跳到正文
cccskills
免费在 GitHub 公开

executing-plans

Execute implementation plans in batches with review checkpoints

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Executing Plans

Purpose

Execute plans in controlled batches with verification gates.

"I'm using the Executing Plans skill to implement this plan."

The Process

Load Plan → Review → Execute Batch → Report → Feedback → Next Batch

Step 1: Load & Review

  1. Read the plan file
  2. Review critically - identify concerns
  3. If concerns → Raise with user before starting
  4. Create TodoWrite for all tasks

Step 2: Execute Batch

Default batch size: 3 tasks

For each task:

  1. Mark as in_progress
  2. Follow each step exactly
  3. Run verifications as specified
  4. Mark as completed

Step 3: Report

After each batch:

## Batch Complete

**Implemented:**
- Task 1: [summary]
- Task 2: [summary]
- Task 3: [summary]

**Verification:**
\`\`\`
[test output]
\`\`\`

Ready for feedback.

Step 4: Continue

Based on feedback:

  • Apply changes if needed
  • Execute next batch
  • Repeat until complete

When to STOP

🛑 Stop immediately when:

  • Hit a blocker (missing dependency, unclear instruction)
  • Test fails unexpectedly
  • Plan has gaps preventing progress
  • You don't understand something

Ask for clarification. Don't guess.

Verification Rules

Before marking ANY task complete:

  1. Run the verification command
  2. Read the FULL output
  3. Confirm it matches expectations
  4. Only THEN mark complete

No "should work" or "looks good" - actual verification output.

Batch Reporting Format

### Batch N Complete

| Task | Status | Verification |
|------|--------|--------------|
| Task X | ✅ | 12/12 tests pass |
| Task Y | ✅ | Build successful |
| Task Z | ⚠️ | Needs review |

**Next batch:** Tasks A, B, C

Continue?

Completion

After all tasks:

  1. Run full test suite
  2. Verify all requirements met
  3. Report final status
  4. Hand off to finishing-branch skill if applicable

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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。

a-ariff/ariff-claude-plugins142026年3月29日 更新

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。

a-ariff/ariff-claude-plugins142026年3月29日 更新

Canvas API Connection Skill

中文简介正在准备中。当前显示原文说明。

a-ariff/ariff-claude-plugins142026年3月29日 更新

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。

a-ariff/ariff-claude-plugins142026年3月29日 更新

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。

a-ariff/ariff-claude-plugins142026年3月29日 更新

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。

a-ariff/ariff-claude-plugins142026年3月29日 更新

查看 a-ariff 的全部技能

报告此技能的问题