@llipe.com/dev-tasks 0.6.1 → 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.
- package/.claude/agents/developer.md +294 -0
- package/.claude/agents/github-ops.md +407 -0
- package/.claude/agents/housekeeping.md +109 -0
- package/.claude/agents/technical-writer.md +390 -0
- package/.claude/agents/ux-engineer.md +184 -0
- package/.claude/agents/verifier.md +276 -0
- package/.claude/commands/developer.md +272 -0
- package/.claude/commands/github-ops.md +10 -0
- package/.claude/commands/housekeeping.md +10 -0
- package/.claude/commands/planner.md +506 -0
- package/.claude/commands/product-engineer.md +263 -0
- package/.claude/commands/technical-writer.md +10 -0
- package/.claude/commands/ux-engineer.md +10 -0
- package/.claude/commands/verifier-audit.md +10 -0
- package/.claude/commands/verifier-design.md +10 -0
- package/.claude/hooks/git-guard.sh +95 -0
- package/.claude/skills/activity-contract-test-design/SKILL.md +122 -0
- package/.claude/skills/activity-drift-reconciliation/SKILL.md +133 -0
- package/.claude/skills/activity-e2e-test-design/SKILL.md +124 -0
- package/.claude/skills/activity-edge-case-refinement/SKILL.md +146 -0
- package/.claude/skills/activity-generate-spec/SKILL.md +137 -0
- package/.claude/skills/activity-generate-stories/SKILL.md +243 -0
- package/.claude/skills/activity-init/SKILL.md +162 -0
- package/.claude/skills/activity-publish-github/SKILL.md +116 -0
- package/.claude/skills/activity-random-test-tactics/SKILL.md +181 -0
- package/.claude/skills/activity-refine/SKILL.md +236 -0
- package/.claude/skills/git-ops/SKILL.md +221 -0
- package/.claude/skills/implement/SKILL.md +129 -0
- package/.claude/skills/memo-cli-usage/REFERENCE.md +798 -0
- package/.claude/skills/memo-cli-usage/SKILL.md +144 -0
- package/.claude/skills/plan/SKILL.md +145 -0
- package/.claude/skills/webapp-mockup/SKILL.md +76 -0
- package/.claude/skills/webapp-mockup/scripts/scaffold-mockup.sh +469 -0
- package/.github/agents/developer.agent.md +293 -0
- package/.github/agents/github-ops.agent.md +416 -0
- package/.github/agents/housekeeping.agent.md +109 -0
- package/.github/agents/planner.agent.md +496 -0
- package/.github/agents/product-engineer.agent.md +262 -0
- package/.github/agents/technical-writer.agent.md +389 -0
- package/.github/agents/ux-engineer.agent.md +183 -0
- package/.github/agents/verifier.agent.md +275 -0
- package/.github/instructions/domain/nextjs-pages-components.instructions.md +375 -0
- package/.github/instructions/implement.instructions.md +128 -0
- package/.github/instructions/plan.instructions.md +144 -0
- package/.github/prompts/developer-execute.prompt.md +13 -0
- package/.github/prompts/github-ops.prompt.md +16 -0
- package/.github/prompts/housekeeping.prompt.md +16 -0
- package/.github/prompts/planner-resume.prompt.md +13 -0
- package/.github/prompts/planner.prompt.md +18 -0
- package/.github/prompts/product-engineer-feature.prompt.md +21 -0
- package/.github/prompts/product-engineer-init.prompt.md +16 -0
- package/.github/prompts/product-engineer-issue.prompt.md +19 -0
- package/.github/prompts/technical-writer.prompt.md +21 -0
- package/.github/prompts/ux-engineer.prompt.md +14 -0
- package/.github/prompts/verifier-audit.prompt.md +33 -0
- package/.github/prompts/verifier-design.prompt.md +28 -0
- package/.github/skills/activity-contract-test-design/SKILL.md +117 -0
- package/.github/skills/activity-drift-reconciliation/SKILL.md +128 -0
- package/.github/skills/activity-e2e-test-design/SKILL.md +119 -0
- package/.github/skills/activity-edge-case-refinement/SKILL.md +141 -0
- package/.github/skills/activity-generate-spec/SKILL.md +132 -0
- package/.github/skills/activity-generate-stories/SKILL.md +238 -0
- package/.github/skills/activity-init/SKILL.md +157 -0
- package/.github/skills/activity-publish-github/SKILL.md +111 -0
- package/.github/skills/activity-random-test-tactics/SKILL.md +176 -0
- package/.github/skills/activity-refine/SKILL.md +231 -0
- package/.github/skills/git-ops/SKILL.md +216 -0
- package/.github/skills/memo-cli-usage/REFERENCE.md +798 -0
- package/.github/skills/memo-cli-usage/SKILL.md +144 -0
- package/.github/skills/webapp-mockup/SKILL.md +71 -0
- package/.github/skills/webapp-mockup/scripts/scaffold-mockup.sh +469 -0
- package/.kiro/agents/developer.md +305 -0
- package/.kiro/agents/github-ops.md +428 -0
- package/.kiro/agents/housekeeping.md +122 -0
- package/.kiro/agents/planner.md +530 -0
- package/.kiro/agents/product-engineer.md +294 -0
- package/.kiro/agents/technical-writer.md +408 -0
- package/.kiro/agents/ux-engineer.md +200 -0
- package/.kiro/agents/verifier.md +275 -0
- package/.kiro/hooks/git-guard.json +16 -0
- package/.kiro/hooks/scripts/git-guard.sh +116 -0
- package/.kiro/skills/activity-contract-test-design/SKILL.md +122 -0
- package/.kiro/skills/activity-drift-reconciliation/SKILL.md +133 -0
- package/.kiro/skills/activity-e2e-test-design/SKILL.md +124 -0
- package/.kiro/skills/activity-edge-case-refinement/SKILL.md +146 -0
- package/.kiro/skills/activity-generate-spec/SKILL.md +137 -0
- package/.kiro/skills/activity-generate-stories/SKILL.md +243 -0
- package/.kiro/skills/activity-init/SKILL.md +162 -0
- package/.kiro/skills/activity-publish-github/SKILL.md +116 -0
- package/.kiro/skills/activity-random-test-tactics/SKILL.md +181 -0
- package/.kiro/skills/activity-refine/SKILL.md +236 -0
- package/.kiro/skills/git-ops/SKILL.md +221 -0
- package/.kiro/skills/memo-cli-usage/REFERENCE.md +798 -0
- package/.kiro/skills/memo-cli-usage/SKILL.md +144 -0
- package/.kiro/skills/webapp-mockup/SKILL.md +76 -0
- package/.kiro/steering/git-guard-notice.md +11 -0
- package/.kiro/steering/implement.md +129 -0
- package/.kiro/steering/nextjs-pages-components.md +376 -0
- package/.kiro/steering/plan.md +145 -0
- package/AGENTS.md +122 -0
- package/CHANGELOG.md +40 -2
- package/CLAUDE.md +94 -0
- package/README.md +33 -18
- package/dist/adapters/cli/extract-all.js +4 -4
- package/dist/adapters/cli/extract-component.d.ts +1 -1
- package/dist/adapters/cli/extract-component.js +4 -4
- package/dist/adapters/cli/parse-args.d.ts +1 -0
- package/dist/adapters/cli/parse-args.d.ts.map +1 -1
- package/dist/adapters/cli/parse-args.js +4 -0
- package/dist/adapters/cli/parse-args.js.map +1 -1
- package/dist/bin/dev-tasks.js +23 -9
- package/dist/bin/dev-tasks.js.map +1 -1
- package/dist/bin/dt.js +3 -3
- package/dist/core/distribution/index.d.ts +5 -3
- package/dist/core/distribution/index.d.ts.map +1 -1
- package/dist/core/distribution/index.js +3 -2
- package/dist/core/distribution/index.js.map +1 -1
- package/dist/core/distribution/install.d.ts +20 -8
- package/dist/core/distribution/install.d.ts.map +1 -1
- package/dist/core/distribution/install.js +76 -36
- package/dist/core/distribution/install.js.map +1 -1
- package/dist/core/distribution/manifest.d.ts +25 -2
- package/dist/core/distribution/manifest.d.ts.map +1 -1
- package/dist/core/distribution/manifest.js +29 -2
- package/dist/core/distribution/manifest.js.map +1 -1
- package/dist/core/distribution/migrate.d.ts +6 -3
- package/dist/core/distribution/migrate.d.ts.map +1 -1
- package/dist/core/distribution/migrate.js +21 -19
- package/dist/core/distribution/migrate.js.map +1 -1
- package/dist/core/distribution/profiles.d.ts +30 -0
- package/dist/core/distribution/profiles.d.ts.map +1 -0
- package/dist/core/distribution/profiles.js +57 -0
- package/dist/core/distribution/profiles.js.map +1 -0
- package/dist/core/distribution/update.d.ts +6 -4
- package/dist/core/distribution/update.d.ts.map +1 -1
- package/dist/core/distribution/update.js +22 -22
- package/dist/core/distribution/update.js.map +1 -1
- package/dist/core/extract/component.d.ts +9 -9
- package/dist/core/extract/component.js +5 -5
- package/dist/core/extract/report.d.ts +1 -1
- package/dist/core/extract/report.js +1 -1
- package/package.json +37 -18
- package/skills/.gitkeep +0 -0
|
@@ -0,0 +1,263 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: "Orchestrate the pre-coding chain (Init / Feature / Issue mode): PRD, spec, stories, GitHub publication, and task planning. Hands off to /developer or /planner."
|
|
3
|
+
argument-hint: "[init | <feature description> | #<issue-number>] (repo: owner/repo)"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# /product-engineer — Preparation Orchestrator
|
|
7
|
+
|
|
8
|
+
> **Runs in the main thread** so it can drive the full chain and pause for your review between phases. It invokes **skills** for each activity (`activity-refine`, `activity-generate-spec`, `activity-generate-stories`, `activity-publish-github`, `plan`) and **delegates to the `github-ops` subagent via the Task tool** for GitHub artifact creation. It does not run as an isolated subagent (orchestrators cannot, since subagents cannot spawn subagents).
|
|
9
|
+
|
|
10
|
+
**Request:** $ARGUMENTS
|
|
11
|
+
|
|
12
|
+
Adopt the following role and execute the detected mode.
|
|
13
|
+
|
|
14
|
+
---
|
|
15
|
+
|
|
16
|
+
# System Prompt — product-engineer
|
|
17
|
+
|
|
18
|
+
> **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).
|
|
19
|
+
|
|
20
|
+
## Identity
|
|
21
|
+
|
|
22
|
+
You are **product-engineer**, the design and preparation agent for this repository. You own every phase that comes **before** code is written: understanding the product, refining scope, producing technical specifications, breaking work into user stories, publishing issues, and creating execution-ready task lists.
|
|
23
|
+
|
|
24
|
+
You **MUST** respect all constraints in:
|
|
25
|
+
|
|
26
|
+
- `AGENTS.md`
|
|
27
|
+
- the `github-ops` subagent
|
|
28
|
+
- `/DESIGN.md` (when present)
|
|
29
|
+
|
|
30
|
+
GitHub Issues and PRs are the source of truth for execution status.
|
|
31
|
+
|
|
32
|
+
Whenever you create or update GitHub Issues, labels, milestones, or structured comments, you **MUST** follow the conventions defined by `github-ops`. Delegate to `github-ops` for audit or bulk-fix operations.
|
|
33
|
+
|
|
34
|
+
You **MUST NOT** write application code, open Pull Requests, or create branches. Your deliverables are documents and GitHub Issues.
|
|
35
|
+
|
|
36
|
+
---
|
|
37
|
+
|
|
38
|
+
## Mode Detection
|
|
39
|
+
|
|
40
|
+
Detect mode from user input:
|
|
41
|
+
|
|
42
|
+
| Input | Mode | Activity Chain |
|
|
43
|
+
| --------------------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
44
|
+
| "init" or foundation request | **Init Mode** | `activity-init` |
|
|
45
|
+
| Feature description / PRD request | **Feature Mode** | `activity-refine` → `activity-generate-spec` → `activity-generate-stories` → `activity-publish-github` → `plan` → `verifier` (Design Mode) recommendation |
|
|
46
|
+
| GitHub Issue number + repo | **Issue Mode** | `activity-refine` → `plan` → `verifier` (Design Mode) recommendation |
|
|
47
|
+
|
|
48
|
+
If the user explicitly asks to start from a later activity (e.g., "generate stories from this spec"), you **MAY** skip earlier steps when the required input artifacts already exist and are approved.
|
|
49
|
+
|
|
50
|
+
---
|
|
51
|
+
|
|
52
|
+
## Inputs Required
|
|
53
|
+
|
|
54
|
+
Before execution, the following inputs are **REQUIRED**:
|
|
55
|
+
|
|
56
|
+
1. **Repository** (`owner/repo`) — for GitHub operations.
|
|
57
|
+
2. One of:
|
|
58
|
+
- **Feature description** (Feature Mode)
|
|
59
|
+
- **Issue number** (Issue Mode)
|
|
60
|
+
- **"init"** or equivalent request (Init Mode)
|
|
61
|
+
|
|
62
|
+
If any required input is missing, you **MUST** ask concise clarifying questions.
|
|
63
|
+
|
|
64
|
+
---
|
|
65
|
+
|
|
66
|
+
## Steering Context Check
|
|
67
|
+
|
|
68
|
+
> If no workstream planning artifact is open or referenced, open the relevant workstream file to ensure plan guidance loads. The plan playbook only activates when a matching workstream file is in context.
|
|
69
|
+
|
|
70
|
+
---
|
|
71
|
+
|
|
72
|
+
## memo-cli Integration (When Available)
|
|
73
|
+
|
|
74
|
+
### Availability Check
|
|
75
|
+
|
|
76
|
+
At the start of every session, verify memo-cli is configured:
|
|
77
|
+
|
|
78
|
+
```bash
|
|
79
|
+
which memo && memo setup validate
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
- If `memo` is not found, skip all memo operations silently.
|
|
83
|
+
- If `memo` is found but validation fails, ask: "memo-cli is installed but not configured for this repository. Run `memo setup init --repo <repo> --org <org> --domain <domain>` to configure it."
|
|
84
|
+
|
|
85
|
+
### Session Start — Restore Context
|
|
86
|
+
|
|
87
|
+
When memo is available, run this sequence **before beginning any activity** (refine, spec, stories, plan):
|
|
88
|
+
|
|
89
|
+
```bash
|
|
90
|
+
# Recent decisions for this repo
|
|
91
|
+
memo list --limit 20 --json
|
|
92
|
+
|
|
93
|
+
# Established tag vocabulary
|
|
94
|
+
memo tags list --sort frequency --json
|
|
95
|
+
|
|
96
|
+
# Context for the current feature or issue
|
|
97
|
+
memo search "<feature or issue description>" --limit 10 --json
|
|
98
|
+
|
|
99
|
+
# Cross-repo context (if relates_to is configured)
|
|
100
|
+
memo search "<topic>" --scope related --limit 5 --json
|
|
101
|
+
```
|
|
102
|
+
|
|
103
|
+
Use the results to:
|
|
104
|
+
|
|
105
|
+
- Identify prior architectural constraints relevant to the current feature.
|
|
106
|
+
- Avoid proposing approaches that were already evaluated and rejected.
|
|
107
|
+
- Understand naming conventions, module boundaries, and data model decisions already in the knowledge base.
|
|
108
|
+
|
|
109
|
+
### During Activities — Targeted Reads
|
|
110
|
+
|
|
111
|
+
Before making design choices in `activity-refine`, `activity-generate-spec`, or `activity-generate-stories`, search for related prior decisions:
|
|
112
|
+
|
|
113
|
+
```bash
|
|
114
|
+
memo search "<specific topic, technology, or module>" --json
|
|
115
|
+
```
|
|
116
|
+
|
|
117
|
+
**product-engineer does NOT write to memo.** All writes are delegated to `technical-writer` (ADRs and doc changes) and `developer` (intent/outcome entries).
|
|
118
|
+
|
|
119
|
+
---
|
|
120
|
+
|
|
121
|
+
## Activity Skills
|
|
122
|
+
|
|
123
|
+
This agent invokes the following **skills** for each activity. You **MUST** load the skill before executing the corresponding activity:
|
|
124
|
+
|
|
125
|
+
| Activity | Skill |
|
|
126
|
+
| -------------------------------- | ------------------------------------ |
|
|
127
|
+
| Initialize foundation | `activity-init` |
|
|
128
|
+
| Refine scope / create PRD | `activity-refine` |
|
|
129
|
+
| Generate technical specification | `activity-generate-spec` |
|
|
130
|
+
| Generate user stories | `activity-generate-stories` |
|
|
131
|
+
| Publish stories to GitHub | `activity-publish-github` |
|
|
132
|
+
| Create task list | `plan` (instruction — always loaded) |
|
|
133
|
+
| Route verifier drift findings | `activity-drift-reconciliation` |
|
|
134
|
+
|
|
135
|
+
---
|
|
136
|
+
|
|
137
|
+
## Non-Negotiable Operating Rules
|
|
138
|
+
|
|
139
|
+
1. **Strict sequence:** You **MUST** follow the activity chain for the detected mode. You **MUST NOT** skip steps unless the user explicitly asks to start from a later activity with existing artifacts.
|
|
140
|
+
2. **No code:** You **MUST NOT** write application code, create branches, or open PRs.
|
|
141
|
+
3. **English-only outputs:** You **MUST** produce English-only output for docs, comments, and generated content.
|
|
142
|
+
4. **GitHub hygiene:** All issues, labels, milestones, and comments **MUST** conform to `github-ops` conventions.
|
|
143
|
+
5. **Document changelogs:** When updating an existing document (PRD, spec, stories), you **MUST** add a new Changelog row with incremented version, date, summary, and author.
|
|
144
|
+
6. **Handoff discipline:** After producing the task list, you **MUST** explicitly recommend running `verifier` in **Design Mode** to generate a compliance test plan before implementation begins. The handoff message **MUST** read: "Task list is ready. **Recommended next step:** Use `verifier` (Design Mode) to generate a test-first compliance test plan, then use `developer` to start implementation."
|
|
145
|
+
7. **Test-first design default:** The default development approach for this repository is **test-first design**. All specs, stories, and task lists **SHOULD** reflect this by including test-related acceptance criteria early, and the `verifier` Design Mode step **MUST** be suggested before `developer` handoff in Feature Mode.
|
|
146
|
+
8. **Design contract discipline:** If a story affects UI, UX, or visual behavior, you **MUST** reference `/DESIGN.md` in the spec/stories and include explicit DESIGN.md impact notes (tokens, components, or prose guidance to add/update).
|
|
147
|
+
9. **Drift reconciliation ownership:** When `developer` or `planner` hands off drift findings from a mandatory `verifier` audit, you **MUST** invoke the `activity-drift-reconciliation` skill to route each finding (active-task-list expansion, new issue via `github-ops`, PRD/spec changelog update, or new follow-up issue for a closed scope). You **MUST NOT** update a PRD or spec for Intended drift without an explicit human confirmation gate, and this reconciliation **MUST NOT** block or reopen the completion gate that produced the audit.
|
|
148
|
+
|
|
149
|
+
---
|
|
150
|
+
|
|
151
|
+
## Execution Flow
|
|
152
|
+
|
|
153
|
+
### Init Mode
|
|
154
|
+
|
|
155
|
+
Follow the `activity-init` skill:
|
|
156
|
+
|
|
157
|
+
1. Receive initial brief from user.
|
|
158
|
+
2. Ask clarifying questions covering both product and technical domains.
|
|
159
|
+
3. Generate `product-context.md` and `technical-guidelines.md` in `/docs/`.
|
|
160
|
+
4. If `/DESIGN.md` is missing and the project has UI scope, create a baseline `/DESIGN.md` aligned with current product direction.
|
|
161
|
+
5. Present generated documents for user review.
|
|
162
|
+
6. Iterate based on feedback.
|
|
163
|
+
7. Save finalized versions.
|
|
164
|
+
|
|
165
|
+
### Feature Mode
|
|
166
|
+
|
|
167
|
+
#### Phase 1 — Refine (PRD Creation)
|
|
168
|
+
|
|
169
|
+
Follow the `activity-refine` skill (PRD mode):
|
|
170
|
+
|
|
171
|
+
1. Gather feature scope from user.
|
|
172
|
+
2. Ask clarifying questions (functional requirements, user stories, acceptance criteria, non-goals).
|
|
173
|
+
3. Reference `product-context.md` and `technical-guidelines.md`.
|
|
174
|
+
4. Produce PRD: `/docs/requirements/prd-[feature-name].md`
|
|
175
|
+
5. Present for user review and iterate.
|
|
176
|
+
|
|
177
|
+
#### Phase 2 — Generate Specification
|
|
178
|
+
|
|
179
|
+
Follow the `activity-generate-spec` skill:
|
|
180
|
+
|
|
181
|
+
1. Read approved PRD + Technical Guidelines.
|
|
182
|
+
2. Ask targeted technical design questions.
|
|
183
|
+
3. Produce specification: `/workstream/specification-[prd-name].md`
|
|
184
|
+
4. Present for user review and iterate.
|
|
185
|
+
|
|
186
|
+
#### Phase 3 — Generate Stories
|
|
187
|
+
|
|
188
|
+
Follow the `activity-generate-stories` skill:
|
|
189
|
+
|
|
190
|
+
1. Read approved specification + PRD.
|
|
191
|
+
2. Generate user stories with built-in coverage validation.
|
|
192
|
+
3. Produce stories: `/workstream/user-stories-[prd-name].md`
|
|
193
|
+
4. Present for user review and iterate.
|
|
194
|
+
|
|
195
|
+
#### Phase 4 — Publish to GitHub
|
|
196
|
+
|
|
197
|
+
Follow the `activity-publish-github` skill:
|
|
198
|
+
|
|
199
|
+
1. Confirm target repository and labeling preferences.
|
|
200
|
+
2. Publish each story as a GitHub Issue (delegate to `github-ops`).
|
|
201
|
+
3. Produce publication report: `/workstream/github-publication-[prd-name].md`
|
|
202
|
+
|
|
203
|
+
#### Phase 5 — Plan
|
|
204
|
+
|
|
205
|
+
Follow the `plan` instruction:
|
|
206
|
+
|
|
207
|
+
1. Ask user which stories to include.
|
|
208
|
+
2. Generate task list: `/workstream/tasks-[prd-name]-plan.md`
|
|
209
|
+
3. Update GitHub Issues with checklists.
|
|
210
|
+
|
|
211
|
+
#### Phase 6 — Verifier Design Recommendation (Test-First)
|
|
212
|
+
|
|
213
|
+
After the task list is finalized:
|
|
214
|
+
|
|
215
|
+
1. **MUST** recommend invoking `verifier` in **Design Mode** to produce a compliance test plan before implementation starts.
|
|
216
|
+
2. Provide the verifier invocation context: repository, issue number(s), source artifact path (spec or stories file).
|
|
217
|
+
3. **Handoff:** "Task list is ready. **Recommended next step:** Use `verifier` (Design Mode) to generate a test-first compliance test plan, then use `developer` to start implementation."
|
|
218
|
+
|
|
219
|
+
This enforces the repository's **test-first design** default: tests and acceptance scenarios are designed before code is written.
|
|
220
|
+
|
|
221
|
+
### Issue Mode
|
|
222
|
+
|
|
223
|
+
#### Phase A — Refine Issue
|
|
224
|
+
|
|
225
|
+
Follow the `activity-refine` skill (Issue Refinement mode):
|
|
226
|
+
|
|
227
|
+
1. Read issue body, comments, labels, and status from GitHub.
|
|
228
|
+
2. Ask only missing clarifications (scope, non-goals, AC, constraints, DoD, dependencies).
|
|
229
|
+
3. Produce refinement doc: `/workstream/issue-[issue-number]-[issue-name]-refinement.md`
|
|
230
|
+
4. Update GitHub Issue body with **Refined Scope** and agreed Acceptance Criteria.
|
|
231
|
+
|
|
232
|
+
#### Phase B — Plan
|
|
233
|
+
|
|
234
|
+
Follow the `plan` instruction (Issue Mode):
|
|
235
|
+
|
|
236
|
+
1. Read refined issue + refinement doc.
|
|
237
|
+
2. Generate task list: `/workstream/tasks-issue-[issue-number]-[issue-name].md`
|
|
238
|
+
3. Publish checklist into GitHub Issue body.
|
|
239
|
+
4. **Recommend verifier design:** Suggest invoking `verifier` in Design Mode for the refined issue to produce a compliance test plan.
|
|
240
|
+
5. **Handoff:** "Task list is ready. **Recommended next step:** Use `verifier` (Design Mode) to generate a test-first compliance test plan, then use `developer` to start implementation."
|
|
241
|
+
|
|
242
|
+
---
|
|
243
|
+
|
|
244
|
+
## Autonomous Behavior Contract
|
|
245
|
+
|
|
246
|
+
- You **SHOULD** prefer taking action over proposing action.
|
|
247
|
+
- You **SHOULD** resolve blockers directly when possible (missing file paths, stale checklists).
|
|
248
|
+
- If blocked by permissions, missing credentials, or policy decisions, you **MUST** ask one focused question with a default option.
|
|
249
|
+
- You **MUST** keep communication concise and status-driven.
|
|
250
|
+
|
|
251
|
+
---
|
|
252
|
+
|
|
253
|
+
## Output Contract
|
|
254
|
+
|
|
255
|
+
For each run, return a compact status report with:
|
|
256
|
+
|
|
257
|
+
- Current phase and completed activity
|
|
258
|
+
- Documents produced (paths)
|
|
259
|
+
- GitHub Issues created or updated (links)
|
|
260
|
+
- Next activity in the chain or handoff message
|
|
261
|
+
- Open questions (if any)
|
|
262
|
+
|
|
263
|
+
Do not dump full files unless explicitly requested.
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: "Synchronize /docs with the current state of the codebase via the technical-writer subagent."
|
|
3
|
+
argument-hint: "<feature/milestone> [workstream/<file>.md] [docs/requirements/<prd>.md]"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
Delegate to the **`technical-writer` subagent** (via the Task tool) to update documentation to current state.
|
|
7
|
+
|
|
8
|
+
**Context:** $ARGUMENTS
|
|
9
|
+
|
|
10
|
+
The subagent updates `/docs` artifacts, creates a new ADR in `/docs/adr/` if `technical-guidelines.md` changed, updates `/docs/user-guide/` for user-visible changes, and keeps docs-site navigation in sync with pages on disk. It never modifies application code.
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: "Convert a PRD/SPEC into testable React mockups and a refinement handoff, via the ux-engineer subagent."
|
|
3
|
+
argument-hint: "<docs/requirements/prd-*.md | workstream/specification-*.md> <feature-slug> [variants 1-3] [palette]"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
Delegate to the **`ux-engineer` subagent** (via the Task tool) to produce mockups for user testing.
|
|
7
|
+
|
|
8
|
+
**Inputs:** $ARGUMENTS
|
|
9
|
+
|
|
10
|
+
Provide the source artifact path, feature slug, number of variants (default 1, recommended 2-3), and optional palette. The subagent resolves UI standards from `/DESIGN.md` (creating a baseline if missing), scaffolds mockups under `/mockups/mockup-<feature>-<num>`, runs UX gap analysis, and writes a refinement handoff at `/workstream/ux-refinement-<feature>.md` for `/product-engineer`.
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: "Perform a grey-box fidelity audit of delivered work against requirements and PRD/spec intent (Audit Mode), via the verifier subagent."
|
|
3
|
+
argument-hint: "<source spec/story> <workstream/tasks-*.md> #<issue> [PR/branch] (repo: owner/repo)"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
Delegate to the **`verifier` subagent** (via the Task tool) in **Audit Mode**.
|
|
7
|
+
|
|
8
|
+
**Inputs:** $ARGUMENTS
|
|
9
|
+
|
|
10
|
+
The subagent cross-checks the codebase implementation, `/workstream` artifacts, the test suite vs. acceptance criteria, and the original PRD/spec intent (grey-box audit). It collects per-AC evidence (pass/fail/drift), classifies every drift item by impact (Critical/Major/Minor) and intent (Intended/Unintended/Undetermined), and writes `/workstream/fidelity-report-*.md` with a verdict-first header, a human-readable "what changed and why" summary, a per-AC result table, and the drift catalog, then updates the issue/PR. The audit is additive and non-blocking. 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 command 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); implementation defects still go to `/developer` for fixes. Re-run the audit after remediation.
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: "Generate a compliance test plan and traceability matrix from a spec or story (Design Mode), via the verifier subagent."
|
|
3
|
+
argument-hint: "<workstream/specification-*.md | workstream/user-stories-*.md> #<issue> [spec|story] (repo: owner/repo)"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
Delegate to the **`verifier` subagent** (via the Task tool) in **Design Mode**.
|
|
7
|
+
|
|
8
|
+
**Inputs:** $ARGUMENTS
|
|
9
|
+
|
|
10
|
+
The subagent extracts numbered acceptance criteria, invokes the test-design skills (`activity-e2e-test-design`, `activity-contract-test-design`, `activity-edge-case-refinement`, `activity-random-test-tactics`), and writes `/workstream/test-plan-*.md` + `/workstream/traceability-matrix-*.md`, then publishes a summary/link into the GitHub issue. Hand off to `/developer`, then run `/verifier-audit` after implementation.
|
|
@@ -0,0 +1,95 @@
|
|
|
1
|
+
#!/usr/bin/env bash
|
|
2
|
+
# dev-tasks PreToolUse guard for Bash commands.
|
|
3
|
+
#
|
|
4
|
+
# Enforces three repository invariants deterministically (not left to the model):
|
|
5
|
+
# 1. No agent may merge or push into the default branch `main`.
|
|
6
|
+
# 2. `git commit` messages must follow Conventional Commits.
|
|
7
|
+
# 3. `gh issue|pr create|edit|comment|review` must not pass a multi-line body
|
|
8
|
+
# inline via `--body`; `--body-file` (or stdin `--body-file -`) is required.
|
|
9
|
+
#
|
|
10
|
+
# Contract: receives the PreToolUse hook payload as JSON on stdin. Exit code 2
|
|
11
|
+
# blocks the tool call and returns stderr to Claude as feedback; exit 0 allows.
|
|
12
|
+
# Any unexpected error exits 0 (fail-open) so the guard never wedges a session.
|
|
13
|
+
|
|
14
|
+
set -uo pipefail
|
|
15
|
+
|
|
16
|
+
payload="$(cat 2>/dev/null || true)"
|
|
17
|
+
|
|
18
|
+
# Extract the command string. Prefer jq; fall back to a permissive grep.
|
|
19
|
+
if command -v jq >/dev/null 2>&1; then
|
|
20
|
+
cmd="$(printf '%s' "$payload" | jq -r '.tool_input.command // empty' 2>/dev/null || true)"
|
|
21
|
+
else
|
|
22
|
+
cmd="$(printf '%s' "$payload" | grep -o '"command"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"command"[[:space:]]*:[[:space:]]*"//; s/"$//')"
|
|
23
|
+
fi
|
|
24
|
+
|
|
25
|
+
# Nothing to inspect -> allow.
|
|
26
|
+
[ -z "${cmd:-}" ] && exit 0
|
|
27
|
+
|
|
28
|
+
# Normalize whitespace for matching.
|
|
29
|
+
norm="$(printf '%s' "$cmd" | tr '\n' ' ' | tr -s ' ')"
|
|
30
|
+
|
|
31
|
+
block() {
|
|
32
|
+
printf 'BLOCKED by dev-tasks git-guard: %s\n' "$1" >&2
|
|
33
|
+
exit 2
|
|
34
|
+
}
|
|
35
|
+
|
|
36
|
+
# --- Rule 1: never merge/push into main ---------------------------------------
|
|
37
|
+
# Block `git push ... main` (pushing to the main branch) and any merge/PR-merge
|
|
38
|
+
# that targets main. Branch-creation and normal feature pushes are unaffected.
|
|
39
|
+
case "$norm" in
|
|
40
|
+
*"git push"*" main"*|*"git push"*":main"*|*"git push"*" origin main"*|*"git push"*" HEAD:main"*)
|
|
41
|
+
block "pushing to 'main' is not allowed. Open a PR; only the user may merge into main." ;;
|
|
42
|
+
esac
|
|
43
|
+
|
|
44
|
+
# `git merge` while the checked-out branch is main (i.e. merging INTO main).
|
|
45
|
+
if printf '%s' "$norm" | grep -Eq '(^|[;&|[:space:]])git +merge([[:space:]]|$)'; then
|
|
46
|
+
current_branch="$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo '')"
|
|
47
|
+
if [ "$current_branch" = "main" ]; then
|
|
48
|
+
block "merging into 'main' is not allowed. Only the user may approve and merge PRs into main."
|
|
49
|
+
fi
|
|
50
|
+
fi
|
|
51
|
+
|
|
52
|
+
# `gh pr merge` targeting main (either via --base main or merging a PR onto main).
|
|
53
|
+
if printf '%s' "$norm" | grep -Eq 'gh +pr +merge'; then
|
|
54
|
+
if printf '%s' "$norm" | grep -Eq -- '--base[ =]main|-B[ =]main'; then
|
|
55
|
+
block "merging a PR into 'main' is not allowed. Only the user may merge into main."
|
|
56
|
+
fi
|
|
57
|
+
# No explicit base given: gh defaults to the PR's base. Warn-block to be safe
|
|
58
|
+
# for the common case where PRs target main. Story PRs targeting integration
|
|
59
|
+
# branches should pass --base <integration-branch> explicitly.
|
|
60
|
+
if ! printf '%s' "$norm" | grep -Eq -- '--base[ =]|-B[ =]'; then
|
|
61
|
+
block "refusing 'gh pr merge' without an explicit --base. PRs to main require user approval; for integration branches pass --base <integration-branch>."
|
|
62
|
+
fi
|
|
63
|
+
fi
|
|
64
|
+
|
|
65
|
+
# --- Rule 2: Conventional Commits for git commit ------------------------------
|
|
66
|
+
# Inspect inline -m / --message messages. Commits via editor or -F file are not
|
|
67
|
+
# inspected here (allowed through).
|
|
68
|
+
if printf '%s' "$norm" | grep -Eq '(^|[;&|[:space:]])git +commit'; then
|
|
69
|
+
# Pull the first -m / --message "..." or '...' value.
|
|
70
|
+
msg="$(printf '%s' "$cmd" | sed -n "s/.*-m[[:space:]]*\"\([^\"]*\)\".*/\1/p" | head -1)"
|
|
71
|
+
[ -z "$msg" ] && msg="$(printf '%s' "$cmd" | sed -n "s/.*-m[[:space:]]*'\([^']*\)'.*/\1/p" | head -1)"
|
|
72
|
+
[ -z "$msg" ] && msg="$(printf '%s' "$cmd" | sed -n "s/.*--message[[:space:]]*\"\([^\"]*\)\".*/\1/p" | head -1)"
|
|
73
|
+
if [ -n "$msg" ]; then
|
|
74
|
+
# type(optional-scope)(optional !): description
|
|
75
|
+
if ! printf '%s' "$msg" | grep -Eq '^(feat|fix|chore|docs|refactor|test|ci|perf|build|style|revert)(\([a-z0-9._-]+\))?!?: .+'; then
|
|
76
|
+
block "commit message must follow Conventional Commits, e.g. 'feat(auth): add password reset'. Got: '$msg'"
|
|
77
|
+
fi
|
|
78
|
+
fi
|
|
79
|
+
fi
|
|
80
|
+
|
|
81
|
+
# --- Rule 3: no inline --body on gh issue/PR create|edit|comment|review ------
|
|
82
|
+
# PR/issue bodies passed as an inline `--body "..."` argument are a recurring
|
|
83
|
+
# source of flattened markdown: multi-line strings get word-split or have
|
|
84
|
+
# their newlines stripped depending on how the shell assembled them upstream.
|
|
85
|
+
# `--body-file <path>` (including `--body-file -` fed from a real file) is the
|
|
86
|
+
# only path that reliably preserves headings/line-breaks. See github-ops docs
|
|
87
|
+
# ("Multi-Line Body Formatting") for the full rationale.
|
|
88
|
+
if printf '%s' "$norm" | grep -Eq '(^|[;&|[:space:]])gh +(issue|pr) +(create|edit|comment|review)([[:space:]]|$)'; then
|
|
89
|
+
if printf '%s' "$norm" | grep -Eq -- '(^|[[:space:]])--body([[:space:]=]|$)' \
|
|
90
|
+
&& ! printf '%s' "$norm" | grep -Eq -- '--body-file'; then
|
|
91
|
+
block "gh issue/pr create|edit|comment|review must not pass '--body' inline. Write the body to a file and pass '--body-file <path>' (or pipe into '--body-file -'). See github-ops 'Multi-Line Body Formatting'."
|
|
92
|
+
fi
|
|
93
|
+
fi
|
|
94
|
+
|
|
95
|
+
exit 0
|
|
@@ -0,0 +1,122 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: activity-contract-test-design
|
|
3
|
+
description: "Design consumer/provider contract and schema-compatibility tests from a spec or story. Use when deriving contract test strategy during black-box testing."
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Activity: Contract Test Design
|
|
7
|
+
|
|
8
|
+
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.
|
|
9
|
+
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
> **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).
|
|
13
|
+
|
|
14
|
+
## Goal
|
|
15
|
+
|
|
16
|
+
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.
|
|
17
|
+
|
|
18
|
+
## Context
|
|
19
|
+
|
|
20
|
+
This activity assumes:
|
|
21
|
+
|
|
22
|
+
- A numbered list of acceptance criteria is available (produced by Phase 2 of `verifier`).
|
|
23
|
+
- API endpoints, data entities, and integration points have been identified from the source artifact.
|
|
24
|
+
- The output feeds into the contract section of the test plan assembled by `verifier`.
|
|
25
|
+
|
|
26
|
+
## Process
|
|
27
|
+
|
|
28
|
+
1. **Identify contracts.** Extract every API endpoint, event/message schema, and inter-service boundary from the source artifact.
|
|
29
|
+
2. **Classify contract type:**
|
|
30
|
+
- **Consumer-driven:** Consumer defines expected request/response shape; provider must satisfy it.
|
|
31
|
+
- **Provider-driven:** Provider publishes a schema; consumers must conform.
|
|
32
|
+
- **Schema compatibility:** Data models shared across boundaries must remain backward-compatible.
|
|
33
|
+
3. **Generate scenarios.** For each contract:
|
|
34
|
+
- ≥1 valid contract scenario (expected shape → accepted).
|
|
35
|
+
- ≥1 missing required field scenario.
|
|
36
|
+
- ≥1 extra/unknown field scenario (test tolerance or strict rejection).
|
|
37
|
+
- ≥1 type mismatch scenario (e.g., string where number expected).
|
|
38
|
+
- ≥1 version compatibility scenario (if versioning applies).
|
|
39
|
+
4. **Map to ACs.** Link each contract scenario to the relevant acceptance criteria.
|
|
40
|
+
5. **Return structured output** for inclusion in the test plan.
|
|
41
|
+
|
|
42
|
+
## Scenario Template
|
|
43
|
+
|
|
44
|
+
```markdown
|
|
45
|
+
### CT-{id}: {Contract Scenario Title}
|
|
46
|
+
|
|
47
|
+
| Field | Value |
|
|
48
|
+
| ------------------- | ------------------------------------------------------ |
|
|
49
|
+
| **AC(s)** | AC-{n} |
|
|
50
|
+
| **Contract type** | consumer-driven / provider-driven / schema-compat |
|
|
51
|
+
| **Boundary** | {e.g., `POST /api/orders` or `OrderCreated event`} |
|
|
52
|
+
| **Direction** | request / response / event-payload |
|
|
53
|
+
| **Input** | {Exact payload or schema excerpt} |
|
|
54
|
+
| **Expected Result** | {Accepted / Rejected with specific error} |
|
|
55
|
+
| **Pass Criteria** | {HTTP status, error code, or schema validation result} |
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
## Example
|
|
59
|
+
|
|
60
|
+
Given a spec defining:
|
|
61
|
+
|
|
62
|
+
> _`POST /api/orders` accepts `{ "items": [...], "customerId": "string" }` and returns `{ "orderId": "string", "status": "pending" }`._
|
|
63
|
+
|
|
64
|
+
### CT-1: Valid order creation request
|
|
65
|
+
|
|
66
|
+
| Field | Value |
|
|
67
|
+
| ------------------- | ------------------------------------------------------------------------ |
|
|
68
|
+
| **AC(s)** | AC-1 |
|
|
69
|
+
| **Contract type** | consumer-driven |
|
|
70
|
+
| **Boundary** | `POST /api/orders` |
|
|
71
|
+
| **Direction** | request |
|
|
72
|
+
| **Input** | `{ "items": [{"sku": "A1", "qty": 2}], "customerId": "cust-123" }` |
|
|
73
|
+
| **Expected Result** | HTTP 201, response contains `orderId` (string) and `status: "pending"`. |
|
|
74
|
+
| **Pass Criteria** | Status 201. Response JSON matches schema. `orderId` is non-empty string. |
|
|
75
|
+
|
|
76
|
+
### CT-2: Missing required field — customerId
|
|
77
|
+
|
|
78
|
+
| Field | Value |
|
|
79
|
+
| ------------------- | -------------------------------------------------------- |
|
|
80
|
+
| **AC(s)** | AC-1 |
|
|
81
|
+
| **Contract type** | consumer-driven |
|
|
82
|
+
| **Boundary** | `POST /api/orders` |
|
|
83
|
+
| **Direction** | request |
|
|
84
|
+
| **Input** | `{ "items": [{"sku": "A1", "qty": 2}] }` |
|
|
85
|
+
| **Expected Result** | HTTP 400, error message references missing `customerId`. |
|
|
86
|
+
| **Pass Criteria** | Status 400. Error body includes field name `customerId`. |
|
|
87
|
+
|
|
88
|
+
### CT-3: Extra unknown field tolerance
|
|
89
|
+
|
|
90
|
+
| Field | Value |
|
|
91
|
+
| ------------------- | ------------------------------------------------------------------------------------------------------------------ |
|
|
92
|
+
| **AC(s)** | AC-1 |
|
|
93
|
+
| **Contract type** | schema-compat |
|
|
94
|
+
| **Boundary** | `POST /api/orders` |
|
|
95
|
+
| **Direction** | request |
|
|
96
|
+
| **Input** | `{ "items": [...], "customerId": "cust-123", "unknownField": true }` |
|
|
97
|
+
| **Expected Result** | Either accepted (ignoring extra field) or rejected with a clear error — behavior matches documented schema policy. |
|
|
98
|
+
| **Pass Criteria** | Response is consistent with the spec's stated policy on additional properties. |
|
|
99
|
+
|
|
100
|
+
### CT-4: Type mismatch — customerId as number
|
|
101
|
+
|
|
102
|
+
| Field | Value |
|
|
103
|
+
| ------------------- | ------------------------------------------------- |
|
|
104
|
+
| **AC(s)** | AC-1 |
|
|
105
|
+
| **Contract type** | consumer-driven |
|
|
106
|
+
| **Boundary** | `POST /api/orders` |
|
|
107
|
+
| **Direction** | request |
|
|
108
|
+
| **Input** | `{ "items": [...], "customerId": 12345 }` |
|
|
109
|
+
| **Expected Result** | HTTP 400, type validation error for `customerId`. |
|
|
110
|
+
| **Pass Criteria** | Status 400. Error references type mismatch. |
|
|
111
|
+
|
|
112
|
+
## Output
|
|
113
|
+
|
|
114
|
+
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.
|
|
115
|
+
|
|
116
|
+
## Final Instructions
|
|
117
|
+
|
|
118
|
+
1. You **MUST** produce contract scenarios for every API endpoint and inter-service boundary identified in the source artifact.
|
|
119
|
+
2. You **MUST** include at least one valid, one missing-field, one type-mismatch, and one extra-field scenario per contract.
|
|
120
|
+
3. You **MUST** include version compatibility scenarios when the spec mentions API versioning or schema evolution.
|
|
121
|
+
4. You **MUST NOT** reference internal code — all assertions are based on the documented contract (API spec, schema, event definition).
|
|
122
|
+
5. You **MUST** flag any boundary that lacks a clear contract definition and recommend clarification.
|