Complete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify before claiming, cite before asserting, and admit uncertainty instead of guessing.
中文简介正在准备中。当前显示原文说明。
Create detailed implementation plans with bite-sized tasks
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Create comprehensive plans assuming the implementer has zero context.
"I'm using the Writing Plans skill to create the implementation plan."
Save to: docs/plans/YYYY-MM-DD-<feature-name>.md
# [Feature Name] Implementation Plan
**Goal:** [One sentence]
**Architecture:** [2-3 sentences]
**Tech Stack:** [Key technologies]
**Estimated Tasks:** [count]
---
Each step = ONE action (2-5 minutes):
NOT: "Write tests and implement feature" ← too big
### Task N: [Component Name]
**Files:**
- Create: `exact/path/to/file.ts`
- Modify: `exact/path/to/existing.ts:lines`
- Test: `tests/path/to/test.ts`
**Step 1: Write failing test**
\`\`\`typescript
test('should do X', () => {
expect(thing()).toBe(expected);
});
\`\`\`
**Step 2: Verify failure**
Run: `npm test -- --grep "should do X"`
Expected: FAIL - "thing is not defined"
**Step 3: Implement**
\`\`\`typescript
export function thing() {
return expected;
}
\`\`\`
**Step 4: Verify pass**
Run: `npm test -- --grep "should do X"`
Expected: PASS
**Step 5: Commit**
\`\`\`bash
git add -A && git commit -m "feat: add thing"
\`\`\`
| Principle | Meaning |
|---|---|
| DRY | Don't repeat yourself |
| YAGNI | Don't build what's not needed |
| TDD | Test first, always |
| Small commits | One logical change per commit |
After saving plan:
**Plan saved to `docs/plans/[filename].md`**
Ready to execute. Options:
1. **Execute now** - I'll work through tasks with you
2. **Subagent execution** - Fresh agent per task with review gates
3. **Later** - Plan saved for future session
If executing → Use executing-plans skill
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Complete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify before claiming, cite before asserting, and admit uncertainty instead of guessing.
中文简介正在准备中。当前显示原文说明。
Transform rough ideas into solid designs through structured questioning
中文简介正在准备中。当前显示原文说明。
Canvas API Connection Skill
中文简介正在准备中。当前显示原文说明。
Forces every code-related claim to include file:line citations. No citation means the claim must be verified or removed. Use when building documentation, writing code reviews, or any output that others will rely on.
中文简介正在准备中。当前显示原文说明。
Assign confidence scores (0-100) to every claim in a response. Helps users understand which parts are verified facts and which are educated guesses. Use when the user needs to know how much to trust each part of the answer.
中文简介正在准备中。当前显示原文说明。
Forces Claude to extract exact quotes from files before making claims about them. Prevents hallucinations by grounding every statement in actual text from the codebase. Use when working with large files or unfamiliar code.
中文简介正在准备中。当前显示原文说明。