@llipe.com/dev-tasks 0.6.4 → 0.6.5

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.
Files changed (143) hide show
  1. package/.claude/agents/developer.md +294 -0
  2. package/.claude/agents/github-ops.md +407 -0
  3. package/.claude/agents/housekeeping.md +109 -0
  4. package/.claude/agents/technical-writer.md +390 -0
  5. package/.claude/agents/ux-engineer.md +184 -0
  6. package/.claude/agents/verifier.md +276 -0
  7. package/.claude/commands/developer.md +272 -0
  8. package/.claude/commands/github-ops.md +10 -0
  9. package/.claude/commands/housekeeping.md +10 -0
  10. package/.claude/commands/planner.md +506 -0
  11. package/.claude/commands/product-engineer.md +263 -0
  12. package/.claude/commands/technical-writer.md +10 -0
  13. package/.claude/commands/ux-engineer.md +10 -0
  14. package/.claude/commands/verifier-audit.md +10 -0
  15. package/.claude/commands/verifier-design.md +10 -0
  16. package/.claude/hooks/git-guard.sh +95 -0
  17. package/.claude/skills/activity-contract-test-design/SKILL.md +122 -0
  18. package/.claude/skills/activity-drift-reconciliation/SKILL.md +133 -0
  19. package/.claude/skills/activity-e2e-test-design/SKILL.md +124 -0
  20. package/.claude/skills/activity-edge-case-refinement/SKILL.md +146 -0
  21. package/.claude/skills/activity-generate-spec/SKILL.md +137 -0
  22. package/.claude/skills/activity-generate-stories/SKILL.md +243 -0
  23. package/.claude/skills/activity-init/SKILL.md +162 -0
  24. package/.claude/skills/activity-publish-github/SKILL.md +116 -0
  25. package/.claude/skills/activity-random-test-tactics/SKILL.md +181 -0
  26. package/.claude/skills/activity-refine/SKILL.md +236 -0
  27. package/.claude/skills/git-ops/SKILL.md +221 -0
  28. package/.claude/skills/implement/SKILL.md +129 -0
  29. package/.claude/skills/memo-cli-usage/REFERENCE.md +798 -0
  30. package/.claude/skills/memo-cli-usage/SKILL.md +144 -0
  31. package/.claude/skills/plan/SKILL.md +145 -0
  32. package/.claude/skills/webapp-mockup/SKILL.md +76 -0
  33. package/.claude/skills/webapp-mockup/scripts/scaffold-mockup.sh +469 -0
  34. package/.github/agents/developer.agent.md +293 -0
  35. package/.github/agents/github-ops.agent.md +416 -0
  36. package/.github/agents/housekeeping.agent.md +109 -0
  37. package/.github/agents/planner.agent.md +496 -0
  38. package/.github/agents/product-engineer.agent.md +262 -0
  39. package/.github/agents/technical-writer.agent.md +389 -0
  40. package/.github/agents/ux-engineer.agent.md +183 -0
  41. package/.github/agents/verifier.agent.md +275 -0
  42. package/.github/instructions/domain/nextjs-pages-components.instructions.md +375 -0
  43. package/.github/instructions/implement.instructions.md +128 -0
  44. package/.github/instructions/plan.instructions.md +144 -0
  45. package/.github/prompts/developer-execute.prompt.md +13 -0
  46. package/.github/prompts/github-ops.prompt.md +16 -0
  47. package/.github/prompts/housekeeping.prompt.md +16 -0
  48. package/.github/prompts/planner-resume.prompt.md +13 -0
  49. package/.github/prompts/planner.prompt.md +18 -0
  50. package/.github/prompts/product-engineer-feature.prompt.md +21 -0
  51. package/.github/prompts/product-engineer-init.prompt.md +16 -0
  52. package/.github/prompts/product-engineer-issue.prompt.md +19 -0
  53. package/.github/prompts/technical-writer.prompt.md +21 -0
  54. package/.github/prompts/ux-engineer.prompt.md +14 -0
  55. package/.github/prompts/verifier-audit.prompt.md +33 -0
  56. package/.github/prompts/verifier-design.prompt.md +28 -0
  57. package/.github/skills/activity-contract-test-design/SKILL.md +117 -0
  58. package/.github/skills/activity-drift-reconciliation/SKILL.md +128 -0
  59. package/.github/skills/activity-e2e-test-design/SKILL.md +119 -0
  60. package/.github/skills/activity-edge-case-refinement/SKILL.md +141 -0
  61. package/.github/skills/activity-generate-spec/SKILL.md +132 -0
  62. package/.github/skills/activity-generate-stories/SKILL.md +238 -0
  63. package/.github/skills/activity-init/SKILL.md +157 -0
  64. package/.github/skills/activity-publish-github/SKILL.md +111 -0
  65. package/.github/skills/activity-random-test-tactics/SKILL.md +176 -0
  66. package/.github/skills/activity-refine/SKILL.md +231 -0
  67. package/.github/skills/git-ops/SKILL.md +216 -0
  68. package/.github/skills/memo-cli-usage/REFERENCE.md +798 -0
  69. package/.github/skills/memo-cli-usage/SKILL.md +144 -0
  70. package/.github/skills/webapp-mockup/SKILL.md +71 -0
  71. package/.github/skills/webapp-mockup/scripts/scaffold-mockup.sh +469 -0
  72. package/.kiro/agents/developer.md +305 -0
  73. package/.kiro/agents/github-ops.md +428 -0
  74. package/.kiro/agents/housekeeping.md +122 -0
  75. package/.kiro/agents/planner.md +530 -0
  76. package/.kiro/agents/product-engineer.md +294 -0
  77. package/.kiro/agents/technical-writer.md +408 -0
  78. package/.kiro/agents/ux-engineer.md +200 -0
  79. package/.kiro/agents/verifier.md +275 -0
  80. package/.kiro/hooks/git-guard.json +16 -0
  81. package/.kiro/hooks/scripts/git-guard.sh +116 -0
  82. package/.kiro/skills/activity-contract-test-design/SKILL.md +122 -0
  83. package/.kiro/skills/activity-drift-reconciliation/SKILL.md +133 -0
  84. package/.kiro/skills/activity-e2e-test-design/SKILL.md +124 -0
  85. package/.kiro/skills/activity-edge-case-refinement/SKILL.md +146 -0
  86. package/.kiro/skills/activity-generate-spec/SKILL.md +137 -0
  87. package/.kiro/skills/activity-generate-stories/SKILL.md +243 -0
  88. package/.kiro/skills/activity-init/SKILL.md +162 -0
  89. package/.kiro/skills/activity-publish-github/SKILL.md +116 -0
  90. package/.kiro/skills/activity-random-test-tactics/SKILL.md +181 -0
  91. package/.kiro/skills/activity-refine/SKILL.md +236 -0
  92. package/.kiro/skills/git-ops/SKILL.md +221 -0
  93. package/.kiro/skills/memo-cli-usage/REFERENCE.md +798 -0
  94. package/.kiro/skills/memo-cli-usage/SKILL.md +144 -0
  95. package/.kiro/skills/webapp-mockup/SKILL.md +76 -0
  96. package/.kiro/steering/git-guard-notice.md +11 -0
  97. package/.kiro/steering/implement.md +129 -0
  98. package/.kiro/steering/nextjs-pages-components.md +376 -0
  99. package/.kiro/steering/plan.md +145 -0
  100. package/AGENTS.md +122 -0
  101. package/CHANGELOG.md +18 -2
  102. package/CLAUDE.md +94 -0
  103. package/README.md +6 -6
  104. package/dist/adapters/cli/extract-all.js +4 -4
  105. package/dist/adapters/cli/extract-component.d.ts +1 -1
  106. package/dist/adapters/cli/extract-component.js +4 -4
  107. package/dist/adapters/cli/parse-args.d.ts +1 -0
  108. package/dist/adapters/cli/parse-args.d.ts.map +1 -1
  109. package/dist/adapters/cli/parse-args.js +4 -0
  110. package/dist/adapters/cli/parse-args.js.map +1 -1
  111. package/dist/bin/dev-tasks.js +23 -9
  112. package/dist/bin/dev-tasks.js.map +1 -1
  113. package/dist/bin/dt.js +3 -3
  114. package/dist/core/distribution/index.d.ts +5 -3
  115. package/dist/core/distribution/index.d.ts.map +1 -1
  116. package/dist/core/distribution/index.js +3 -2
  117. package/dist/core/distribution/index.js.map +1 -1
  118. package/dist/core/distribution/install.d.ts +20 -8
  119. package/dist/core/distribution/install.d.ts.map +1 -1
  120. package/dist/core/distribution/install.js +76 -36
  121. package/dist/core/distribution/install.js.map +1 -1
  122. package/dist/core/distribution/manifest.d.ts +25 -2
  123. package/dist/core/distribution/manifest.d.ts.map +1 -1
  124. package/dist/core/distribution/manifest.js +29 -2
  125. package/dist/core/distribution/manifest.js.map +1 -1
  126. package/dist/core/distribution/migrate.d.ts +6 -3
  127. package/dist/core/distribution/migrate.d.ts.map +1 -1
  128. package/dist/core/distribution/migrate.js +21 -19
  129. package/dist/core/distribution/migrate.js.map +1 -1
  130. package/dist/core/distribution/profiles.d.ts +30 -0
  131. package/dist/core/distribution/profiles.d.ts.map +1 -0
  132. package/dist/core/distribution/profiles.js +57 -0
  133. package/dist/core/distribution/profiles.js.map +1 -0
  134. package/dist/core/distribution/update.d.ts +6 -4
  135. package/dist/core/distribution/update.d.ts.map +1 -1
  136. package/dist/core/distribution/update.js +22 -22
  137. package/dist/core/distribution/update.js.map +1 -1
  138. package/dist/core/extract/component.d.ts +9 -9
  139. package/dist/core/extract/component.js +5 -5
  140. package/dist/core/extract/report.d.ts +1 -1
  141. package/dist/core/extract/report.js +1 -1
  142. package/package.json +15 -2
  143. package/skills/.gitkeep +0 -0
@@ -0,0 +1,16 @@
1
+ ---
2
+ agent: housekeeping
3
+ description: "Fix auto-fixable lint, type, and test-wiring issues without changing logic."
4
+ ---
5
+
6
+ Run the `housekeeping` agent to perform a code-quality pass.
7
+
8
+ - **Target scope:** `<path/to/directory — leave blank for the full project>`
9
+
10
+ The agent will fix:
11
+
12
+ - Auto-fixable lint errors and formatting issues
13
+ - Missing type annotations and incorrect return types
14
+ - Broken test imports, wrong mock paths, and outdated snapshots (re-generated only)
15
+
16
+ The agent will **not** change test logic, business logic, or package versions without explicit confirmation. Logic changes and package upgrades are escalated with a clear report — never applied silently.
@@ -0,0 +1,13 @@
1
+ ---
2
+ agent: planner
3
+ description: "Resume an interrupted multi-story execution run from the last checkpoint."
4
+ ---
5
+
6
+ Resume the `planner` agent from an existing checkpoint:
7
+
8
+ - **Repository:** `<owner/repo>`
9
+ - **State file:** `workstream/planner-state-<plan-id>.md`
10
+
11
+ The planner will read the checkpoint state file, display completed and pending stories, and ask for confirmation before resuming from the next pending story.
12
+
13
+ Use this prompt when a previous planner run was interrupted (context loss, session timeout, etc.) and you want to continue from where it left off.
@@ -0,0 +1,18 @@
1
+ ---
2
+ agent: planner
3
+ description: "Orchestrate multi-story execution from a /workstream task file or GitHub milestone."
4
+ ---
5
+
6
+ Run the `planner` agent to orchestrate a multi-story implementation:
7
+
8
+ - **Repository:** `<owner/repo>`
9
+ - **Task source** _(choose one)_:
10
+ - Task file: `workstream/<tasks-prd-XXX-description.md>`
11
+ - GitHub milestone: `<milestone-name-or-id>`
12
+ - **Developer execution mode:** pre-approved autonomous sequential _(change to `step-gated` for manual approval per sub-task)_
13
+
14
+ The planner will present a dependency-based batch plan and pause for your approval before any work begins.
15
+
16
+ - Integration branch: `integration/<plan-id>-<short-description>`
17
+ - Story branches and PRs are created by `developer` per `github-ops` conventions
18
+ - Final output: one consolidated PR from integration branch to `main` plus a mandatory `PR Directives (User Action Required)` block (review, approve, merge steps)
@@ -0,0 +1,21 @@
1
+ ---
2
+ agent: product-engineer
3
+ description: "Design and plan a new feature end-to-end — from PRD to task list."
4
+ ---
5
+
6
+ Run the `product-engineer` agent to design a new feature:
7
+
8
+ - **Repository:** `<owner/repo>`
9
+ - **Feature description:**
10
+ > <Describe the feature in one or more sentences, or paste a PRD excerpt here>
11
+
12
+ The agent will chain: `refine` → `generate-spec` → `generate-stories` → `publish-github` → `plan` → `verifier` (Design Mode) recommendation.
13
+
14
+ Artifacts produced:
15
+
16
+ - PRD under `/docs/requirements/`
17
+ - Specification under `/workstream/`
18
+ - User stories published as GitHub Issues
19
+ - Execution-ready task list under `/workstream/`
20
+
21
+ When complete, use `verifier` (Design Mode) to generate a test-first compliance test plan, then use `developer` (Execute Mode) or `planner` to start implementation.
@@ -0,0 +1,16 @@
1
+ ---
2
+ agent: product-engineer
3
+ description: "Initialize project foundation — create product-context.md and technical-guidelines.md."
4
+ ---
5
+
6
+ Run the `product-engineer` agent to establish foundation documents for this project:
7
+
8
+ - **Project/product description:**
9
+ > <Describe the product, project, or technology stack>
10
+
11
+ The agent will invoke the `activity-init` skill to create:
12
+
13
+ - `docs/product-context.md` — Product context and strategic goals
14
+ - `docs/technical-guidelines.md` — Technical standards and patterns
15
+
16
+ These documents serve as the "constitution" for all future development. Run this once per project or on major strategic/technical pivots.
@@ -0,0 +1,19 @@
1
+ ---
2
+ agent: product-engineer
3
+ description: "Refine and plan a GitHub Issue for implementation."
4
+ ---
5
+
6
+ Run the `product-engineer` agent to refine and plan a GitHub Issue:
7
+
8
+ - **Repository:** `<owner/repo>`
9
+ - **Issue number:** `#<issue-number>`
10
+
11
+ The agent will chain: `refine` → `plan` → `verifier` (Design Mode) recommendation.
12
+
13
+ Artifacts produced:
14
+
15
+ - Lightweight refinement doc under `/workstream/`
16
+ - GitHub Issue updated with "Refined Scope" section
17
+ - Execution-ready task list under `/workstream/`
18
+
19
+ When complete, use `verifier` (Design Mode) to generate a test-first compliance test plan, then use `developer` (Execute Mode) to start implementation.
@@ -0,0 +1,21 @@
1
+ ---
2
+ agent: technical-writer
3
+ description: "Audit and update /docs to reflect the current state of the codebase."
4
+ ---
5
+
6
+ Run the `technical-writer` agent to synchronize documentation with the codebase.
7
+
8
+ Context for this pass _(provide one or more)_:
9
+
10
+ - **Feature / milestone completed:** `<feature name or milestone>`
11
+ - **Relevant workstream files:** `workstream/<file.md>`
12
+ - **PRD reference:** `docs/requirements/<prd-file.md>` _(optional)_
13
+
14
+ The agent will:
15
+
16
+ - Update `/docs` artifacts to reflect current implemented behavior
17
+ - Create a new ADR in `/docs/adr/` if `technical-guidelines.md` changed
18
+ - Update `/docs/user-guide/` for any user-visible changes
19
+ - Keep `mkdocs.yml` navigation in sync with pages on disk
20
+
21
+ `technical-writer` never modifies application code.
@@ -0,0 +1,14 @@
1
+ Run the `ux-engineer` agent to convert requirements into testable mockups:
2
+
3
+ - **Source artifact path:** `<docs/requirements/prd-*.md | workstream/specification-*.md>`
4
+ - **Design standard path:** `<DESIGN.md>` _(optional; defaults to `/DESIGN.md`)_
5
+ - **Feature slug:** `<feature-slug>`
6
+ - **Number of variants:** `<1-3>`
7
+ - **Palette:** `<palette-url-or-hex-set>` _(optional; fallback will be used if omitted)_
8
+
9
+ Expected outputs:
10
+
11
+ - Mockups in `/mockups/mockup-<feature>-<num>`
12
+ - UX gap analysis and user-testing questions
13
+ - Refinement handoff file in `/workstream/ux-refinement-<feature>.md`
14
+ - DESIGN.md compliance notes and explicit deviations (if any)
@@ -0,0 +1,33 @@
1
+ ---
2
+ agent: verifier
3
+ description: "Grey-box fidelity audit of delivered work against requirements and PRD/spec intent — Audit Mode."
4
+ ---
5
+
6
+ Run the `verifier` agent in **Audit Mode** to check the fidelity of delivered code:
7
+
8
+ - **Repository:** `<owner/repo>`
9
+ - **GitHub Issue:** `#<issue-number>`
10
+ - **Source artifact:** `<workstream/specification-*.md | workstream/user-stories-*.md | issue body>`
11
+ - **Task list:** `<workstream/tasks-*.md>`
12
+ - **PR or branch:** `<PR-number or branch-name>`
13
+ - **Test plan (optional):** `<workstream/test-plan-*.md>` if Design Mode already ran for this scope
14
+
15
+ The agent will chain: intake → requirement extraction → evidence collection (grey-box audit) → reporting & publication.
16
+
17
+ The grey-box audit cross-checks four sources: (a) the codebase implementation, (b) `/workstream` artifacts, (c) the test suite vs. acceptance criteria, and (d) the original PRD/spec intent.
18
+
19
+ Artifacts produced:
20
+
21
+ - `/workstream/fidelity-report-{issue-or-story-id}.md` — Per-AC fidelity results, drift catalog, human-readable summary, and overall verdict
22
+ - GitHub issue or PR updated with the report's header/verdict section
23
+
24
+ The fidelity report includes:
25
+
26
+ - Header/verdict first: overall fidelity verdict and highest drift impact
27
+ - Human-readable "what changed and why" summary, free of implementation jargon
28
+ - Per-AC result table (pass / fail / drift)
29
+ - Drift catalog with impact class (Critical/Major/Minor) and intent class (Intended/Unintended/Undetermined) per item — drift is non-blocking to completion
30
+ - Edge-case and randomized test outcomes (when a prior test plan exists)
31
+ - Recommendations per drift item
32
+
33
+ This mode is now also invoked automatically as a mandatory, non-skippable step by `developer` (post-implementation, pre-PR-ready, per issue) and by `planner` (per-story and PRD-level rollup) — this manual prompt remains available for ad-hoc or standalone audits outside that automatic flow. When defects or Unintended drift are found, they route to `product-engineer`'s `activity-drift-reconciliation` skill (task-list/checklist expansion, new issue via `github-ops`, or a human-confirmed PRD/spec changelog update), rather than only "hand off to developer for fixes" — implementation defects still go to `developer`, but write-back of drift findings is owned by `product-engineer`. Re-run the audit after remediation.
@@ -0,0 +1,28 @@
1
+ ---
2
+ agent: verifier
3
+ description: "Generate a compliance test plan from a specification or user story — Design Mode."
4
+ ---
5
+
6
+ Run the `verifier` agent in **Design Mode** to generate a compliance test plan:
7
+
8
+ - **Repository:** `<owner/repo>`
9
+ - **GitHub Issue:** `#<issue-number>`
10
+ - **Source artifact:** `<workstream/specification-*.md | workstream/user-stories-*.md | issue body>`
11
+ - **Input type:** `spec` or `story`
12
+
13
+ The agent will chain: intake → requirement extraction → test design → reporting & publication.
14
+
15
+ Skills invoked:
16
+
17
+ - `activity-e2e-test-design` — E2E black-box scenarios
18
+ - `activity-contract-test-design` — Contract validation scenarios
19
+ - `activity-edge-case-refinement` — Categorized edge-case catalog
20
+ - `activity-random-test-tactics` — Randomized and property-based tactics
21
+
22
+ Artifacts produced:
23
+
24
+ - `/workstream/test-plan-{issue-or-story-id}.md` — Compliance test plan
25
+ - `/workstream/traceability-matrix-{issue-or-story-id}.md` — AC-to-test mapping
26
+ - GitHub issue updated with test plan summary or artifact link
27
+
28
+ When complete, hand off to `developer` for implementation, then use `verifier-audit` after implementation to check fidelity.
@@ -0,0 +1,117 @@
1
+ # Activity: Contract Test Design
2
+
3
+ Generate consumer/provider contract test strategies and schema compatibility checks from a specification or user story. Produces contract validation scenarios that ensure API boundaries, data schemas, and inter-service agreements are honored. Invoked by the `verifier` agent in Design Mode.
4
+
5
+ ---
6
+
7
+ > **RFC 2119 Notice:** The key words **MUST**, **MUST NOT**, **REQUIRED**, **SHALL**, **SHALL NOT**, **SHOULD**, **SHOULD NOT**, **RECOMMENDED**, **MAY**, and **OPTIONAL** in this document are to be interpreted as described in [RFC 2119](https://www.rfc-editor.org/rfc/rfc2119).
8
+
9
+ ## Goal
10
+
11
+ Derive contract-level test scenarios that validate API boundaries, data schemas, and inter-service agreements from the outside. Contract tests verify that providers deliver what consumers expect, without coupling to internal implementation.
12
+
13
+ ## Context
14
+
15
+ This activity assumes:
16
+
17
+ - A numbered list of acceptance criteria is available (produced by Phase 2 of `verifier`).
18
+ - API endpoints, data entities, and integration points have been identified from the source artifact.
19
+ - The output feeds into the contract section of the test plan assembled by `verifier`.
20
+
21
+ ## Process
22
+
23
+ 1. **Identify contracts.** Extract every API endpoint, event/message schema, and inter-service boundary from the source artifact.
24
+ 2. **Classify contract type:**
25
+ - **Consumer-driven:** Consumer defines expected request/response shape; provider must satisfy it.
26
+ - **Provider-driven:** Provider publishes a schema; consumers must conform.
27
+ - **Schema compatibility:** Data models shared across boundaries must remain backward-compatible.
28
+ 3. **Generate scenarios.** For each contract:
29
+ - ≥1 valid contract scenario (expected shape → accepted).
30
+ - ≥1 missing required field scenario.
31
+ - ≥1 extra/unknown field scenario (test tolerance or strict rejection).
32
+ - ≥1 type mismatch scenario (e.g., string where number expected).
33
+ - ≥1 version compatibility scenario (if versioning applies).
34
+ 4. **Map to ACs.** Link each contract scenario to the relevant acceptance criteria.
35
+ 5. **Return structured output** for inclusion in the test plan.
36
+
37
+ ## Scenario Template
38
+
39
+ ```markdown
40
+ ### CT-{id}: {Contract Scenario Title}
41
+
42
+ | Field | Value |
43
+ | ------------------- | ------------------------------------------------------ |
44
+ | **AC(s)** | AC-{n} |
45
+ | **Contract type** | consumer-driven / provider-driven / schema-compat |
46
+ | **Boundary** | {e.g., `POST /api/orders` or `OrderCreated event`} |
47
+ | **Direction** | request / response / event-payload |
48
+ | **Input** | {Exact payload or schema excerpt} |
49
+ | **Expected Result** | {Accepted / Rejected with specific error} |
50
+ | **Pass Criteria** | {HTTP status, error code, or schema validation result} |
51
+ ```
52
+
53
+ ## Example
54
+
55
+ Given a spec defining:
56
+
57
+ > _`POST /api/orders` accepts `{ "items": [...], "customerId": "string" }` and returns `{ "orderId": "string", "status": "pending" }`._
58
+
59
+ ### CT-1: Valid order creation request
60
+
61
+ | Field | Value |
62
+ | ------------------- | ------------------------------------------------------------------------ |
63
+ | **AC(s)** | AC-1 |
64
+ | **Contract type** | consumer-driven |
65
+ | **Boundary** | `POST /api/orders` |
66
+ | **Direction** | request |
67
+ | **Input** | `{ "items": [{"sku": "A1", "qty": 2}], "customerId": "cust-123" }` |
68
+ | **Expected Result** | HTTP 201, response contains `orderId` (string) and `status: "pending"`. |
69
+ | **Pass Criteria** | Status 201. Response JSON matches schema. `orderId` is non-empty string. |
70
+
71
+ ### CT-2: Missing required field — customerId
72
+
73
+ | Field | Value |
74
+ | ------------------- | -------------------------------------------------------- |
75
+ | **AC(s)** | AC-1 |
76
+ | **Contract type** | consumer-driven |
77
+ | **Boundary** | `POST /api/orders` |
78
+ | **Direction** | request |
79
+ | **Input** | `{ "items": [{"sku": "A1", "qty": 2}] }` |
80
+ | **Expected Result** | HTTP 400, error message references missing `customerId`. |
81
+ | **Pass Criteria** | Status 400. Error body includes field name `customerId`. |
82
+
83
+ ### CT-3: Extra unknown field tolerance
84
+
85
+ | Field | Value |
86
+ | ------------------- | ------------------------------------------------------------------------------------------------------------------ |
87
+ | **AC(s)** | AC-1 |
88
+ | **Contract type** | schema-compat |
89
+ | **Boundary** | `POST /api/orders` |
90
+ | **Direction** | request |
91
+ | **Input** | `{ "items": [...], "customerId": "cust-123", "unknownField": true }` |
92
+ | **Expected Result** | Either accepted (ignoring extra field) or rejected with a clear error — behavior matches documented schema policy. |
93
+ | **Pass Criteria** | Response is consistent with the spec's stated policy on additional properties. |
94
+
95
+ ### CT-4: Type mismatch — customerId as number
96
+
97
+ | Field | Value |
98
+ | ------------------- | ------------------------------------------------- |
99
+ | **AC(s)** | AC-1 |
100
+ | **Contract type** | consumer-driven |
101
+ | **Boundary** | `POST /api/orders` |
102
+ | **Direction** | request |
103
+ | **Input** | `{ "items": [...], "customerId": 12345 }` |
104
+ | **Expected Result** | HTTP 400, type validation error for `customerId`. |
105
+ | **Pass Criteria** | Status 400. Error references type mismatch. |
106
+
107
+ ## Output
108
+
109
+ This skill returns a list of contract scenarios in the template format above. The calling agent (`verifier`) assembles them into the contract section of the test plan.
110
+
111
+ ## Final Instructions
112
+
113
+ 1. You **MUST** produce contract scenarios for every API endpoint and inter-service boundary identified in the source artifact.
114
+ 2. You **MUST** include at least one valid, one missing-field, one type-mismatch, and one extra-field scenario per contract.
115
+ 3. You **MUST** include version compatibility scenarios when the spec mentions API versioning or schema evolution.
116
+ 4. You **MUST NOT** reference internal code — all assertions are based on the documented contract (API spec, schema, event definition).
117
+ 5. You **MUST** flag any boundary that lacks a clear contract definition and recommend clarification.
@@ -0,0 +1,128 @@
1
+ # Activity: Drift Reconciliation
2
+
3
+ Take a `verifier` fidelity report (Audit Mode) or PRD-level rollup audit and route each drift finding to the correct destination — an expanded task list, a new GitHub issue, a PRD/spec changelog update, or a new follow-up issue for a closed scope — without ever blocking the PR/issue completion that triggered the audit. Invoked by the `product-engineer` agent whenever `developer` or `planner` hands off drift findings from a mandatory `verifier` audit.
4
+
5
+ ---
6
+
7
+ > **RFC 2119 Notice:** The key words **MUST**, **MUST NOT**, **REQUIRED**, **SHALL**, **SHALL NOT**, **SHOULD**, **SHOULD NOT**, **RECOMMENDED**, **MAY**, and **OPTIONAL** in this document are to be interpreted as described in [RFC 2119](https://www.rfc-editor.org/rfc/rfc2119).
8
+
9
+ ## Goal
10
+
11
+ Given a `verifier` drift catalog (per-item impact class, intent class, and evidence), decide and execute the correct reconciliation path for each item, so drift is never silently dropped and never silently blocks completion.
12
+
13
+ ## Context
14
+
15
+ This activity assumes:
16
+
17
+ - A `/workstream/fidelity-report-{issue-or-story-id}.md` produced by `verifier` in Audit Mode exists, or a rollup report from a `planner` Phase 5 run.
18
+ - The drift catalog in that report classifies every item by **impact** (`Critical`/`Major`/`Minor`) and **intent** (`Intended`/`Unintended`/`Undetermined`).
19
+ - The originating task list (`/workstream/tasks-*.md`) and GitHub Issue for the current scope are known.
20
+ - `developer` or `planner` has already reached (or passed) its own completion gate — this activity runs **after** that gating decision, never before it, and its outcome never reopens or blocks that gate.
21
+
22
+ ## Non-Negotiable Operating Rules
23
+
24
+ 1. **Non-blocking, always:** Reconciliation **MUST NOT** be used to block, reopen, or gate PR/issue completion. It is a post-hoc write-back activity only.
25
+ 2. **Route by intent first, then scope:** Every drift item **MUST** be classified by intent (`Intended`/`Unintended`/`Undetermined`) before deciding a destination. `Undetermined` items **MUST** be escalated to a human as a clarifying question before routing — do not guess.
26
+ 3. **Human confirmation gate for Intended drift:** You **MUST NOT** update a PRD or spec for Intended drift without an explicit human confirmation step. No new task is created for Intended drift.
27
+ 4. **Active task list expansion:** For Unintended drift against a task list that is still open/active, you **MUST** expand `/workstream/tasks-*.md` with new sub-task(s) and update the GitHub Issue checklist to match — the GitHub Issue and local file **MUST** stay in sync.
28
+ 5. **New issue for out-of-scope drift:** For Unintended drift that warrants tracking beyond the current task's scope, you **MUST** delegate to `github-ops` to create a new GitHub issue/sub-task, cross-referenced to the originating issue.
29
+ 6. **Closed-scope drift never reopens:** For drift found against an already-closed/merged task list or issue (including a PRD-level rollup after a consolidated PR), you **MUST** open a new follow-up issue/task list rather than reopening the closed one.
30
+ 7. **Changelog discipline:** Any PRD/spec update resulting from Intended drift **MUST** include an incremented changelog entry (version, date, summary, author) in that document.
31
+ 8. **Traceability:** Every routed drift item **MUST** be traceable back to its source fidelity report and AC (or `N/A` for out-of-scope/rollup-only findings).
32
+ 9. **English-only outputs:** All new tasks, issue bodies, comments, and changelog entries **MUST** be in English.
33
+
34
+ ## Process
35
+
36
+ ### Step 1 — Intake
37
+
38
+ Read the fidelity report (or rollup report). For each drift catalog item, extract:
39
+
40
+ - `drift_id`, `AC(s)` affected (or `N/A`)
41
+ - Impact class (`Critical`/`Major`/`Minor`)
42
+ - Intent class (`Intended`/`Unintended`/`Undetermined`)
43
+ - Evidence source(s) cited by `verifier`
44
+ - Originating scope: issue/story task list path + GitHub issue number, and whether that scope is still open or already closed/merged
45
+
46
+ ### Step 2 — Classify Undetermined Items
47
+
48
+ For any item classified `Undetermined` by `verifier`, ask the user one focused clarifying question per item (or a batched question if several share context) to resolve intent before proceeding. Do not route an `Undetermined` item until it is resolved to `Intended` or `Unintended`.
49
+
50
+ ### Step 3 — Route Each Item
51
+
52
+ Apply this decision table in order:
53
+
54
+ | Condition | Route | AC Reference |
55
+ | ---------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- | ------------ |
56
+ | Intended drift | Human-confirmation gate → PRD/spec changelog update (Step 4). No new task. | AC-5 |
57
+ | Unintended drift, originating task list/issue still open | Expand `/workstream/tasks-*.md` with new sub-task(s); sync GitHub Issue checklist (Step 5) | AC-3 |
58
+ | Unintended drift, warrants tracking beyond current task scope | Create new GitHub issue/sub-task via `github-ops`, cross-referenced to originating issue (Step 6) | AC-4 |
59
+ | Drift found against an already-closed/merged task list or issue (e.g., PRD-level rollup) | Open a new follow-up issue/task list; do not reopen the closed one (Step 7) | AC-6 |
60
+
61
+ A single audit run may produce items routed to more than one path — process each item independently through this table.
62
+
63
+ ### Step 4 — Intended Drift → Human-Confirmed PRD/Spec Update
64
+
65
+ 1. Present the drift item (what changed, why it appears intentional, evidence) to the human and ask for explicit confirmation: _"Confirm this is an intentional deviation from the PRD/spec — update the document? (y/n)"_
66
+ 2. If declined, re-classify as `Unintended` and re-route via Step 3.
67
+ 3. If confirmed:
68
+ - Update the relevant PRD and/or spec section to reflect the confirmed behavior.
69
+ - Add a changelog row: `| <version+1> | <date> | <summary of what changed and why> | product-engineer |`.
70
+ - **MUST NOT** create a new task for this item.
71
+ - Record the confirmation (who/when) in the changelog summary or a linked comment.
72
+
73
+ ### Step 5 — Unintended Drift, Active Task List
74
+
75
+ 1. Add new sub-task(s) to the correct parent task in `/workstream/tasks-*.md`, following the existing numbering convention (e.g., `N.x`).
76
+ 2. Update the corresponding GitHub Issue checklist with the same new sub-task(s), keeping wording identical between the two.
77
+ 3. Note the originating drift item ID in the new sub-task text so the fix is traceable back to the fidelity report.
78
+ 4. Hand off the new sub-task(s) to `developer` for execution through the normal `implement` flow — this activity does not implement the fix itself.
79
+
80
+ ### Step 6 — Unintended Drift, Beyond Current Task Scope
81
+
82
+ 1. Delegate to `github-ops` to create a new GitHub issue using standard issue conventions (title format, Summary, Acceptance Criteria).
83
+ 2. The new issue body **MUST** cross-reference the originating issue (`Refs #<originating-issue-number>`) and cite the drift item and AC from the fidelity report.
84
+ 3. If the new issue is large enough to need its own task list, hand off to the `plan` activity to generate one — this activity only creates the issue, it does not itself plan the fix.
85
+
86
+ ### Step 7 — Drift Against a Closed/Merged Scope
87
+
88
+ 1. Confirm the originating task list/issue state is closed or merged (do not proceed on an assumption — check GitHub issue state and/or task-list completion markers).
89
+ 2. Create a new GitHub issue and a new `/workstream/tasks-*.md` follow-up task list scoped to the drift item(s) only.
90
+ 3. Cross-reference the closed issue/PR in the new issue body (`Follow-up to #<closed-issue-number>`, `Refs PR #<merged-pr-number>`).
91
+ 4. **MUST NOT** reopen the closed issue or reopen/merge into the closed task list.
92
+
93
+ ## Output
94
+
95
+ Reconciliation summary returned to the caller (`developer`, `planner`, or the user):
96
+
97
+ ```markdown
98
+ # Drift Reconciliation Summary — [scope]
99
+
100
+ Source fidelity report: /workstream/fidelity-report-{id}.md
101
+
102
+ ## Routed Items
103
+
104
+ | Drift ID | Impact | Intent | Route | Destination |
105
+ | -------- | -------- | ---------- | -------------------------- | ------------------------------------------- |
106
+ | D-1 | Minor | Unintended | Active task list expansion | tasks-issue-42.md #3.5, Issue #42 checklist |
107
+ | D-2 | Major | Intended | PRD/spec changelog update | spec-checkout.md v1.3 |
108
+ | D-3 | Critical | Unintended | New issue | Issue #58 (Refs #42) |
109
+ | D-4 | Minor | Unintended | Follow-up (closed scope) | Issue #59 + tasks-issue-59.md |
110
+
111
+ ## Escalations
112
+
113
+ - Undetermined items resolved: <list, or none>
114
+
115
+ ## Non-Blocking Confirmation
116
+
117
+ This reconciliation pass ran after [developer/planner]'s completion gate and did not block or reopen it.
118
+ ```
119
+
120
+ ## Final Instructions
121
+
122
+ 1. You **MUST** classify every drift item by intent before routing it — resolve `Undetermined` first.
123
+ 2. You **MUST NOT** create a new task for Intended drift, and you **MUST NOT** update the PRD/spec for Intended drift without explicit human confirmation.
124
+ 3. You **MUST** keep the local task file and the GitHub Issue checklist in sync whenever you expand an active task list.
125
+ 4. You **MUST** delegate new-issue creation to `github-ops` and follow its conventions (title format, labels, cross-referencing).
126
+ 5. You **MUST NOT** reopen a closed/merged issue or task list — open a new follow-up instead.
127
+ 6. You **MUST** confirm and state that this activity never blocks or reopens the completion gate that triggered it.
128
+ 7. You **MUST** return the reconciliation summary in the format above.
@@ -0,0 +1,119 @@
1
+ # Activity: E2E Black-Box Test Design
2
+
3
+ Generate end-to-end black-box test scenarios from a complete specification or a single user story. Produces executable scenario descriptions tied to acceptance criteria, covering happy paths, negative paths, and abuse cases. Invoked by the `verifier` agent in Design Mode.
4
+
5
+ ---
6
+
7
+ > **RFC 2119 Notice:** The key words **MUST**, **MUST NOT**, **REQUIRED**, **SHALL**, **SHALL NOT**, **SHOULD**, **SHOULD NOT**, **RECOMMENDED**, **MAY**, and **OPTIONAL** in this document are to be interpreted as described in [RFC 2119](https://www.rfc-editor.org/rfc/rfc2119).
8
+
9
+ ## Goal
10
+
11
+ Derive a comprehensive set of end-to-end black-box test scenarios from requirements. Every acceptance criterion (AC) **MUST** be covered by at least one positive (happy-path) scenario and at least one negative or edge-case scenario.
12
+
13
+ ## Context
14
+
15
+ This activity assumes:
16
+
17
+ - A numbered list of acceptance criteria is available (produced by Phase 2 of `verifier`).
18
+ - The source artifact (spec or user story) has been read and parsed.
19
+ - The output feeds into the test plan assembled by `verifier`.
20
+
21
+ ## Process
22
+
23
+ 1. **Receive AC list and source artifact.**
24
+ 2. **Identify user-facing workflows.** Map each AC to the observable behavior it describes.
25
+ 3. **Generate scenarios.** For each AC, produce:
26
+ - ≥1 happy-path scenario (expected inputs → expected outputs).
27
+ - ≥1 negative-path scenario (invalid/missing inputs → expected error behavior).
28
+ - ≥1 abuse-case scenario where applicable (malicious input, privilege escalation, injection).
29
+ 4. **Assign severity.** Mark each scenario as `critical`, `major`, or `minor` based on business impact.
30
+ 5. **Cross-reference.** Ensure every AC has at least one scenario; flag uncovered ACs.
31
+ 6. **Return structured output** for inclusion in the test plan.
32
+
33
+ ## Scenario Template
34
+
35
+ Each scenario **MUST** follow this structure:
36
+
37
+ ```markdown
38
+ ### SC-{id}: {Scenario Title}
39
+
40
+ | Field | Value |
41
+ | ------------------- | --------------------------------------- |
42
+ | **AC(s)** | AC-{n}, AC-{m} |
43
+ | **Type** | happy-path / negative-path / abuse-case |
44
+ | **Severity** | critical / major / minor |
45
+ | **Preconditions** | {State required before execution} |
46
+ | **Steps** | 1. {Step} 2. {Step} … |
47
+ | **Expected Result** | {Observable outcome from the outside} |
48
+ | **Pass Criteria** | {Unambiguous condition for pass} |
49
+ ```
50
+
51
+ ## Example
52
+
53
+ Given a user story:
54
+
55
+ > _As a user, I want to log in with my email and password so that I can access my dashboard._
56
+
57
+ **AC-1:** User with valid credentials is redirected to the dashboard.
58
+ **AC-2:** User with invalid credentials sees an error message.
59
+ **AC-3:** Account is locked after 5 consecutive failed attempts.
60
+
61
+ ### SC-1: Successful login with valid credentials
62
+
63
+ | Field | Value |
64
+ | ------------------- | ------------------------------------------------------------------------------- |
65
+ | **AC(s)** | AC-1 |
66
+ | **Type** | happy-path |
67
+ | **Severity** | critical |
68
+ | **Preconditions** | User account exists and is active. |
69
+ | **Steps** | 1. Navigate to `/login`. 2. Enter valid email and password. 3. Submit the form. |
70
+ | **Expected Result** | User is redirected to `/dashboard`. Session is established. |
71
+ | **Pass Criteria** | HTTP 302 redirect to `/dashboard`. Auth cookie present. |
72
+
73
+ ### SC-2: Login with wrong password
74
+
75
+ | Field | Value |
76
+ | ------------------- | ------------------------------------------------------------------------------------- |
77
+ | **AC(s)** | AC-2 |
78
+ | **Type** | negative-path |
79
+ | **Severity** | critical |
80
+ | **Preconditions** | User account exists and is active. |
81
+ | **Steps** | 1. Navigate to `/login`. 2. Enter valid email and wrong password. 3. Submit the form. |
82
+ | **Expected Result** | Login page displays "Invalid email or password" error. |
83
+ | **Pass Criteria** | HTTP 401. Error message displayed. No session created. |
84
+
85
+ ### SC-3: Account lockout after 5 failures
86
+
87
+ | Field | Value |
88
+ | ------------------- | ---------------------------------------------------------------------------------------------------------------- |
89
+ | **AC(s)** | AC-3 |
90
+ | **Type** | negative-path |
91
+ | **Severity** | major |
92
+ | **Preconditions** | User account exists. Failed attempt counter is at 0. |
93
+ | **Steps** | 1. Submit login with wrong password 5 times consecutively. 2. Attempt login with correct password. |
94
+ | **Expected Result** | After 5th failure, account is locked. 6th attempt (even with correct password) returns "Account locked" message. |
95
+ | **Pass Criteria** | HTTP 423 on 6th attempt. Lock message displayed. |
96
+
97
+ ### SC-4: SQL injection in email field
98
+
99
+ | Field | Value |
100
+ | ------------------- | ------------------------------------------------------------------ |
101
+ | **AC(s)** | AC-1, AC-2 |
102
+ | **Type** | abuse-case |
103
+ | **Severity** | critical |
104
+ | **Preconditions** | Login page accessible. |
105
+ | **Steps** | 1. Enter `' OR 1=1 --` as email. 2. Enter any password. 3. Submit. |
106
+ | **Expected Result** | Login fails with "Invalid email or password". No data leak. |
107
+ | **Pass Criteria** | HTTP 401. No SQL error exposed. No authentication bypass. |
108
+
109
+ ## Output
110
+
111
+ This skill returns a list of scenarios in the template format above. The calling agent (`verifier`) assembles them into the E2E section of the test plan.
112
+
113
+ ## Final Instructions
114
+
115
+ 1. You **MUST** produce at least one happy-path and one negative-path scenario per AC.
116
+ 2. You **MUST** include abuse-case scenarios for ACs involving authentication, authorization, or user input.
117
+ 3. You **MUST** assign severity to every scenario.
118
+ 4. You **MUST NOT** reference internal implementation details — all assertions are based on observable behavior.
119
+ 5. You **MUST** flag any AC that cannot be covered by an E2E scenario and explain why.