Agent skill
claude-project-docs
Generate concise CLAUDE.md files and agent documentation following best practices. Use when setting up a new project for Claude Code, auditing existing CLAUDE.md, or creating progressive disclosure documentation structure.
Install this agent skill to your Project
npx add-skill https://github.com/leegonzales/AISkills/tree/main/ClaudeProjectDocs/claude-project-docs
SKILL.md
Claude Project Docs
Create well-crafted, minimal CLAUDE.md files (~60 lines) with progressive disclosure through agent_docs/.
When to Use
Invoke when user:
- Asks to "set up Claude for this project" or "create a CLAUDE.md"
- Wants to "audit" or "improve" their existing CLAUDE.md
- Needs to create agent documentation or progressive disclosure structure
- Says "help Claude understand this codebase"
Core Methodology
The 60-Line Rule
CLAUDE.md goes into EVERY session. Keep it:
- < 60 lines ideal (HumanLayer recommendation)
- < 300 lines absolute maximum
- Universally applicable - no task-specific content
WHAT/WHY/HOW Structure
# Project Name
[One sentence: what this is]
## Tech Stack
- [Framework/Language]
- [Key dependencies]
## Project Structure
[3-5 line overview of directories that matter]
## Development
[Essential commands only - build, test, run]
## Critical Rules
[2-3 non-negotiable constraints]
## Reference Documentation
When working on specific tasks, read:
- `agent_docs/[topic].md`
Progressive Disclosure
Create agent_docs/ for task-specific documentation:
| File | Content |
|---|---|
building.md |
Build commands, compilation, bundling |
testing.md |
Test commands, coverage, fixtures |
architecture.md |
System design, key decisions |
database.md |
Schema, migrations, connections |
deployment.md |
Deploy process, environments |
Claude reads these ON DEMAND, not every session.
Anti-Patterns to Prevent
NEVER include in CLAUDE.md:
- Code style rules (use ESLint/Prettier/linters)
- Full command documentation (use agent_docs/)
- Implementation examples (point to actual code)
-
300 lines of content
- Generic boilerplate from /init
Why: LLMs follow ~150-200 instructions reliably. Every unnecessary line degrades compliance.
Workflow
1. Generate New CLAUDE.md
User: Set up Claude for this project
→ Analyze: package.json, pyproject.toml, go.mod, Makefile
→ Generate: Minimal CLAUDE.md (~60 lines)
→ Create: agent_docs/ structure
2. Audit Existing CLAUDE.md
User: Audit my CLAUDE.md
→ Check: Line count, anti-patterns, task-specific content
→ Report: Issues found with severity
→ Suggest: Specific removals and agent_docs/ migrations
3. Create Agent Docs
User: Create agent docs for testing
→ Generate: agent_docs/testing.md with project-specific content
→ Update: CLAUDE.md reference section
Output Format
When generating CLAUDE.md:
- Show the complete file content
- Explain what was included and why
- List what was intentionally excluded
- Suggest agent_docs/ files to create next
References
For templates and examples:
references/claude-md-template.md- Minimal starter templatereferences/agent-docs-catalog.md- Complete agent_docs file listreferences/anti-patterns.md- Detailed anti-pattern guidereferences/examples/- Project-type examples
Principle: High leverage documentation. Every line in CLAUDE.md costs context across all sessions.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
leegonzales/AISkills
context-continuity
High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful degradation. Use when the user says "transfer," "handoff," "continue this in another chat," or needs to work around context window limits. Produces structured artifacts (Minimal ~200 words, Full ~1000 words). DO NOT trigger on simple "summarize our conversation" requests—only when transfer intent is explicit.
leegonzales/AISkills
codex-peer-review
leegonzales/AISkills
silicon-doppelganger
Build psychometrically accurate personal proxy agents for the PAIRL Conductor system. Extracts personality, decision heuristics, and values into portable schemas that enable AI agents to negotiate, filter, and act on a principal's behalf.
leegonzales/AISkills
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Dispatches three independent reviewers in parallel.
leegonzales/AISkills
fabric-patterns
Run danielmiessler/fabric CLI patterns for content analysis, extraction, summarization, writing, security analysis, and more. Use when user asks to "use fabric," "run a pattern," "extract wisdom," "summarize with fabric," or when piping content through AI patterns would be more effective than inline processing. Triggers include "fabric," "pattern," "extract wisdom," "summarize this article," "analyze this threat report," or any reference to a specific fabric pattern name.
leegonzales/AISkills
moltbook-enclave
Secure, air-gapped interface for Moltbook (social network for AI agents). Isolates untrusted external content from your main agent's memory and context.
Didn't find tool you were looking for?