Token导航 LogoToken导航

Agent Skill · 研究检索

execute-plan(执行计划)

execute-plan 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

execute-plan 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 15,487。

总安装 7,822周安装 336GitHub Stars 45下载 2,742核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:execute-plan(执行计划)
来源仓库:https://github.com/buiducnhat/agent-skills
仓库路径:skills/execute-plan
安装命令:
npx skills add https://github.com/buiducnhat/agent-skills --skill execute-plan
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/buiducnhat/agent-skills --skill execute-plan

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

execute-plan 用于严格按照预批准计划执行任务,确保范围、顺序和验证环节准确无误。它加载计划摘要并分批次执行子任务,支持并行与串行调度,并在遇到问题时暂停等待确认。

使用时需提供计划路径(如 docs/plans/YYMMDD-HHmm-plan-slug/SUMMARY.md),不得在过程中 redesign 计划。安装前请确认仓库权限、维护状态,以及是否会触发文件读写、测试运行或外部服务调用。

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。

来源仓库内路径:skills/execute-plan

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/buiducnhat/agent-skills --skill execute-plan;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

execute-plan 怎么安装?

在终端执行 npx skills add https://github.com/buiducnhat/agent-skills --skill execute-plan。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

execute-plan 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

execute-plan 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

execute-plan 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

execute-plan 用的人多吗?

公开数据是累计安装 7,822 次,近一周安装 336 次,下载 2,742 次,GitHub 45 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

execute-plan 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
execute-plan

执行计划 · 本页

7,82245只读未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Execute Plan

Overview

Execute a pre-approved plan with strict adherence to scope, sequence, and verification.

The input is typically: execute-plan docs/plans/YYMMDD-HHmm-<plan-slug>/SUMMARY.md

Do not redesign the plan during execution. If ambiguity or blockers appear, stop and ask.

Workflow

Step 1: Initialize

  1. Locate Plan

- Confirm the plan path exists and is readable. - If a directory is provided, locate SUMMARY.md inside it.

  1. Load Execution Context

- Load project context per the shared Context Loading Protocol. - Review the plan’s phase files and dependencies.

  1. Select Execution Mode (Explicit Rule)

- Default mode: Batch - Use Interactive when any of the following is true: - High-risk changes (auth, payments, migrations, security-critical logic) - Irreversible operations (data migrations, destructive scripts) - Unclear acceptance criteria - User explicitly requests checkpoints - If mode is unclear, ask once and proceed with user choice.

  1. Find Next Pending Phase

- First [] phase - If none, first [-] phase - If no pending/in-progress phases remain, go to final verification.

  1. Critical Plan Sanity Check

- Ensure each phase has: - clear objective - file targets - verification commands - If essential details are missing or contradictory, stop and request clarification.

Step 2: Execute Per-Phase Loop

For each phase in order:

  1. Skip Completed

- If status is [x], continue to next phase.

  1. Mark In Progress

- Update phase status to [-] before making changes.

  1. Execute Exactly

- Implement only the tasks defined in that phase. - Do not expand scope without approval. - Write the minimum code that satisfies the phase. No speculative features, no abstractions for single-use code, no error handling for impossible scenarios. See Simplicity first and Surgical changes rules below.

  1. Verify Phase

- Run the phase-specific verification commands from the plan. - At minimum, run relevant tests/checks tied to touched files.

  1. Handle Failures

- If verification fails: - Attempt focused fixes within phase scope. - Re-run verification. - If still failing or root cause is outside scope, stop and report blocker.

  1. Mark Complete

- Update phase status to [x] only after verification passes.

  1. Progress Report

- Interactive mode: report and wait for confirmation before next phase. - Batch mode: report briefly and continue immediately.

Step 3: Final Verification

After all phases are complete:

  1. Project-Wide Validation

- Run full lint/type-check suite - Run all relevant tests (or full test suite if required by the plan) - Run build verification if applicable

  1. Stabilize

- Fix regressions introduced during execution. - Re-run failed checks until green or blocked.

  1. Manual Validation Checkpoint

- If user/manual QA is required, ask explicitly and pause: - Verified to accept - or provide feedback for follow-up iteration

Step 4: Completion Artifacts

  1. Documentation Sync

- If behavior/architecture/codebase expectations changed, update the docs artifacts.

  1. Create Execution Report

- File: docs/plans/YYMMDD-HHmm-<plan-slug>/EXECUTION-REPORT.md - Include all required sections below.

  1. Archive Plan Folder

- Move the plan folder to docs/plans/archived/ after the execution report is created. - Command: mkdir -p docs/plans/archived && mv docs/plans/YYMMDD-HHmm-<plan-slug> docs/plans/archived/

  1. Announce Completion

- Output: Execution complete. Report archived at docs/plans/archived/YYMMDD-HHmm-<plan-slug>/EXECUTION-REPORT.md.

Step 5: Final Confirmation Gate

After completion artifacts are done, ask the user for a final confirmation using the Question Tool with exactly these options:

  • Confirm: End session
  • Confirm and Auto commit git
  • Need verify

Handle the selected option as follows:

  1. Confirm: End session

- End the execution session.

  1. Confirm and Auto commit git

- Trigger the git-commit skill and complete an automatic commit flow. - After commit succeeds, end the execution session.

  1. Confirm and update documentation

- Use skill /docs to update the relevant documentation files with any changes made during execution. - After documentation is updated, end the execution session.

  1. Confirm and update documentation and auto commit git

- Use skill /docs to update the relevant documentation files with any changes made during execution. - Trigger the git-commit skill and complete an automatic commit flow. - After commit succeeds, end the execution session.

  1. Need verify

- Allow the user to provide verification feedback/details. - Continue the execution loop to address feedback, then re-run verification and completion steps as needed.

Execution Report Standard

EXECUTION-REPORT.md must use the following template: references/execution-report-template.md

Rules

  • Respect project standards: follow docs/ and related project docs.
  • Follow the plan strictly: no silent scope changes.
  • Stop on blocker: missing dependency, contradictory instructions, or unexplained failures.
  • No guessing: ask for clarification when uncertain.
  • Verify before complete: never mark phase done without passing checks.
  • Idempotency: prefer safe/re-runnable operations.
  • Simplicity first: Implement the minimum code that satisfies the phase's exit criteria. No features beyond what the plan asks for. No abstractions for single-use code. No configurability that wasn't requested. If you write 200 lines and it could be 50, rewrite it.
  • Surgical changes: Touch only what the phase requires. Don't "improve" adjacent code, comments, or formatting. Don't refactor things that aren't broken. Match existing style even if you'd do it differently. Only remove imports/variables/functions that *your* changes orphaned — don't delete pre-existing dead code unless the plan asks for it. Every changed line should trace to a phase task.
  • Do not skip workflow steps: initialization, per-phase verification, final verification, and reporting are all mandatory.

平台分布

Codex

37.79%
按下载量换算1,036

Claude

25.95%
按下载量换算712

Cursor

17.91%
按下载量换算491

Gemini CLI

8.99%
按下载量换算247

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills