Install
$ agentstack add skill-jnlk-cn-superpowers-cn-executing-plans ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →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
- 读取计划文件
- 严格复核——识别计划中任何疑问或顾虑
- 如有顾虑:在开始前向用户提出
- 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:
- 标记为 in_progress
- 严格遵循每一步(计划已拆分为小步骤)
- 按要求运行验证
- 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.
- Author: jnlk-cn
- Source: jnlk-cn/superpowers-cn
- License: MIT
- Homepage: https://github.com/jnlk-cn/superpowers-cn
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.