Token导航 LogoToken导航TokenDH.com
待分类需要联网github未标认证来源可访问许可证需确认审计通过

plan-self-review计划自我审查

Agent Skill

plan-self-review 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

954

周安装

41

GitHub Stars

公开资料未说明

下载量

335
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:plan-self-review(计划自我审查)
来源仓库:https://github.com/hrdtbs/agent-skills
仓库路径:skills/plan-self-review
安装命令:
npx skills add https://github.com/hrdtbs/agent-skills --skill plan-self-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/hrdtbs/agent-skills --skill plan-self-review

简介

plan-self-review 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。

  • 它可辅助查询项目进展、分析代码差异、跟踪 Issue 状态或协助生成协作摘要。
  • 通过 npx skills add 命令从指定仓库安装,具体用法请参考原始 README。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Plan Self-Review

Use this skill immediately after creating or updating a plan. Catching logical gaps, ambiguous steps, or missing dependencies early prevents cascading failures during execution. Self-reviewing your plan helps you approach the problem methodically and reduces the likelihood of needing major revisions later.

Review Steps

  1. Score Plan (100pt): Evaluate the plan based on the following criteria:

- Clarity (25): Are the steps clear and easy to follow? Do they specify which files and tools will be used? - Comprehensiveness (25): Does the plan cover all necessary aspects of the task? Are there any unaddressed edge cases? - Feasibility (25): Are the steps achievable with the available tools and context? Do you have enough information to execute them? - Consistency (25): Are there any logical contradictions or missing elements? Do the steps follow a logical sequence?

  1. List Deficiencies: Create a prioritized task list (- []) of any gaps, omissions, or ambiguities found in the plan.
  2. Improve: Edit the plan to resolve the identified deficiencies. Update the plan using the appropriate tool.
  3. Final Check: Perform a final check to confirm no logical contradictions or missing elements remain.

Output Format

Present your review using the following structure:

Self-Evaluation Score: [Score]/100

  • Clarity: [Score]/25
  • Comprehensiveness: [Score]/25
  • Feasibility: [Score]/25
  • Consistency: [Score]/25

Deficiencies

  • [Deficiency 1]
  • [Deficiency 2]

Improvements Made

  • [Briefly describe the improvements made to the plan]

Final Check

  • [Confirm that the plan is now logically sound and complete]

Examples

Example 1: Reviewing a plan for adding a new API endpoint

Initial Plan:

  1. Create new endpoint.
  2. Update tests.

Self-Review Output:

Self-Evaluation Score: 40/100

  • Clarity: 10/25 (Missing details on which file to edit and what the endpoint does)
  • Comprehensiveness: 10/25 (Missing documentation update, error handling details)
  • Feasibility: 10/25 (Too vague to execute without further clarification)
  • Consistency: 10/25 (Logically sound but lacks concrete steps)

Deficiencies

  • Specify the exact file and route for the new endpoint
  • Add error handling requirements
  • Identify which test file needs to be updated and what test cases to add
  • Include a step to update the API documentation

Improvements Made

  • Updated the plan to specify the target file (src/api/users.js) and route (POST /users).
  • Added a sub-step for implementing input validation and error handling.
  • Specified the test file (tests/api/users.test.js) and explicitly required testing the error cases.
  • Added a step to update docs/api.md.

Final Check

  • The revised plan is now clear, comprehensive, and specifies exact files and actions. It is logically sound and ready for execution.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.62%
按下载量换算129

Claude

27.63%
按下载量换算93

Cursor

16.95%
按下载量换算57

Gemini CLI

8.53%
按下载量换算29

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills