بنقرة واحدة
writing-plans
Use when creating implementation plans. Break specs into bite-sized tasks (2-5 min each).
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use when creating implementation plans. Break specs into bite-sized tasks (2-5 min each).
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | writing-plans |
| description | Use when creating implementation plans. Break specs into bite-sized tasks (2-5 min each). |
| version | 1.0.0 |
| tags | ["process","planning"] |
∀ plan workflow, after spec approved.
∀ task ∈ plan: must have exact file path, complete code snippet, exact command to run, expected output. "Assumes engineer has zero context ∧ questionable taste."
Each task = 1 action (2-5 minutes):
¬combine multiple actions into one task. ¬"implement feature X" (too broad).
## Wave 0 (parallel)
### T01: Write failing test for [feature]
- **File**: `src/domain/feature.spec.ts`
- **Code**: [exact test code]
- **Run**: `npx vitest run src/domain/feature.spec.ts`
- **Expect**: FAIL — "feature is not defined"
- **AC**: AC1
### T02: Implement [feature]
- **File**: `src/domain/feature.ts`
- **Code**: [exact implementation]
- **Run**: `npx vitest run src/domain/feature.spec.ts`
- **Expect**: PASS — 1/1 tests passing
- **Commit**: `feat(auth/T02): add feature`
## Wave 1 (depends on Wave 0)
...
When breaking a spec into tasks, prefer vertical slices that traverse every architectural layer over horizontal tiers.
Each slice is an independently demonstrable end-to-end segment:
Schema change → API endpoint → UI component → Integration test
Label each slice:
## Wave N
### T<NN>: <slice-name> [HITL | AFK]
- **Scope**: <one-sentence description>
- **Layers**: schema, API, UI, tests (list affected)
- **Blocked by**: T<NN>, T<NN>
- **Verify**: <exact check that proves the slice works>
Use when reviewing architecture decisions. C4 model, dependency inversion, hexagonal boundaries.
Use during discuss-slice and plan-slice to stress-test a spec or plan against domain vocabulary before approval.
Use during research-slice to build disposable experiments that answer technical uncertainty.
Use during project:init to scaffold repo-level agent configuration (CLAUDE.md, AGENTS.md, tracker labels).
Use when debugging. 4-phase investigation, root cause, minimal fix.
Use when implementing features/fixes. Iron law: ¬∃ production code without failing test.