generate-claudemd

Solid

Generate project-specific AGENTS.md from repo analysis.

AI & Automation 3 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
20
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Generate AGENTS.md Skill Produce a project-specific AGENTS.md through a 4-phase pipeline: SCAN repo facts, DETECT domain enrichment, GENERATE from template, VALIDATE output. The goal is a AGENTS.md that makes new Codex sessions immediately productive by documenting only verified, project-specific facts. This skill generates new AGENTS.md files. It cannot improve an existing one (use `Codex-md-improver` for that), cannot document private dependencies or encrypted configs it cannot read, cannot infer runtime behavior from static files, and cannot replace deep domain expertise — enrichment patterns are templates, not knowledge. This skill does not use `context: fork` because it requires interactive user gates (confirmation when AGENTS.md already exists, review of generated output), which a forked context would bypass. ## Reference Loading Table | Signal | Load These Files | Why | |---|---|---| | tasks related to this reference | `CLAUDEMD_TEMPLATE.md` | Loads detailed guidance from `CLAUDEMD_TEMPLATE.md`. | | example-driven tasks, errors | `examples-and-errors.md` | Loads detailed guidance from `examples-and-errors.md`. | ## Instructions Execute all phases sequentially. Verify each gate before advancing. Load the template from `${CLAUDE_SKILL_DIR}/references/CLAUDEMD_TEMPLATE.md` before Phase 3. On explicit user request, two optional modes are available: - **Subdirectory AGENTS.md**: Generate per-package AGENTS.md files for monorepos. - **Minimal Mode** ("minimal AGENT...

Details

Author
maister-dev
Repository
maister-dev/maister
Created
2 weeks ago
Last Updated
today
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category