [role or step]
|
|
251
|
+
|
|
252
|
+
### Compliance and Audit Constraints
|
|
253
|
+
|
|
254
|
+
When the user or a source states a regulatory, policy, or audit obligation (retention rules, approval mandates, regulated decisions, evidence requirements) → append to `as-is/compliance.md`: the obligation, its source (regulation / internal policy), where the process enforces it today, and the evidence retained. This page is the PDD §9 source — compliance facts parked anywhere else never reach the document.
|
|
255
|
+
|
|
256
|
+
### Pain Points
|
|
257
|
+
|
|
258
|
+
When the user expresses frustration, manual workarounds, errors, delays, or rework → append to `as-is/pain-points.md`:
|
|
259
|
+
|
|
260
|
+
| Pain Point | Description |
|
|
261
|
+
|---|---|
|
|
262
|
+
| [short label] | [as stated by the user] |
|
|
263
|
+
|
|
264
|
+
### Case AS-IS gap pass
|
|
265
|
+
|
|
266
|
+
When the AS-IS capture format is a case map (inputs decided it, or the user confirmed it at the capture-format question), frame `as-is/overview.md` around the case: name the case object, the lifecycle states it moves through, and the stages that own the work — not a linear step narrative. Then run a case-aware gap pass before closing AS-IS. Normalize the current process into case dimensions and identify what is missing before the future case is designed.
|
|
267
|
+
|
|
268
|
+
Capture or mark gaps for:
|
|
269
|
+
- current trigger
|
|
270
|
+
- current stages
|
|
271
|
+
- current stage work / case activities
|
|
272
|
+
- stage owners / personas
|
|
273
|
+
- systems touched
|
|
274
|
+
- data, artifacts, and evidence
|
|
275
|
+
- decisions and routes
|
|
276
|
+
- exceptions, rework, and escalations
|
|
277
|
+
- volume / frequency / backlog
|
|
278
|
+
- cycle time / SLA
|
|
279
|
+
- AS-IS gaps and pain points
|
|
280
|
+
|
|
281
|
+
If a current-state answer is missing and it affects the future case shape, ask one targeted question before drawing the AS-IS map. If the missing answer is not needed until target design, record it as a TO-BE question instead of blocking AS-IS.
|
|
282
|
+
|
|
283
|
+
When AS-IS exposes an obvious improvement, write it as one of the candidate TO-BE changes in `to-be/seeds.md` with the AS-IS issue it came from. Example: "Approval happens by email with no audit trail → candidate TO-BE change: tracked approval task with explicit outcomes." Do not design the future state during AS-IS; only preserve the seed and keep capturing today's process.
|
|
284
|
+
|
|
285
|
+
### BPMN AS-IS gap pass
|
|
286
|
+
|
|
287
|
+
When the AS-IS capture format is a BPMN model (inputs decided it, or the user confirmed it at the capture-format question), run a BPMN-aware gap pass before closing AS-IS. Normalize the current process into process-model dimensions and identify what is missing before the future BPMN map is designed.
|
|
288
|
+
|
|
289
|
+
Capture or mark gaps for:
|
|
290
|
+
- current participants and lanes
|
|
291
|
+
- start event and terminal outcomes
|
|
292
|
+
- activities and subprocesses
|
|
293
|
+
- handoffs between participants
|
|
294
|
+
- gateways, decisions, splits, and merges
|
|
295
|
+
- messages, waits, timers, callbacks, and escalations
|
|
296
|
+
- systems and data objects
|
|
297
|
+
- exceptions, rework, and recovery routes
|
|
298
|
+
- volume / frequency / backlog
|
|
299
|
+
- cycle time / SLA
|
|
300
|
+
- AS-IS gaps and pain points
|
|
301
|
+
|
|
302
|
+
If a current-state answer is missing and it affects the future BPMN shape, ask one targeted question before drawing the AS-IS map. If the missing answer is not needed until target design, record it as a TO-BE question instead of blocking AS-IS.
|
|
303
|
+
|
|
304
|
+
When AS-IS exposes an obvious process-model improvement, write it as one of the candidate TO-BE changes in `to-be/seeds.md` with the AS-IS issue it came from. Example: "Escalation happens through informal email follow-up → candidate TO-BE change: explicit timer event and escalation route." Do not design the future state during AS-IS; only preserve the seed and keep capturing today's process.
|
|
305
|
+
|
|
306
|
+
### TO-BE Surfacing During AS-IS
|
|
307
|
+
|
|
308
|
+
The user will sometimes drop automation-shaped content during AS-IS (vendor decisions, "we have X licensed", sketched future flows). Route it to `to-be/`, don't park it in AS-IS files (Phase 2 won't find it there).
|
|
309
|
+
|
|
310
|
+
- Concrete (vendor decision, licensed product, sketched flow, hard constraint) → write to the matching `to-be/` file (`delivery-model.md`, `constraints.md`, `overview.md`).
|
|
311
|
+
- Lighter (intent, partial idea) → one-line note to `to-be/seeds.md`.
|
|
312
|
+
- Process-knowledge suggestions (retrieved improvements, best-practice steps the user doesn't do today) describe the future state → use them as AS-IS *probes* (ask whether they do it), then route confirmed improvements to `to-be/seeds.md`. Only what the user confirms they do today goes in `as-is/`.
|
|
313
|
+
|
|
314
|
+
Keep capturing AS-IS; don't pivot the conversation to TO-BE.
|
|
315
|
+
|
|
316
|
+
## AS-IS process artifact — ask the capture format
|
|
317
|
+
|
|
318
|
+
Today's process is captured in the format the user wants — the three inputs-decide conditions below skip the question, and in every other case you ask it explicitly (the question rides the pre-drawing batch; see SKILL.md "AS-IS capture format"). The router's inference supplies the recommendation; the user decides. The confirmed format is recorded in `as-is/overview.md` as one line — `Process map shape: Case map (user choice, 2026-08-10)` — and a recorded choice is never re-asked across sessions.
|
|
319
|
+
|
|
320
|
+
**The provenance in that line is a factual claim, not a formality.** Write `(user choice, <date>)` only when the user answered the question, and `(best assumption, <date>)` only when the user picked "Take your best assumption". Never draw the map having written either one without asking — a shape you chose yourself, recorded as though it were confirmed, is the one failure this gate exists to prevent. The choice seeds the Phase 2 guide recommendation: Case map → `case-to-be-design.md`, BPMN model → `bpmn-to-be-design.md`.
|
|
321
|
+
|
|
322
|
+
Skip the question when — and only when — the inputs decide it. This list is exhaustive; sources that merely *suggest* a shape make it the recommendation, not the answer:
|
|
323
|
+
|
|
324
|
+
- **Inputs decide, no question:** a user-supplied valid BPMN 2.0 model is saved verbatim as `as-is/process.bpmn` — User-supplied BPMN always wins; it is the AS-IS process-model source of truth. BPMNDI optional; never convert it to Mermaid or recreate it by hand (if it fails XML or reference validation, keep it as evidence and author the chosen-format artifact instead). A Decision 1-confirmed task is captured as a Simple flow map without asking — the route is RPA; case vs BPMN does not apply. A user who named the format gets that format. A wiki-recorded choice from an earlier session stands — never re-ask.
|
|
325
|
+
- **Otherwise ask** — "How should I map today's process?" with the recommendation first (stages/owners/SLAs in the sources → Case map; cross-department handoffs and events → BPMN model; a linear sequence → Simple flow map) plus "Take your best assumption".
|
|
326
|
+
|
|
327
|
+
Produce the artifact per the confirmed format:
|
|
328
|
+
|
|
329
|
+
- **BPMN model** → author `as-is/process.bpmn` as a current-state BPMN 2.0 semantic model using the Documentation BPMN profile and the Mandatory saved-artifact validation in `bpmn-to-be-design.md` (same rules, current state instead of future: `isExecutable="false"`, no `bpmndi:*`, real XML-parser and reference validation before presenting). Read that profile section during this phase if not already read this session.
|
|
330
|
+
- **Case map** → write `as-is/diagram.md` with `diagramFamily=case-design` per the `case-design` family contract in `diagram-authoring.md`: `flowchart LR`, stage subgraphs, exactly one `case-task-*` per task, `case-ends-case` terminal markers, no authored `classDef`. **Derive current stages from the captured flow first:** a stage seam is where ownership changes or a major decision routes the work; cluster the steps between seams into 3–7 named stages; today's exception and rework paths become secondary stages. Fill the stage table (stage, owner, work item, how it runs today, routes), then transcribe. Today's work is classed by how it runs now: human work → `case-task-action`, legacy automation → `case-task-rpa` or `case-task-process`, system waits → `case-task-wait-for-connector`/`wait-for-timer`. This is current-state capture: do not read the TO-BE case guide for this. Then document the case per "Case capture" below — the diagram alone is not the documentation.
|
|
331
|
+
- **Simple flow map** → write `as-is/diagram.md` with `diagramFamily=generic` per `diagram-authoring.md`: `flowchart TB`, exactly one `kind-*` and one `mode-*` per node, no authored `classDef`. One node per sub-process or activity; its UI-level steps open from the node through `as-is/attachments.md` (simple flow sidecar, below), never as map nodes. A request for click-level detail in the map gets the one-sentence answer in `diagram-authoring.md` (Level).
|
|
332
|
+
|
|
333
|
+
### Case capture — document the case, not just the diagram
|
|
334
|
+
|
|
335
|
+
A case-map capture documents the current state AS A CASE, then draws it. The stage model is the source of truth; the diagram is a projection of it, not the documentation itself. Run the Case AS-IS gap pass and write the stage docs below. Stage subgraph ids are stable slugs referenced by other artifacts — rename a stage by changing its quoted title, keep the id. When a restructure genuinely changes the stages (split, merge, add, remove), migrate `as-is/attachments.md` in the SAME change: re-key every attachment entry and note to the new stage ids (splitting a stage means deciding which successor each ref belongs to), re-key item notes whose node ids changed, and update the stage docs to match. A redrawn diagram that leaves the sidecar on the old keys silently orphans every piece of evidence the user supplied — never leave keys that no current stage answers to. The diagram lint fails on it (`orphaned-attachment-key`, `orphaned-note-key`), so a redrawn map does not pass until the sidecar is re-keyed.
|
|
336
|
+
|
|
337
|
+
**Case stage docs (Case route only).** One file per stage, `as-is/stages/<stage-id>.md`, matching the subgraph ids in the diagram. Each carries:
|
|
338
|
+
|
|
339
|
+
- purpose — what the case object is doing while it sits in this stage;
|
|
340
|
+
- entry conditions — what puts the case here, including the labelled transitions that lead in;
|
|
341
|
+
- allowed activities — the work that may happen here, each linking its step doc in `as-is/steps/`;
|
|
342
|
+
- owners and personas — who does the work, who decides;
|
|
343
|
+
- systems and source of truth for this stage;
|
|
344
|
+
- timing — SLA, typical dwell time, what makes a case sit longer;
|
|
345
|
+
- exceptions and subcases — the ad-hoc paths opened from here, and how each closes;
|
|
346
|
+
- evidence — the documents and exports that confirm the above.
|
|
347
|
+
|
|
348
|
+
Also write `as-is/stages.md` as the index: the case object, its lifecycle states in order, and one line per stage linking its doc. A case whose stages exist only as boxes in a diagram is not documented — the stage docs are what a reviewer, an auditor, or the next agent reads.
|
|
349
|
+
|
|
350
|
+
Case evidence refs → maintain `as-is/attachments.md`: YAML frontmatter with an `attachments:` map of stage id or item node id → reference entries, body free for prose. Key every stage by the SAME id the diagram declares in `subgraph <id>["Label"]` — the viewer resolves the stage label's slug too, but the subgraph id is canonical and keeps one stage from being filed under two keys. Write `local-file` paths in full (`/Users/<name>/...`), not `~/...`. The Diagrams view renders the refs as chips on the stage frames, so every stage should carry the evidence it rests on.
|
|
351
|
+
|
|
352
|
+
File a ref against the STAGE when it evidences the stage as a whole (the SOP, the volumetrics export, the interview notes), and against a single WORK ITEM — its node id, the same key an item note uses — when the document belongs to that one step: the form that step fills in, the screenshot of the screen it works, the rule table it applies. The viewer offers an item's own refs on the task itself and the stage's refs alongside them, so a ref filed at the wrong level is still reachable but says the wrong thing about what it evidences. Do not duplicate one ref at both levels.
|
|
353
|
+
|
|
354
|
+
A BPMN capture keys the SAME sidecar (`as-is/attachments.md`) by BPMN element instead: either the element's `id` or the slug of its `name` — `<bpmn:serviceTask id="Task_1" name="Run diagnostics">` answers to `Task_1` and to `run-diagnostics`. Prefer the name slug: BPMNDI ids are generated tokens (`Activity_0abc123`) that change when the model is regenerated, and the name is what the map shows. The viewer badges every element the sidecar names and opens its documents on click. Note that no lint covers the BPMN sidecar — the diagram lint reads Mermaid fences, and `process.bpmn` is XML — so re-key it by hand whenever you rename or remove an element, and check the viewer's orphan banner after a model change.
|
|
355
|
+
|
|
356
|
+
A simple flow capture keys the SAME sidecar by node id, and it is where each activity's steps open from. For every activity node, write a `notes:` entry holding its step table (one row per UI step, as in its step pages) and an `attachments:` `kind: wiki-artifact` ref to each of its step pages in `as-is/steps/`. Clicking the node opens both. Collapsing, splitting, or renaming nodes re-keys these entries in the same rewrite; the diagram lint fails on a dead key (`orphaned-attachment-key`, `orphaned-note-key`).
|
|
357
|
+
|
|
358
|
+
The sidecar has TWO writers: you and the viewer — drag-drop and the stage paperclip add `origin: user` refs with no chat turn. Before every write to `as-is/attachments.md`, re-read the file and merge into its current content; never regenerate it from memory. Preserve every entry you did not deliberately change — a write built from a stale read silently erases user-attached evidence.
|
|
359
|
+
|
|
360
|
+
Two entry kinds:
|
|
361
|
+
|
|
362
|
+
- `kind: wiki-artifact` — a wiki file you wrote (wiki-relative `path`, `origin: generated`), e.g. `business-rules.md`, `metrics.md`, `open-items.md`.
|
|
363
|
+
- `kind: local-file` — a file the USER supplied in this conversation: attached, dropped, or given by path (absolute `path`, `origin: user`, `displayName` = file name). Register these on the stage they evidence; a source the user handed you must not be invisible in the case just because it lives outside the wiki.
|
|
364
|
+
|
|
365
|
+
Only paths the user actually supplied may become `local-file` entries. Never register a path you found by listing directories, guessed, or read from another document — those are not user-provided evidence, and a chip pointing at an arbitrary file on someone's machine is a false provenance claim.
|
|
366
|
+
|
|
367
|
+
Attached evidence must be READ, not just referenced. At every checkpoint, re-read `as-is/attachments.md`; for each `origin: user` ref not yet folded into the documentation, read the file at its `path`, fold what it confirms into the stage doc and capture note, and name it as the source. A ref whose content was never read documents nothing.
|
|
368
|
+
|
|
369
|
+
Capture notes → same frontmatter, a `notes:` map of stage id or item node id (the same keys `attachments:` takes) → what was captured there. Notes are long-form markdown: the diagram shows the first line and opens the full note on click, so write the complete picture, not a teaser. A mature stage note carries what happens here, the systems and owners involved, the rules and thresholds confirmed, where each fact came from (interview, document, export), and the open questions.
|
|
370
|
+
|
|
371
|
+
Notes GROW with the interview. Write a first note when the stage appears, then extend it at every checkpoint as answers arrive: add the confirmed detail, name the new source, and delete an open question when it is answered rather than leaving it to rot. A stage that gained five turns of detail must not still carry its one-line first draft. Write an item note whenever a single step carries its own rule, system, or exception — not only stages.
|
|
372
|
+
|
|
373
|
+
```
|
|
374
|
+
---
|
|
375
|
+
attachments:
|
|
376
|
+
intake:
|
|
377
|
+
- kind: wiki-artifact
|
|
378
|
+
path: as-is/data-inputs-outputs.md
|
|
379
|
+
origin: generated
|
|
380
|
+
category: evidence
|
|
381
|
+
registerInvoice:
|
|
382
|
+
- kind: local-file
|
|
383
|
+
path: /Users/jane/Documents/coupa-entry-form.pdf
|
|
384
|
+
displayName: coupa-entry-form.pdf
|
|
385
|
+
origin: user
|
|
386
|
+
category: evidence
|
|
387
|
+
---
|
|
388
|
+
```
|
|
389
|
+
|
|
390
|
+
Record the chosen format in `as-is/overview.md`, and identify the model of record there. The capture format seeds the TO-BE routing recommendation but never binds it. Legacy projects whose map still lives in `as-is/overview.md` remain readable as a display fallback; any regeneration writes the canonical artifact for the chosen format.
|
|
391
|
+
|
|
392
|
+
## Process Snapshot — the phase checkpoint
|
|
393
|
+
|
|
394
|
+
**Recording-first route** (`SKILL.md` "Recording-first documentation"): no snapshot. Run the closing sequence through step 5 without its self-review, then generate the document; its draft review is this phase's checkpoint.
|
|
395
|
+
|
|
396
|
+
The single AS-IS checkpoint. The source-derived artifact is provisional until this snapshot is confirmed. Fixed template — present exactly these sections, in order, business wording, every time:
|
|
397
|
+
|
|
398
|
+
1. **Profile** — process name, industry and business area, trigger, outcome, volume/frequency, cycle time/SLA.
|
|
399
|
+
2. **Current flow** — a numbered AS-IS validation recap with one item per mapped step: step name; actor; application(s) and screen / UI surface; decision / rule; exception / rework / escalation. Write `none captured` for missing decisions or exceptions so gaps are visible.
|
|
400
|
+
3. **Systems & data** — each system, its role, the key artifacts it produces or consumes.
|
|
401
|
+
4. **Business rules** — rule IDs with one-line descriptions.
|
|
402
|
+
5. **Exceptions & escalations** — trigger, handler, resolution.
|
|
403
|
+
6. **Metrics** — values with measurement method; estimates labeled as estimates.
|
|
404
|
+
7. **What I assumed from your documents** — one line per safe assumption with its source.
|
|
405
|
+
8. **Open gaps** — what the sources could not answer, including the highest-impact unanswered industry-gap probes. Non-map blocking gaps appear here as the batched questions (map-changing ones were already asked before the model was drawn).
|
|
406
|
+
|
|
407
|
+
**Chat rendering contract.** Render the complete review body as normal assistant Markdown, with all eight headings and their actual content, immediately before one AskUser call in the same turn. Never compress the snapshot into the AskUser `intro` or `question`; a brief recap such as "the map is ready" does not count as the Process Snapshot. AskUser contains only the final decision, with `Confirm`, `Change`, and `Attach or record more evidence` as its options (plus only the blocking questions already carried by Open gaps). The snapshot is the quick-glance review surface; the AskUser card is only its response control.
|
|
408
|
+
|
|
409
|
+
Keep provenance and confidence on every sourced statement; label assumptions and open gaps. Do not paste Mermaid or BPMN source — the validated process map is already rendering in the side panel when the snapshot is sent (never send the snapshot before the artifact passes validation), and the snapshot tells the user so in one line: "The process map is in the side panel — worth a look before you confirm." When the capture ran without documents, section 7 is titled "What I assumed" instead. End with exactly one decision: *"Confirm / Change / Attach or record more evidence?"* (plus the batched blocking questions from section 8 when any exist — plain sentences, no markdown inside questions). On confirmation the phase is done; corrections are edited into the wiki and only the affected snapshot sections are re-presented.
|
|
410
|
+
|
|
411
|
+
## Closing Phase 1
|
|
412
|
+
|
|
413
|
+
**Close this phase on its output.** Before presenting the Process Snapshot, run the readiness check as the
|
|
414
|
+
last silent step — it lists what is still unwritten, and a review presented with the
|
|
415
|
+
pages missing has closed nothing:
|
|
416
|
+
|
|
417
|
+
```
|
|
418
|
+
bash "{BusinessAnalysisSkillDir}/scripts/check-phase-ready.sh" --wiki "{WikiPath}" --phase as-is --route <case|bpmn|rpa>
|
|
419
|
+
```
|
|
420
|
+
|
|
421
|
+
On Windows:
|
|
422
|
+
|
|
423
|
+
```
|
|
424
|
+
& "{BusinessAnalysisSkillDir}\scripts\check-phase-ready.ps1" -Wiki "{WikiPath}" -Phase as-is -Route <case|bpmn|rpa>
|
|
425
|
+
```
|
|
426
|
+
|
|
427
|
+
`PHASEREADY:ok` is the only result that closes the phase. On `PHASEREADY:not-ready`,
|
|
428
|
+
write the pages and columns it names from the facts you have already confirmed, then
|
|
429
|
+
run it again. It never writes anything, so re-running it is free, and it fails open
|
|
430
|
+
with `PHASEREADY:skipped` if it cannot resolve the wiki — which is not a pass.
|
|
431
|
+
|
|
432
|
+
Closing sequence — do all, in order, silently until step 7:
|
|
433
|
+
|
|
434
|
+
1. **Industry gap pass (mandatory, once, silent).** Read `industry-gaps.md`. Pull probes matching Opening Funnel industry + business area, then **answer as many as possible from the sources before involving the user**: evidenced in a source → fold into `entities/`/`as-is/` with provenance; contradicted or clearly out of scope → skip it. The remaining highest-impact unanswered probes (cap 6-8) go into the Process Snapshot's **Open gaps** section — never a separate chat round; the rest become `missing` task list rows. If this writes facts, complete the task list synchronization boundary before continuing. Record the pass result (`N probes folded / no matching section`) in `log.md` at phase close. No silent skips of the pass itself.
|
|
435
|
+
2. Write the current-state framing prose and any remaining factual content to `as-is/overview.md` and the relevant supporting pages. **Persist the snapshot's Open gaps and every carried assumption to `queries/open-questions.md`** (one line each: the gap or assumption, its impact, and where it surfaced) — this page feeds the PDD's assumptions/risks and next steps; open items that live only in chat are lost. Wait for the write results.
|
|
436
|
+
3. **TaskList synchronization gate.** Make the next mutation one `project-task-list` update of `TaskListPath`: every affected FACTS row gets its `answer` + `provenance` (wiki path) and `status` (`from docs` / `needs confirmation` / `missing`). Do not write the AS-IS process artifact until this gate succeeds.
|
|
437
|
+
4. Produce the AS-IS process artifact, drawing gateways from the Decision pass tables, per "AS-IS process artifact — ask the capture format" above (the format question, when needed, was part of the pre-drawing batch): `as-is/process.bpmn` for BPMN, or `as-is/diagram.md` (`case-design` / `generic`) for a case map or simple flow. Identify the model of record in `as-is/overview.md`. The Delegate interface renders the artifact for the user. Do NOT paste the source into chat, not even when asking for feedback. A diagram-only correction needs another task list mutation only when it changes a business fact; in that case update the supporting factual page and pass the synchronization gate before presenting it.
|
|
438
|
+
5. Validate the artifact per its format: BPMN → the Mandatory saved-artifact validation from `bpmn-to-be-design.md` (real XML parse + reference checks); case map or simple flow → read `as-is/diagram.md` back and complete the diagram source audit in `diagram-authoring.md` (lint until `DIAGRAMLINT:ok`; case maps additionally pass the case source audit in `diagram-authoring.md`). Repair and re-validate until it passes. **The snapshot may not be sent until the artifact passes** — do not present the map, recap AS-IS, or offer to start TO-BE while the canonical artifact is missing or fails validation. Then run this phase's one self-review, before the snapshot and never after it (SKILL.md "One Review Per Phase"): one pass, one fix round, and whatever it still leaves goes into the snapshot's Open gaps — never a second pass.
|
|
439
|
+
6. Record this phase's Process Knowledge checkpoint in `process-knowledge.md` — its phase, focus and result status — for every retrieval the phase made, including the ones that matched nothing. A call whose result was never written down is not a checkpoint, and the next session reads the file, not this conversation: an unrecorded retrieval is one the project has to make again.
|
|
440
|
+
7. **MANDATORY STOP — present the Process Snapshot** (fixed template above; its Current flow section is the numbered AS-IS validation recap). Never send it before steps 4–5 succeeded: if the model file is missing or unvalidated, produce and validate it first — the user must be able to see the map in the panel at the moment the snapshot arrives. This is the phase's one checkpoint: assumptions disclosed in section 7, remaining gaps and batched blocking questions in section 8, one decision — *"Confirm / Change / Attach or record more evidence?"*. On change request, edit the wiki and the AS-IS process artifact, then re-present only the affected sections; don't iterate without new user input. Once the user confirms, stamp `verified` on the confirmed `as-is/` pages per SKILL.md Page Trust Stamps, call `AskUserFeedback` with `checkpoint: 'ba.asIsCaptured'` (one non-blocking call; do not announce it or wait for a rating; skip silently if the tool is unavailable), and close with one line stating the future-process design can start whenever they're ready (the first ```sf chip carries that next step). Do not ask an additional "start now?" question — the snapshot confirmation ends the phase. From here those pages are `verified`: a factual change to one of them is named in chat, in the same reply that makes it (SKILL.md "Editing a confirmed page").
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
kind: progress
|
|
2
|
+
locale-skill: business-analysis
|
|
3
|
+
title-key: progress.group.title
|
|
4
|
+
current: discovery
|
|
5
|
+
steps:
|
|
6
|
+
- id: discovery
|
|
7
|
+
label-key: progress.phases.discovery
|
|
8
|
+
- id: as-is
|
|
9
|
+
label-key: progress.phases.asIs
|
|
10
|
+
- id: to-be
|
|
11
|
+
label-key: progress.phases.toBe
|
|
12
|
+
- id: validate-to-be
|
|
13
|
+
label-key: progress.phases.validateToBe
|
|
14
|
+
- id: architect-process
|
|
15
|
+
label-key: progress.phases.architectProcess
|
|
16
|
+
- id: architect-solution
|
|
17
|
+
label-key: progress.phases.architectSolution
|
|
18
|
+
- id: handoff
|
|
19
|
+
label-key: progress.phases.handoff
|
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
---
|
|
2
|
+
schemaId: answer-flow
|
|
3
|
+
statusPresets:
|
|
4
|
+
- label: from docs
|
|
5
|
+
color: accent
|
|
6
|
+
- label: needs confirmation
|
|
7
|
+
color: warning
|
|
8
|
+
- label: missing
|
|
9
|
+
color: neutral
|
|
10
|
+
stages:
|
|
11
|
+
- id: facts_as_is
|
|
12
|
+
title: Facts (as-is)
|
|
13
|
+
- id: analysis_to_be
|
|
14
|
+
title: Analysis (to-be)
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
# Project TaskList
|
|
18
|
+
|
|
19
|
+
- [ ] Identity & domain [id:: chk_identity_domain_5de015] [stage:: facts_as_is] [status:: pending]
|
|
20
|
+
- [ ] Source inventory [id:: chk_source_inventory_ef1e5c] [stage:: facts_as_is] [status:: pending]
|
|
21
|
+
- [ ] Process frame [id:: chk_process_frame_2ac698] [stage:: facts_as_is] [status:: pending]
|
|
22
|
+
- [ ] Systems & data observed [id:: chk_systems_data_59b2e0] [stage:: facts_as_is] [status:: pending]
|
|
23
|
+
- [ ] Compliance & policy terms [id:: chk_compliance_policy_559e9c] [stage:: facts_as_is] [status:: pending]
|
|
24
|
+
- [ ] Metrics & mining signals [id:: chk_metrics_mining_4a68c7] [stage:: facts_as_is] [status:: pending]
|
|
25
|
+
- [ ] Pain points & aspirations [id:: chk_pain_points_418631] [stage:: facts_as_is] [status:: pending]
|
|
26
|
+
- [ ] Process model [id:: chk_stage_model_7445bc] [stage:: analysis_to_be] [status:: pending]
|
|
27
|
+
- [ ] Activities & tasks [id:: chk_stage_tasks_b74068] [stage:: analysis_to_be] [status:: pending]
|
|
28
|
+
- [ ] Personas [id:: chk_personas_fa2ea3] [stage:: analysis_to_be] [status:: pending]
|
|
29
|
+
- [ ] Integrations to build [id:: chk_integrations_90a6e3] [stage:: analysis_to_be] [status:: pending]
|
|
30
|
+
- [ ] Data entities [id:: chk_data_entities_39689d] [stage:: analysis_to_be] [status:: pending]
|
|
31
|
+
- [ ] Compliance controls [id:: chk_compliance_controls_9a9baf] [stage:: analysis_to_be] [status:: pending]
|
|
32
|
+
- [ ] KPIs [id:: chk_kpis_5bfb14] [stage:: analysis_to_be] [status:: pending]
|
|
33
|
+
- [ ] Improvements [id:: chk_improvements_c3eb9e] [stage:: analysis_to_be] [status:: pending]
|
|
34
|
+
- [ ] Design decisions, conflicts & assumptions [id:: chk_design_decisions_992fea] [stage:: analysis_to_be] [status:: pending]
|
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
# Automation Hub publishing — the handoff
|
|
2
|
+
|
|
3
|
+
Read this file on a publish request — a click on a publish chip, or the user asking in their own words. The request is itself the approval, so act on it immediately. Offer timing and silence rules live in `SKILL.md` ("Automation Hub publishing"); this file owns everything from the request onward.
|
|
4
|
+
|
|
5
|
+
Resolve the signed-in user's login email first — the turn's User Context carries it. Where it does not, ask the user for their Automation Hub address, or say publishing needs their Automation Hub access and stop. The publish records an owner and a submitter, and that address is the only value here with no substitute.
|
|
6
|
+
|
|
7
|
+
Then activate `uipath-automationhub` with the `Skill` tool and let it run the publish. Success is what its response says, so wait for it. Skill absent → say Automation Hub publishing is unavailable and continue; nothing else here depends on it. Skill present but its CLI path unavailable → **When the CLI path is unavailable**, below.
|
|
8
|
+
|
|
9
|
+
## Pick the files
|
|
10
|
+
|
|
11
|
+
From `{DraftsDir}`, supply exactly one file per document type (`PDD` or `SDD`) — the Automation Hub skill attaches everything it is handed, and otherwise spends a question asking which format to keep:
|
|
12
|
+
|
|
13
|
+
1. `<process-slug>-<TYPE>.docx` when it is present **and its mtime is at or after the `.md`'s** — the formatted export reads better in Automation Hub. The host regenerates the `.docx` only at Download, so an edit or re-sync since then leaves it a pre-edit copy.
|
|
14
|
+
2. Otherwise `<process-slug>-<TYPE>.md` — the living draft, always present and always current.
|
|
15
|
+
|
|
16
|
+
Compare the two mtimes before choosing; publishing the older `.docx` publishes content the user already changed.
|
|
17
|
+
|
|
18
|
+
## Pass to it
|
|
19
|
+
|
|
20
|
+
- The confirmed process name and description.
|
|
21
|
+
- `ProjectId` and `ProjectName` from context — the originating Delegate project.
|
|
22
|
+
- The signed-in user's login email from the turn's User Context — the publisher, and the owner and submitter to record.
|
|
23
|
+
- For each document: its absolute path, its type (`PDD` or `SDD`), and its mimetype (`.docx` → `application/vnd.openxmlformats-officedocument.wordprocessingml.document`, `.md` → `text/markdown`).
|
|
24
|
+
|
|
25
|
+
Then state the two things it cannot know:
|
|
26
|
+
|
|
27
|
+
1. Record the originating project on the created Business Process — a live schema field when the tenant's idea schema exposes one, otherwise append `ProjectName` to the description.
|
|
28
|
+
2. That login email is the owner and the submitter. Where Automation Hub does not list it, ask the user which of the listed addresses is theirs, or report that publishing needs their Automation Hub access. Publishing a person's document under another account's name is a wrong result, not a fallback.
|
|
29
|
+
|
|
30
|
+
Transport, authentication, schema discovery, category resolution, duplicate names, and returned ids belong to that skill and change on its release cadence — read them there, not here.
|
|
31
|
+
|
|
32
|
+
## When the CLI path is unavailable
|
|
33
|
+
|
|
34
|
+
The skill's CLI transport needs `uip ah`, which a host can ship without: `uip` is a dispatcher and the Automation Hub verb is its own package. When the skill reports `uip ah` unavailable — `unknown command 'ah'`, or a fall-through to its raw Open API flow — do **not** let it run that flow here. Its raw flow is shell HTTP, and the Delegate sandbox denies shell HTTP: the call dies at DNS and the user is told their network policy blocked Automation Hub, which is false.
|
|
35
|
+
|
|
36
|
+
Instead, run the publish from this skill over the `SendUiPathRequest` tool, following `references/automation-hub-open-api.md` in full — same inputs as **Pass to it**, same two statements. Never `curl`. Never `x-ah-openapi-auth`. If `SendUiPathRequest` is not available either, say plainly that this build ships without the Automation Hub CLI tool and cannot reach Automation Hub, and continue; do not describe it as a network problem.
|
|
37
|
+
|
|
38
|
+
## Report
|
|
39
|
+
|
|
40
|
+
After the Automation Hub skill reports a successful publish, resolve all four facts from its response or read them back from Automation Hub — on the fallback path, from the `idea-from-schema` and `documents` responses in `references/automation-hub-open-api.md`. Report them with these labels:
|
|
41
|
+
|
|
42
|
+
- `Process ID: <id>`
|
|
43
|
+
- `Document IDs: <id per published document>`
|
|
44
|
+
- `Owner: <resolved owner>`
|
|
45
|
+
- `Originating project route: <route>`
|
|
46
|
+
|
|
47
|
+
For the route, name either the Automation Hub schema field or the description fallback.
|