菜单
Converts approved designs into comprehensive, bite-sized implementation plans. 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
| name | sp-writing-plans |
| description | Converts approved designs into comprehensive, bite-sized implementation plans. Use when you have a spec or requirements for a multi-step task, before touching code. |
| tags | ["planning","workflow","implementation","tdd"] |
| version | 1.0.0 |
| risk | guarded |
| triggers | ["write an implementation plan","create a plan for this","plan this feature","write a plan","make a plan","implementation plan","plan before coding"] |
| requirements | {"cli":[],"env":[]} |
| upstream_ref | skills/writing-plans/SKILL.md |
| author | AlphaComposite |
| license | MIT |
| dependencies | ["sp-brainstorming","sp-subagent-driven-development","sp-executing-plans","sp-using-git-worktrees"] |
Write comprehensive implementation plans assuming the engineer has zero context for the 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 the toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the sp-writing-plans skill to create the implementation plan."
Context: This should be run in a dedicated worktree (created by sp-brainstorming via sp-using-git-worktrees).
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
Dependency note:
sp-subagent-driven-developmentandsp-executing-plansare referenced in the Execution Handoff section. If either is unavailable, inform the user and describe the manual equivalent.
Each step is one action (2-5 minutes):
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For the agent:** REQUIRED SUB-SKILL: Use `sp-executing-plans` to implement this plan task-by-task.
**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"
```
After saving the plan, offer execution choice:
"Plan complete and saved to docs/plans/<filename>.md. Two execution options:
1. Subagent-Driven (this session) — Dispatch a fresh subagent per task, review between tasks, fast iteration
2. Parallel Session (separate) — Open new session with sp-executing-plans, batch execution with checkpoints
Which approach?"
If Subagent-Driven chosen:
sp-subagent-driven-developmentIf Parallel Session chosen:
sp-executing-plansUse when a major project step has been completed and needs review against the original plan and coding standards. Provides the Senior Code Reviewer persona for structured 6-phase review: plan alignment, code quality, architecture, documentation, issue categorization, and communication.
Use when you need to trigger brainstorm, write-plan, or execute-plan workflows via short command shortcuts. These are thin dispatchers that invoke the corresponding sp- skills.
Use when creating new skills, editing existing skills, or verifying skills work before deployment. Apply TDD cycle: baseline test first, write skill second, refactor to close loopholes.
Use when completing tasks, implementing major features, or before merging. Dispatches a code-reviewer session to catch issues before they cascade. Review early, review often.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Decision framework for when and how to dispatch parallel sub-agent sessions for faster resolution.
Use when implementation is complete and all tests pass, to decide how to integrate the work. Guides branch completion by presenting 4 structured options: merge locally, push and create a PR, keep as-is, or discard.