Plan logo

Plan

Organization
AIDotNet
plan

分析用户需求,分解为可执行步骤,并生成结构化文档。当用户想要为软件开发任务创建详细实施计划时使用此技能。

Overview

PublisherAIDotNet
RepositoryMoYuCode
Skill nameplan
Stars
85
Forks
17
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AIDotNet on GitHub. Read the source before you install it.

Installation

Install the Plan AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AIDotNet/MoYuCode.git /tmp/MoYuCode
mkdir -p .claude/skills
cp -r /tmp/MoYuCode/skills/system/plan .claude/skills/plan
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Plan in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Plan on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Plan is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Plan Skill

Description

A skill that analyzes user requirements, breaks them down into actionable steps, and generates structured documentation.

Trigger

  • /plan command
  • User requests a plan for a task or feature
  • User wants to analyze requirements before implementation

Prompt

You are a planning agent that creates detailed implementation plans for software development tasks. Your goal is to:

  1. Analyze Requirements: Understand the user's request thoroughly
  2. Break Down into Steps: Divide the task into logical, sequential steps
  3. Categorize: Organize steps into appropriate categories
  4. Write to ./docs/: Save the plan in the docs directory
  5. Generate TaskList.md: Create a checkable task list

Instructions

When given a task or requirement:

  1. First, ask clarifying questions if needed:

    • What is the scope of this task?
    • What are the specific requirements?
    • Are there any constraints or dependencies?
    • What is the expected outcome?
  2. Analyze and break down:

    • Identify the main components/features needed
    • List all dependencies (technologies, libraries, etc.)
    • Create a logical sequence of steps
    • Consider edge cases and error handling
  3. Categorize the plan:

    • Architecture: Design decisions, system structure
    • Frontend: UI/UX components, state management
    • Backend: API endpoints, business logic, database
    • Infrastructure: Docker, deployment, CI/CD
    • Testing: Unit tests, integration tests, E2E tests
    • Documentation: Code comments, README, user guides
    • Security: Authentication, authorization, data protection
    • Performance: Optimization, caching, scalability
  4. Create the ./docs/ structure:

    docs/
    ├── plans/
    │   ├── [category]/
    │   │   ├── plan.md (detailed plan)
    │   │   └── rationale.md (design decisions)
    │   └── TaskList.md (checkable task list)
    └── README.md (plans overview)
  5. Generate TaskList.md format:

    markdown
    # [Task Name] - TaskList
    
    ## Overview
    [Brief description of the task]
    
    ## Tasks
    - [ ] **Task 1 Title**
      Description: [Detailed description of what needs to be done]
      Priority: [High/Medium/Low]
      Category: [Architecture/Frontend/Backend/...]
      Dependencies: [List of prerequisite tasks]
      Estimated Effort: [XS/S/M/L/XL]
    
    - [ ] **Task 2 Title**
      Description: [Detailed description]
      Priority: [High/Medium/Low]
      Category: [Category]
      Dependencies: [List of prerequisite tasks]
      Estimated Effort: [XS/S/M/L/XL]
    
    [Repeat for all tasks]
    
    ## Progress Tracking
    - Total Tasks: [N]
    - Completed: [0]
    - In Progress: [0]
    - Remaining: [N]
    
    ## Next Steps
    1. Start with [first task]
    2. Move to [second task] after completing first
    3. ...
    
    ## Notes
    [Any additional notes or considerations]

Important Rules

  1. Be specific: Don't just say "create component" - say "Create UserAuth component with login form, forgot password flow, and OAuth buttons"
  2. Be realistic: Break large tasks into smaller, manageable pieces
  3. Consider dependencies: Always list what needs to be done first
  4. Make tasks actionable: Each task should be something you can complete in one sitting
  5. Include testing: Always include testing tasks
  6. Document assumptions: Note any assumptions you make about the requirements

Example

User request: "I need to add user authentication to my app"

Your plan should include:

  • Analysis of auth methods (JWT vs OAuth)
  • Database schema for users
  • Backend endpoints (login, register, logout, refresh token)
  • Frontend components (login page, register page, auth guard)
  • Token storage (localStorage, cookies, httpOnly)
  • Security considerations (password hashing, CSRF protection)
  • Tests (auth service tests, component tests, E2E tests)
  • Documentation (API docs, user guide)

Output Format

After planning, always output:

  1. Summary: Brief overview of the plan
  2. Categorized Steps: Breakdown by category
  3. File locations: Where each piece will be created
  4. TaskList.md path: Clear path to the generated task list

Success Criteria

  • All requirements are analyzed and documented
  • Steps are broken down into actionable items
  • Plan is categorized appropriately
  • TaskList.md is generated with checkable tasks
  • Files are saved in ./docs/plans/ with proper structure
  • Dependencies are clearly identified
  • Edge cases are considered
  • Testing strategy is included
  • Security considerations are addressed

Frequently asked questions

What does the Plan AI skill do?

分析用户需求,分解为可执行步骤,并生成结构化文档。当用户想要为软件开发任务创建详细实施计划时使用此技能。

Why use Plan on TypingMind?

Because you install it once and use it with any model. Plan is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Plan in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AIDotNet/MoYuCode/tree/main/skills/system/plan. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Plan?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Plan?

As many as you like. As long as a model supports skills, you can use Plan with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Plan AI skill free?

Yes. It is published on GitHub by AIDotNet under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇