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

Executing Plans

skill-myswallow-superpowers-lite-executing-plans · by MySwallow

当你有一份书面实施计划,需要在独立会话中执行并设置评审检查点时使用

No reviews yet
0 installs
9 views
0.0% view→install

Install

$ agentstack add skill-myswallow-superpowers-lite-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-myswallow-superpowers-lite-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

执行计划

概述

加载计划,批判性地审查,执行所有任务,完成后汇报。

开始时声明: "我正在使用 executing-plans skill 来实施这份计划。"

注意: 如果支持子代理(Claude Code),优先使用 subagent-driven-development skill,质量更高。

流程

步骤 1:加载并审查计划

  1. 读取计划文件
  2. 批判性审查——识别对计划的任何疑问或顾虑
  3. 如有顾虑:开始前先向你的协作伙伴提出
  4. 若无顾虑:创建 TodoWrite 并继续

步骤 2:执行任务

每项任务:

  1. 标记为 in_progress
  2. 严格按每个步骤执行(计划包含细粒度步骤)
  3. 按规范运行验证
  4. 标记为 completed

步骤 3:完成开发

所有任务完成并验证后:

  • 按项目惯例运行静态检查(类型检查 / lint / 构建)
  • 向用户汇报完成——不要自动提交或开 PR
  • 让用户决定何时以及如何整合工作

何时停下来求助

立刻停止执行,当:

  • 遇到障碍(缺少依赖、测试失败、指令不清)
  • 计划存在关键缺口,无法开始
  • 你不理解某个指令
  • 验证反复失败

与其猜测,不如寻求澄清。

何时回到前面的步骤

回到审查(步骤 1),当:

  • 协作伙伴根据你的反馈更新了计划
  • 整体方案需要重新思考

不要强行突破阻碍——停下并询问。

记住

  • 先批判性地审查计划
  • 严格按计划步骤执行
  • 不要跳过验证
  • 计划要求引用某 skill 时就引用
  • 受阻时停下,不要猜测
  • 未经用户明确同意,绝不在 main/master 分支上开始实施

集成

相关 skills:

  • writing-plans - 创建本 skill 要执行的计划
  • subagent-driven-development - 替代方案:在同一会话中通过子代理执行

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.