create-yss-spec 1.1.2 → 1.1.4

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-yss-spec",
-  "version": "1.1.2",
+  "version": "1.1.4",
   "description": "Initialize a YSS spec project template repository",
   "files": [
     "bin",

package/template/.agents/skills/excalidraw-diagram-generator/SKILL.md

@@ -33,7 +33,7 @@ Use this skill when users request:
 
 ## YSS Lifecycle Integration
 
-In YSS projects, this skill is a visualization and review aid. It can clarify lifecycle artifacts, but it must not replace Discovery, PRD, OpenAPI, ADR, OpenSpec/Comet design, or tests.
+In YSS projects, this skill is a visualization and review aid. It can clarify lifecycle artifacts, but it must not replace Discovery, PRD, OpenAPI, ADR, Spec Delta design, or tests.
 
 Use it after the relevant source artifact exists:
 
@@ -41,14 +41,14 @@ Use it after the relevant source artifact exists:
 |--------------------|----------------|-----------------|--------------------|
 | Business architecture | Opportunity exploration / Discovery | user journey, value stream, swimlane, capability map, ecosystem map | `docs/discovery/diagrams/` or `docs/architecture/diagrams/` |
 | Functional architecture | PRD baseline / product design / PRD calibration | feature map, module map, dependency graph, page map | `docs/design/diagrams/` or `docs/architecture/diagrams/` |
-| System architecture | Engineering baseline / Architecture / OpenSpec / Comet design | C4/container view, deployment, sequence, DDD boundary, DFD | `docs/architecture/diagrams/` |
+| System architecture | Engineering baseline / Architecture / Spec Delta design | C4/container view, deployment, sequence, DDD boundary, DFD | `docs/architecture/diagrams/` |
 | Data architecture | Detailed design before persistence / repository work | ER, class, meta-model, lineage graph, query/data-flow diagram | `docs/architecture/diagrams/` |
 
 Guardrails:
 
 - Do not invent product requirements or architecture decisions only from the diagram prompt.
 - Reference the source artifact in the Markdown document that links the `.excalidraw` file.
-- If a diagram exposes a missing field, unclear state, dependency, or boundary problem, write that finding back to the source PRD, OpenAPI Draft, architecture document, ADR, OpenSpec/Comet design, or issue.
+- If a diagram exposes a missing field, unclear state, dependency, or boundary problem, write that finding back to the source PRD, OpenAPI Draft, architecture document, ADR, Spec Delta design, or issue.
 - Do not require diagrams for small copy, style, configuration, or single-point bug fixes.
 - For data modeling, metadata management, model versioning, or lineage-analysis products, prefer ER, class/meta-model, DFD, and lineage diagrams before persistence implementation.
 

package/template/.agents/skills/grill-me/SKILL.md

@@ -0,0 +1,7 @@
+---
+name: grill-me
+description: A relentless interview to sharpen a plan or design.
+disable-model-invocation: true
+---
+
+Run a `/grilling` session.

package/template/.agents/skills/grilling/SKILL.md

@@ -0,0 +1,12 @@
+---
+name: grilling
+description: Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
+---
+
+Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
+
+Ask the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering.
+
+If a *fact* can be found by exploring the codebase, look it up rather than asking me. The *decisions*, though, are mine — put each one to me and wait for my answer.
+
+Do not enact the plan until I confirm we have reached a shared understanding.

package/template/.agents/skills/handoff/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: handoff
+description: Compact the current conversation into a handoff document for another agent to pick up.
+argument-hint: "What will the next session be used for?"
+disable-model-invocation: true
+---
+
+Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS - not the current workspace.
+
+Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.
+
+Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
+
+Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
+
+If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.

package/template/.agents/skills/to-issues/SKILL.md

@@ -54,7 +54,7 @@ Iterate until the user approves the breakdown.
 
 For each approved slice, publish a new issue to the issue tracker. Use the issue body template below. These issues are considered ready for AFK agents, so publish them with the correct triage label unless instructed otherwise.
 
-Publish issues in dependency order (blockers first) so you can reference real issue identifiers in the "Blocked by" field.
+Publish issues in dependency order (blockers first) so you can reference real issue identifiers. Where the tracker supports it, link each slice to its parent as a native **sub-issue** and wire each blocker as a native **blocking edge** (mechanics in the issue-tracker doc); the `## Parent` and `## Blocked by` body sections are the fallback otherwise.
 
 <issue-template>
 ## Parent
@@ -65,7 +65,7 @@ A reference to the parent issue on the issue tracker (if the source was an exist
 
 A concise description of this vertical slice. Describe the end-to-end behavior, not layer-by-layer implementation.
 
-Avoid specific file paths or code snippets — they go stale fast. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it here and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.
+Avoid specific file paths or code snippets — they go stale fast. Exception: if the `/prototype` skill produced code that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), add a context pointer to where that prototype code lives rather than inlining it.
 
 ## Acceptance criteria
 

package/template/.claude/skills/grill-me/SKILL.md

@@ -0,0 +1,7 @@
+---
+name: grill-me
+description: A relentless interview to sharpen a plan or design.
+disable-model-invocation: true
+---
+
+Run a `/grilling` session.

package/template/.claude/skills/grilling/SKILL.md

@@ -0,0 +1,12 @@
+---
+name: grilling
+description: Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
+---
+
+Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
+
+Ask the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering.
+
+If a *fact* can be found by exploring the codebase, look it up rather than asking me. The *decisions*, though, are mine — put each one to me and wait for my answer.
+
+Do not enact the plan until I confirm we have reached a shared understanding.

package/template/.claude/skills/handoff/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: handoff
+description: Compact the current conversation into a handoff document for another agent to pick up.
+argument-hint: "What will the next session be used for?"
+disable-model-invocation: true
+---
+
+Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS - not the current workspace.
+
+Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.
+
+Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
+
+Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
+
+If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.

package/template/.claude/skills/to-issues/SKILL.md

@@ -54,7 +54,7 @@ Iterate until the user approves the breakdown.
 
 For each approved slice, publish a new issue to the issue tracker. Use the issue body template below. These issues are considered ready for AFK agents, so publish them with the correct triage label unless instructed otherwise.
 
-Publish issues in dependency order (blockers first) so you can reference real issue identifiers in the "Blocked by" field.
+Publish issues in dependency order (blockers first) so you can reference real issue identifiers. Where the tracker supports it, link each slice to its parent as a native **sub-issue** and wire each blocker as a native **blocking edge** (mechanics in the issue-tracker doc); the `## Parent` and `## Blocked by` body sections are the fallback otherwise.
 
 <issue-template>
 ## Parent
@@ -65,7 +65,7 @@ A reference to the parent issue on the issue tracker (if the source was an exist
 
 A concise description of this vertical slice. Describe the end-to-end behavior, not layer-by-layer implementation.
 
-Avoid specific file paths or code snippets — they go stale fast. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it here and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.
+Avoid specific file paths or code snippets — they go stale fast. Exception: if the `/prototype` skill produced code that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), add a context pointer to where that prototype code lives rather than inlining it.
 
 ## Acceptance criteria
 

package/template/.codex/skills/cross-repo-implementation-routing/SKILL.md

@@ -9,7 +9,7 @@ description: Use when a Harness change or vertical slice may require work across
 
 ## Inputs
 
-- Harness change / OpenSpec / Comet change。
+- Harness change / Spec Delta change。
 - 垂直切片 Issue 或实施计划。
 - OpenAPI Freeze 或无 API 影响记录。
 - 已登记的实现仓库记录；没有登记时先使用 `implementation-repo-onboarding`。

package/template/.codex/skills/data-analytics/.app.json

@@ -0,0 +1,84 @@
+{
+  "apps": {
+    "slack": {
+      "id": "REPLACE_WITH_SLACK_APP_OR_CONNECTOR_ID"
+    },
+    "teams": {
+      "id": "connector_246af0940da3457da0e751171dc1ce60",
+      "optional": true
+    },
+    "notion": {
+      "id": "REPLACE_WITH_NOTION_APP_OR_CONNECTOR_ID"
+    },
+    "gmail": {
+      "id": "connector_2128aebfecb84f64a069897515042a44",
+      "optional": true
+    },
+    "outlook_email": {
+      "id": "connector_4aaab2856305417b993eca9a216aaf6e",
+      "optional": true
+    },
+    "outlook_calendar": {
+      "id": "connector_e6a7394682e24467ac68c60696f275a4",
+      "optional": true
+    },
+    "google_calendar": {
+      "id": "connector_947e0d954944416db111db556030eea6",
+      "optional": true
+    },
+    "google_drive": {
+      "id": "connector_5f3c8c41a1e54ad7a76272c89e2554fa"
+    },
+    "databricks": {
+      "id": "templated_apps_Databricks",
+      "optional": true
+    },
+    "bigquery": {
+      "id": "connector_7c3f2c8cdbf64bb0b183ff52f527a06e",
+      "optional": true
+    },
+    "snowflake": {
+      "id": "templated_apps_Snowflake",
+      "optional": true
+    },
+    "sharepoint": {
+      "id": "connector_1e4f6a44acf14e3ca1d96672f8c945bc",
+      "optional": true
+    },
+    "github": {
+      "id": "connector_76869538009648d5b282a4bb21c3d157"
+    },
+    "statsig": {
+      "id": "REPLACE_WITH_STATSIG_APP_OR_CONNECTOR_ID",
+      "optional": true
+    },
+    "hex": {
+      "id": "REPLACE_WITH_HEX_APP_OR_CONNECTOR_ID",
+      "optional": true
+    },
+    "deepnote": {
+      "id": "REPLACE_WITH_DEEPNOTE_APP_OR_CONNECTOR_ID",
+      "optional": true
+    },
+    "amplitude": {
+      "id": "REPLACE_WITH_AMPLITUDE_APP_OR_CONNECTOR_ID",
+      "optional": true
+    },
+    "mixpanel": {
+      "id": "REPLACE_WITH_MIXPANEL_APP_OR_CONNECTOR_ID",
+      "optional": true
+    },
+    "omni-analytics": {
+      "id": "REPLACE_WITH_OMNI_ANALYTICS_APP_OR_CONNECTOR_ID",
+      "optional": true
+    },
+    "metabase": {
+      "id": "templated_apps_Metabase",
+      "optional": true
+    },
+    "thoughtspot": {
+      "id": "REPLACE_WITH_THOUGHTSPOT_APP_OR_CONNECTOR_ID",
+      "optional": true
+    }
+  }
+}

package/template/.codex/skills/data-analytics/.codex-plugin/plugin.json

@@ -0,0 +1,66 @@
+{
+  "name": "data-analytics",
+  "version": "0.1.34",
+  "description": "Analyze product usage, investigate metric movements, prepare KPI reports, build high-quality dashboards and notebooks, create source-backed semantic layers, guide first-run analytics setup, and generate analytics-grade report apps.",
+  "author": {
+    "name": "Data Analytics Maintainers"
+  },
+  "homepage": "https://github.com/openai/role-specific-plugins",
+  "repository": "https://github.com/openai/role-specific-plugins/tree/main/plugins/data-analytics",
+  "license": "MIT",
+  "keywords": [
+    "data-analytics",
+    "analytics",
+    "business-context",
+    "dashboards",
+    "funnel-analysis",
+    "kpi-reporting",
+    "market-sizing",
+    "metric-diagnostics",
+    "post-launch-updates",
+    "product-analysis",
+    "retention",
+    "root-cause-analysis",
+    "scorecards",
+    "validation",
+    "visualization",
+    "jupyter-notebooks",
+    "databricks",
+    "bigquery",
+    "snowflake",
+    "deepnote",
+    "mixpanel",
+    "mixpanel-headless",
+    "metabase",
+    "thoughtspot",
+    "onboarding",
+    "semantic-layer"
+  ],
+  "skills": "./skills/",
+  "apps": "./.app.json",
+  "mcpServers": "./.mcp.json",
+  "interface": {
+    "displayName": "Data Analytics",
+    "shortDescription": "Turn data into clear decisions",
+    "longDescription": "Turn analytical questions into validated answers, dashboards, reports, notebooks, and clear recommendations. Explore product and business data, explain why key metrics changed, design KPIs, size opportunities, check data quality, and save reusable metric and source context for future work.\n\nStart with connected warehouses, BI tools, product analytics, docs, chat, spreadsheets, or uploaded files. Guided onboarding helps you connect core tools and set up reusable data context, while interactive charts, tables, dashboards, and report apps keep the evidence reviewable and ready to share.",
+    "developerName": "OpenAI",
+    "category": "Analytics",
+    "capabilities": [
+      "Interactive",
+      "Read",
+      "Write"
+    ],
+    "websiteURL": "https://openai.com/",
+    "privacyPolicyURL": "https://openai.com/policies/privacy-policy/",
+    "termsOfServiceURL": "https://openai.com/policies/terms-of-use/",
+    "defaultPrompt": [
+      "Help me get started and set up reusable data context for future data work",
+      "Analyze product usage and recommend where the team should focus next",
+      "Diagnose why a key metric changed and identify the biggest drivers"
+    ],
+    "brandColor": "#0285FF",
+    "composerIcon": "./assets/datascience-small.svg",
+    "logo": "./assets/datascience.png",
+    "screenshots": []
+  }
+}

package/template/.codex/skills/data-analytics/.mcp.json

@@ -0,0 +1,30 @@
+{
+  "mcpServers": {
+    "datascienceWidgets": {
+      "title": "Data Analytics Widgets",
+      "description": "Render Data Analytics charts, tables, dashboards, and report artifacts.",
+      "icons": [
+        {
+          "src": "./assets/datascience-small.svg",
+          "mimeType": "image/svg+xml",
+          "sizes": [
+            "24x24"
+          ]
+        },
+        {
+          "src": "./assets/datascience.png",
+          "mimeType": "image/png",
+          "sizes": [
+            "360x360"
+          ]
+        }
+      ],
+      "cwd": ".",
+      "command": "node",
+      "args": [
+        "./mcp/server.cjs",
+        "--stdio"
+      ]
+    }
+  }
+}

package/template/.codex/skills/data-analytics/AGENTS.md

@@ -0,0 +1,20 @@
+# Data Analytics MCP Apps
+
+## Purpose
+
+This plugin contains a complex fullscreen analytics artifact workspace plus compact inline chart and table widgets. Preserve that architecture when iterating: artifacts are snapshot-first workspaces, while chart and table widgets are focused views of reviewed query results.
+
+## Visual Style
+
+Follow the local Codex style contract in `src/codex-style-contract.md`.
+`src/styles/codex-theme.css` is the copied Codex fallback baseline and must load before `src/analytics-app/tokens.css`. Shared surfaces, controls, typography, spacing, borders, radii, shadows, focus, and motion should resolve through the Codex tokens. Analytics CSS may extend the baseline for charts, KPI states, tables, report widths, and dashboard layouts.
+
+## Fullscreen Behavior
+
+Inline surfaces that support fullscreen expose a compact top-right fullscreen control and hide it after fullscreen is active.
+
+## Workflow
+
+Before future changes, start with the installed `codex-mcp-app-devkit` skill so it can route to the app-development workflow and the Codex visual references. Use `npm run preview:widgets` for local previews, `npm run build` for all widget bundles, `npm run typecheck` for TypeScript, and `npm test` for MCP server and widget contract coverage.
+
+The plugin package is materialized directly from this directory. After changing widget source, run `npm run build` so `assets/` and normalized bundle parts stay aligned, then reinstall the updated development plugin from the Plugin Development marketplace when testing inside Codex.

package/template/.codex/skills/data-analytics/DEPENDENCIES.MD

@@ -0,0 +1,27 @@
+# Dependencies
+
+## How tool references work
+
+Data Analytics plugin files use lane placeholders such as `~~structured_data` for whatever source the user connects or provides in that category. For example, `~~structured_data` might mean a warehouse connector, SQL runner, API/CLI result, pasted query output, uploaded file, or schema description.
+
+The plugin is tool-agnostic. It describes workflows in terms of analysis lanes rather than one required stack. Direct connectors give the best experience, but the workflows should still be useful with pasted results, SQL snippets, screenshots, exports, or uploaded files.
+
+## Dependencies for this plugin
+
+| Category | Placeholder | Providers | Purpose |
+| --- | --- | --- | --- |
+| Data warehouse | `~~structured_data` | Databricks, BigQuery, Snowflake, Redshift, PostgreSQL, MySQL | Query tables, explore schemas, and produce result sets. Databricks, BigQuery, and Snowflake are declared in `.app.json` as app-backed connector choices. |
+| Notebook lab | `~~notebook_lab` | Hex, Deepnote, Jupyter | Iterate, preserve reusable code, and support richer exploratory work. Hex and Deepnote are declared in `.app.json` as app-backed connector choices. |
+| Behavior signals | `~~behavior_signals` | Amplitude, Mixpanel, Mixpanel Headless | Analyze product event trends and funnels. Amplitude and Mixpanel are declared in `.app.json`; Mixpanel Headless is a companion plugin/skill path when installed. |
+| Dashboards and BI | `~~dashboards_or_bi` | ThoughtSpot, Omni Analytics, Metabase, dashboard/BI app | Inspect dashboard metadata, metric definitions, widget SQL, and BI answers. ThoughtSpot, Omni Analytics, and Metabase are declared in `.app.json` as app-backed connector choices. |
+| Team communication | `~~team_communication` | Slack, Microsoft Teams | Search recent decisions, blockers, owner confirmations, and links to durable artifacts |
+| Email context | `~~email_context` | Gmail, Outlook Email | Inspect relevant message threads, stakeholder context, and follow-up history |
+| Calendar context | `~~calendar_context` | Outlook Calendar | Check meeting timing, attendees, and operating cadence context |
+| Company docs | `~~company_docs` | Google Drive, SharePoint, Google Docs, Google Slides, Notion | Read workspace knowledge, PRDs, metric docs, strategy docs, and source caveats |
+| Sheet workspace | `~~spreadsheet_workspace` | Google Drive, SharePoint, Google Sheets | Review small exports, manual QA, and stakeholder-friendly tables |
+| Presentation surface | `~~presentation_surface` | Google Drive, SharePoint, Google Docs, Google Slides | Create final charts, dashboards, and share-ready narratives |
+| Code repository | `~~code_repository` | GitHub, local checkout | Inspect source logic, model SQL, lineage, tests, and repo context |
+| Files, notebooks, or spreadsheets | `~~files_and_notebooks` | Google Drive, SharePoint, local files, uploaded files, notebooks, spreadsheets | Use local or uploaded analysis inputs, notebooks, CSVs, and spreadsheets |
+| Application hosting | `~~application_hosting` | Site Creator | Host reports, deployed app links, and previewable interactive artifacts |
+| Planning tracker | `~~planning_tracker` | Atlassian, Linear, Asana, Jira | Track analysis requests, owners, deadlines, and dependencies |
+| Data operations | `~~operations_logs` | Airflow | Check pipeline freshness, model ownership, lineage, and outage context |

package/template/.codex/skills/data-analytics/README.md

@@ -0,0 +1,60 @@
+# Data Analytics
+
+Answer product and business questions with data, explain why metrics changed, and turn analysis into reports, dashboards, and clear decisions.
+
+## When to use this plugin
+
+Use Data Analytics when you need to understand product or business performance, explain why a metric changed, define a success measurement plan, assess whether data is trustworthy, or package analysis for stakeholders. You can start from connected data in a data warehouse, dashboards, notebooks, spreadsheets, uploaded files, or pasted context.
+
+## Onboarding
+
+Ask Codex:
+
+`@Data Analytics Help me get started and set up reusable data context for future data work`
+
+Data Analytics has a guided onboarding flow that helps confirm the right data sources, save reusable metric and source-of-truth context you provide, and build a context-specific first analysis prompt.
+
+Onboarding is an interactive, step-by-step conversation. Codex will guide you through setup, ask for approval before making changes, and help you try a first workflow.
+
+Already have a focused task? Start directly with one of the workflows below.
+
+## Example workflows
+
+The primary hero workflow is bolded.
+
+| Workflow | Try this | Skill | Result |
+| --- | --- | --- | --- |
+| **Analyze a product or business question** | `Analyze activation and recommend where the team should focus next` | `product-business-analysis` | A decision-ready analysis with evidence, measurable opportunities, and a clear recommendation |
+| Diagnose a metric movement | `Diagnose why weekly active users dropped last week` | `metric-diagnostics` | A calibrated explanation of verified drivers, likely contributors, unresolved questions, and next actions |
+| Design KPIs | `Design a KPI framework for this new product area` | `design-kpis` | A measurement plan with outcome metrics, drivers, guardrails, targets, and validation priorities |
+| Prepare a KPI readout | `Turn this month's metrics into a leadership-ready operating update` | `kpi-reporting` | A concise KPI update with actuals, comparisons, validated drivers, and operating implications |
+| Build a dashboard | `Build a dashboard for monitoring activation, retention, and conversion` | `build-dashboard` | A source-backed dashboard with metrics, filters, visual hierarchy, QA, and handoff |
+| Size a market | `Estimate the market opportunity for this product and show the assumptions` | `market-sizing` | A transparent market or opportunity sizing estimate with sensitivity, uncertainty, and validation priorities |
+| Build an analytical report | `Create an executive report explaining the biggest growth drivers this quarter` | `build-report` | A polished report with answer-first narrative, charts, tables, caveats, and source metadata |
+| Improve or render a chart | `Turn this analysis into a clear chart for the product review` | `visualize-data` | A production-ready visual with the right chart type, labels, hierarchy, and accessibility checks |
+| Create a notebook | `Build a reproducible notebook for this experiment readout` | `jupyter-notebooks` | A clean SQL or Python notebook that can be skimmed, rerun, and extended |
+| Work with spreadsheets | `Analyze this workbook and add a polished summary tab` | `spreadsheets` | A verified spreadsheet artifact with formulas, formatting, charts, tables, and a clear readout |
+| Validate an analysis | `Review this analysis before I share it with leadership` | `validate-data` | A QA pass covering methodology, sources, calculations, analytical pitfalls, caveats, and conclusion strength |
+| Assess data quality | `Check whether this table is reliable enough for our retention analysis` | `analyze-data-quality` | A source-backed quality assessment covering grain, freshness, missingness, duplicates, joins, and material risks |
+
+## Integrations
+
+Data Analytics can use available tools when they are connected:
+
+| Source | Supported integrations | What they unlock |
+| --- | --- | --- |
+| Warehouses and query tools | Databricks, Databricks Genie, BigQuery, Snowflake | Schema inspection, query-backed analysis, and source-grounded metric investigation |
+| Product analytics and BI | Amplitude, Mixpanel, Omni Analytics, Metabase, ThoughtSpot, Statsig | Behavior analysis, dashboard context, experiment evidence, and reusable reporting inputs |
+| Notebooks and analytical workspaces | Hex, Deepnote | Reproducible analysis, notebook handoff, and shared analytical context |
+| Docs and collaboration | Google Drive, SharePoint, Notion, GitHub, Slack, Microsoft Teams | Business definitions, source-of-truth documents, implementation context, and stakeholder evidence |
+| Email and calendar | Gmail, Outlook Email, Outlook Calendar | Supporting context for stakeholder questions, operating cadence, and analytical handoff |
+
+You can also start with spreadsheets, uploaded files, pasted query results, schema descriptions, or manually provided business context.
+
+## Local development
+
+The published plugin does not require users to install Node.js dependencies. For local development of the Data Analytics MCP server and widgets, install dependencies from the plugin directory:
+
+```sh
+npm ci
+```

package/template/.codex/skills/data-analytics/assets/datascience-artifact-widget.html

@@ -0,0 +1,16 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>Data Analytics artifact app</title>
+    <script type="module">
+      const target = new URL("../src/datascience-artifact-widget.html", import.meta.url);
+      target.search = window.location.search;
+      window.location.replace(target);
+    </script>
+  </head>
+  <body>
+    <p>Redirecting to the local widget source for development.</p>
+    <p><a href="../src/datascience-artifact-widget.html">Open Data Analytics artifact app</a></p>
+  </body>
+</html>