AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Executing Plans

skill-jnlk-cn-superpowers-cn-executing-plans · by jnlk-cn

当需要在一个独立会话中执行已撰写的实现计划,并通过检查点进行复核时必须使用

— No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-jnlk-cn-superpowers-cn-executing-plans

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jnlk-cn-superpowers-cn-executing-plans)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Executing Plans? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Executing Plans

Overview

加载计划,进行严格复核,执行所有任务,完成后报告。

开始时声明:"我正在使用 executing-plans skill 来执行此计划。"

注意: 告诉你的用户,Superpowers 在支持子代理的平台上效果更佳。如果平台支持子代理(Claude Code、Codex CLI、Codex App、Copilot CLI 和 Gemini CLI 均符合条件;各平台工具引用见 ../using-superpowers/references/),产出质量会显著提高。若可使用子代理,请改用 superpowers:subagent-driven-development,而非本 skill。

The Process

Step 1: Load and Review Plan

  1. 读取计划文件
  2. 严格复核——识别计划中任何疑问或顾虑
  3. 如有顾虑:在开始前向用户提出
  4. 如无顾虑:为计划条目创建待办事项并继续

Step 2: Execute Tasks

对于每个任务:

  1. 标记为 in_progress
  2. 严格遵循每一步(计划已拆分为小步骤)
  3. 按要求运行验证
  4. 标记为 completed

Step 3: Complete Development

所有任务完成并通过验证后:

  • 声明:"我正在使用 finishing-a-development-branch skill 来完成这项工作。"
  • 必需子技能: 使用 superpowers:finishing-a-development-branch
  • 遵循该 skill 验证测试、呈现选项并执行选择

When to Stop and Ask for Help

出现以下情况时立即停止执行:

  • 遇到阻塞(缺少依赖、测试失败、指令不清)
  • 计划存在严重缺失,无法开始
  • 不理解某条指令
  • 验证反复失败

请要求澄清,而不是猜测。

When to Revisit Earlier Steps

以下情况返回复核阶段(Step 1):

  • 用户根据你的反馈更新了计划
  • 需要重新思考根本方案

不要强行绕过阻塞——停下来提问。

Remember

  • 首先严格复核计划
  • 严格按计划步骤执行
  • 不要跳过验证
  • 当计划要求引用 skill 时引用对应 skill
  • 遇到阻塞时停下来,不要猜测
  • 未经用户明确同意,绝不在 main/master 分支上开始实现

Integration

必需的工作流 skill:

  • superpowers:using-git-worktrees——确保隔离工作区(创建新的或验证已有的)
  • superpowers:writing-plans——创建本 skill 所执行的计划
  • superpowers:finishing-a-development-branch——完成所有任务后的开发收尾

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.