agentleFS
midFangmidFang/ai-agent-skills-workflow/plan/SKILL.md

plan

Skill2 starsChanged 5 months agoMITView on GitHub

Generate or revise a decision-complete implementation plan file for the current workspace. Use when the user explicitly mentions `$plan`, says "进入 Plan 模式", "生成执行计划", "出实现方案", or wants to replace the deprecated `/prompts:plan` workflow. Gather minimal context, prefer `mcp__sequential-thinking__sequentialthinking` when available, then create or update `plan/YYYY-MM-DD_HH-mm-ss-<slug>.md`.

184 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use heartmula, webhook-subscriptions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • math-incSkill

    heartmula

    Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

    Also in 9 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 5 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 6 projects that use this

  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 projects that use this

  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • +3 more from math-inc

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill as the replacement for the deprecated custom prompt /prompts:plan.

    line 8
  2. Distinctive:

    Start with 5-8 targeted read-only tool calls.

    line 24
  3. Distinctive:

    Stop early once the implementation path is clear.

    line 25
  4. Very specific:

    If mcp__sequential-thinking__sequentialthinking is available and the task is more than trivial, use it to shape the plan.

    line 27
  5. Distinctive:

    Create or update a plan file under the current workspace.

    line 28
  6. Very specific:

    Prefer writing a plan/*.md file instead of only chatting.

    line 59
  7. Distinctive:

    Keep the plan decision-complete so implementation can start without extra design decisions.

    line 60
  8. Distinctive:

    Do not implement the plan unless the user explicitly switches from planning to execution.

    line 61
  9. Distinctive:

    If file writes are blocked, return the full plan text plus the intended file path.

    line 62

“Common” is measured: kept by at least 6 in 10 of the 168 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plan

Use this skill as the replacement for the deprecated custom prompt /prompts:plan.

Invocation

Preferred explicit trigger:

  • $plan 帮我设计用户登录模块的实现方案

Natural-language triggers:

  • 进入 Plan 模式
  • 先出执行计划
  • 帮我生成 plan 文件

Workflow

  1. Confirm the task and current workspace.
  2. Gather only the context needed to name concrete files, modules, or integration points.
    • Start with 5-8 targeted read-only tool calls.
    • Stop early once the implementation path is clear.
  3. Choose simple, medium, or complex based on scope and risk.
  4. If mcp__sequential-thinking__sequentialthinking is available and the task is more than trivial, use it to shape the plan.
  5. Create or update a plan file under the current workspace.
    • New plan: plan/YYYY-MM-DD_HH-mm-ss-<slug>.md
    • Existing plan: reuse the previous file when the user clearly says they want to adjust the earlier plan.
  6. The plan file frontmatter should include:
---
mode: plan
cwd: <current workspace>
task: <task summary>
complexity: <simple|medium|complex>
tool: mcp__sequential-thinking__sequentialthinking
total_thoughts: <final count>
created_at: <ISO8601 timestamp>
---
  1. The plan body should contain:
    • A brief task summary
    • A numbered execution plan
    • Risks and blockers
    • path:line references where they materially help implementation
  2. Reply in concise Chinese using this shape:
    • 🎯 任务
    • 📋 执行计划
    • 🧠 当前思考摘要
    • ⚠️ 风险与阻塞
    • 📎 Plan 文件

Defaults

  • Prefer writing a plan/*.md file instead of only chatting.
  • Keep the plan decision-complete so implementation can start without extra design decisions.
  • Do not implement the plan unless the user explicitly switches from planning to execution.
  • If file writes are blocked, return the full plan text plus the intended file path.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.