菜单
Use when you have a spec or requirements for a multi-step task, before touching code
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate a fully-typed TypeScript API client from Strapi content-type schemas and route contracts. Use after backend-schema when you need to create or regenerate the frontend API layer.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Execute page designs from the design doc — compose shadcn components and wire to generated API types. Phase 4 execution, no re-design.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Scaffold a new fullstack project using scaffold-mcp. Use when the user wants to create a new Strapi+React project or start building a fullstack application.
Use when executing implementation plans with independent tasks in the current session
| name | writing-plans |
| description | Use when you have a spec or requirements for a multi-step task, before touching code |
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree (created by brainstorming skill).
Save plans to: docs/metaforge/plans/YYYY-MM-DD-<feature-name>.md
If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.
When planning a fullstack feature cycle, tasks MUST follow this phase order. Each phase depends on the previous one completing successfully. Plans that violate this order will fail at execution time.
When plans include npx shadcn add commands, each component name MUST be verified via shadcn-mcp before writing it into the plan. Use search_items_in_registries to confirm a component exists in the registry. Never hardcode a component name that hasn't been confirmed against the live registry — component availability and naming changes across shadcn versions.
Schema Design ──► API Types ──► Pages ──► Verification
Each phase boundary gets a git commit with a standard prefix:
checkpoint:feature/<name>/schema — after Phase 2 (schema commit)
checkpoint:feature/<name>/types — after Phase 3 (API types generated)
checkpoint:feature/<name>/pages — after Phase 4 (pages built)
checkpoint:feature/<name>/verified — after Phase 5 (integration verified)
These checkpoints enable Option B rollback in executing-plans.
When a plan task modifies backend schema, annotate it with the GitNexus risk level (if available):
> **Risk:** LOW — 2 consumers affected (api.articles.find, ArticlesPage)
Run gitnexus_impact({target: "symbolName", direction: "upstream"}) before writing schema-modifying tasks to determine risk.
For fullstack plans, each task should specify which domain skill to use:
- [ ] **Task 1: Define content types** — use `metaforge:backend-schema`
- [ ] **Task 2: Generate API types** — use `metaforge:api-client-gen`
- [ ] **Task 3: Build article list page** — use `metaforge:frontend-page`
This ensures executing-plans dispatches to the correct domain skill for each task.
Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.
This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
Each step is one action (2-5 minutes):
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For agentic workers:** REQUIRED SUB-SKILL: Use metaforge:subagent-driven-development (recommended) or metaforge:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** [One sentence describing what this builds]
**Architecture:** [2-3 sentences about approach]
**Tech Stack:** [Key technologies/libraries]
---
### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`
- [ ] **Step 1: Write the failing test**
```python
def test_specific_behavior():
result = function(input)
assert result == expected
```
- [ ] **Step 2: Run test to verify it fails**
Run: `pytest tests/path/test.py::test_name -v`
Expected: FAIL with "function not defined"
- [ ] **Step 3: Write minimal implementation**
```python
def function(input):
return expected
```
- [ ] **Step 4: Run test to verify it passes**
Run: `pytest tests/path/test.py::test_name -v`
Expected: PASS
- [ ] **Step 5: Commit**
```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```
Every step must contain the actual content an engineer needs. These are plan failures — never write them:
After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.
1. Spec coverage: Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps.
2. Placeholder scan: Search your plan for red flags — any of the patterns from the "No Placeholders" section above. Fix them.
3. Type consistency: Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called clearLayers() in Task 3 but clearFullLayers() in Task 7 is a bug.
If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.
After saving the plan, offer execution choice:
"Plan complete and saved to docs/metaforge/plans/<filename>.md. Two execution options:
1. Subagent-Driven (recommended) - I dispatch a fresh subagent per task, review between tasks, fast iteration
2. Inline Execution - Execute tasks in this session using executing-plans, batch execution with checkpoints
Which approach?"
If Subagent-Driven chosen:
If Inline Execution chosen: