Token导航 LogoToken导航TokenDH.com
研究检索可写文件github未标认证来源可访问许可证需确认审计通过

exec-plan执行计划

Agent Skill

exec-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。

总安装

2,101

周安装

85

GitHub Stars

131

下载量

660
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:exec-plan(执行计划)
来源仓库:https://github.com/pproenca/dot-skills
仓库路径:skills/exec-plan
安装命令:
npx skills add https://github.com/pproenca/dot-skills --skill exec-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/pproenca/dot-skills --skill exec-plan

简介

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词或任务场景快速定位候选结果时使用。

  • 适用于执行计划相关的信息查询与整理,可结合来源仓库进一步核验用法。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和维护状态。
  • 安装前建议检查是否会触发联网、命令执行或文件读写,确保操作边界清晰。
  • exec-plan 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

ExecPlan — Lifecycle Management

Announce at start: "Using the exec-plan skill."

What is an ExecPlan

A self-contained, living document that a fresh agent session can follow to deliver observable, working behavior. Lives in docs/exec-plans/. The format follows the specification in docs/PLANS.md.

An ExecPlan is NOT a todo list. It is a narrative that tells the story of a change: why it matters, what the codebase looks like now, what it should look like after, and how to prove it worked.

When to use this skill

  • Required for multi-step or multi-file work, new features, refactors, or tasks expected to take more than about an hour.
  • Optional for trivial fixes, but if you skip it for a substantial task, state the reason.
  • Always when resuming work from a previous session.

The Three Modes

Mode 1: CREATE a new plan

When starting new multi-step work:

  1. Read docs/PLANS.md for the template and requirements.
  2. Create the plan at docs/exec-plans/active/{descriptive-kebab-name}.md.
  3. Fill ALL sections from the template. Non-negotiable sections:

- Purpose / Big Picture — what the user can see/do after the change - Progress — empty checkboxes for each milestone - Surprises & Discoveries — start with (none yet) - Decision Log — start with (none yet) - Outcomes & Retrospective — start with (fill when complete) - Context and Orientation — full file paths, term definitions, current state - Plan of Work — narrative milestones with goal → work → result → proof - Concrete Steps — exact commands with expected outputs - Validation and Acceptance — observable proof of success - Idempotence and Recovery — how to retry or roll back

  1. Every file path must be absolute from repo root.
  2. Every term must be defined inline — assume the reader knows nothing.
  3. Commit the plan before starting implementation.

Mode 2: CONTINUE an existing plan

When resuming work or executing the next milestone:

  1. Read the plan file in docs/exec-plans/active/.
  2. Find the first unchecked item in Progress.
  3. Before starting work, check: are there any Surprises from previous sessions that affect this task?
  4. Execute the milestone following the Plan of Work.
  5. After each completed milestone, IMMEDIATELY update the plan:

- Check the Progress item with a timestamp: - [x] (YYYY-MM-DD HH:MMZ) Description - Add any Surprises & Discoveries encountered - Add any Decision Log entries for choices made

  1. Commit the plan update alongside the code changes.
  2. Run the Validation commands to confirm success.

CRITICAL: Never claim a milestone is done without updating the plan file. The plan IS the persistence mechanism. If you don't update it, the next session will redo the work.

Mode 3: COMPLETE a plan

When all milestones are done:

  1. Fill the Outcomes & Retrospective section:

- What was achieved vs what was planned - Any remaining gaps - Lessons learned - Unexpected benefits or costs

  1. Move the file: git mv docs/exec-plans/active/{name}.md docs/exec-plans/completed/{name}.md
  2. Commit with message: docs: complete exec-plan {name}

Quality Checks

Before committing any plan (new or updated), verify:

  • Purpose describes user-visible behavior, not just code changes
  • Progress has timestamps on completed items
  • Context names files by full path from repo root
  • All terms are defined inline (no "see external doc" for critical terms)
  • Validation has exact commands AND expected outputs
  • Recovery section explains rollback for each risky step
  • Surprises section is up to date (even if empty)
  • Decision Log captures any choices made during implementation

Anti-patterns

  • Checklist without narrative: "- [] Edit file X" tells the next session nothing. WHY edit it? WHAT changes? HOW to verify?
  • External references for critical context: "See ARCHITECTURE.md for details" — the plan must be self-contained. Copy the relevant context in.
  • Forgetting to update Progress: The most common failure. If you finish a milestone and don't check the box with a timestamp, the next session will redo it.
  • Leaving completed plans in active/: After all milestones are done, MOVE to completed/. Active plans should only be unfinished work.
  • Skipping Validation: "Tests pass" is not acceptance. "The isValid computed property no longer exists in the file, verified by grep -n isValid file.swift returning no results" IS acceptance.

Integration with other skills

  • Before implementing plan milestones that involve TCA code: invoke /pfw-composable-architecture
  • Before implementing plan milestones that involve debugging: invoke the debug skill
  • Before implementing plan milestones that involve refactoring: invoke the refactor skill
  • Before implementing plan milestones that involve API design: invoke the rest-api-design skill
  • After completing all plan milestones: invoke refactor skill for a final cleanup pass

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

33.79%
按下载量换算223

Claude

28.4%
按下载量换算187

Cursor

18.86%
按下载量换算124

Gemini CLI

8.95%
按下载量换算59

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

可写文件

该 Skill 可能写入或修改本地文件,使用前需要确认目标目录和修改范围。

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