third774/dotfiles
Overview
This skill generates a hierarchical AGENTS.md knowledge base for a codebase, producing a root AGENTS.md and complexity-scored subdirectory files. It balances discovery, scoring, parallel generation, and review to produce concise, non-redundant documentation for onboarding and maintenance.
How this skill works
The tool inspects the repository with fast bash scans, optional LSP codemap queries, and parallel explore agents that detect entry points, conventions, tests, CI, and anti-patterns. It scores directories with a weighted matrix (file counts, symbols, exports, centrality) to decide AGENTS.md locations, generates the root file first, then produces subdirectory AGENTS.md files in parallel, and finally deduplicates and trims outputs. It tracks phase state (discovery → scoring → generate → review) in real time.
When to use it
- Onboarding to a new or unfamiliar codebase
- Running /init to bootstrap project documentation
- Regenerating stale or missing AGENTS.md files
- Preparing a codebase overview before architectural changes
- When creating consistent, machine-friendly docs for monorepos
Best practices
- Always create a root AGENTS.md; create subdocs only where score > threshold
- Run discovery first and read existing AGENTS.md to preserve context
- Prefer parallel Task calls for explore and generation to speed analysis
- Keep files telegraphic: remove generic advice and never repeat parent content
- Limit subdirectory docs to concise 30–80 lines; root can be 50–150 lines
Example use cases
- Bootstrap documentation after cloning a large monorepo to surface domains and entry points
- Regenerate AGENTS.md after refactors so docs reflect new module boundaries
- Create compact onboarding guides for new engineers focused on conventions and anti-patterns
- Automate knowledge-base updates in CI when significant symbol centrality or file counts change
- Produce a quick code map for maintainers using LSP symbol density and reference centrality
FAQ
The skill falls back to bash analysis, AST-grep and explore agents; scoring uses available signals with adjusted weights.
Will child AGENTS.md repeat root content?
No. Child files are trimmed to avoid duplication and only document directory-specific structure, conventions, and anti-patterns.
12 skills
This skill generates hierarchical AGENTS.md knowledge bases for a codebase, creating root and complexity-scored subdirectories to bootstrap documentation.
This skill streamlines iOS/macOS development by orchestrating XcodeBuildMCP tools to build, test, run, debug, and log across targets.
This skill helps you write and debug AST-based codemods with jscodeshift for automated migrations, standardization, and large-scale refactoring.
This skill generates structured prd.json files for autonomous agent loops to plan bulk tasks with verifiable completion criteria.
This skill helps you create clear, professional Mermaid diagrams with dark mode styling and semantic colors for focused architecture visuals.
This skill helps you author custom ESLint plugins and rules using test-driven development, ensuring robust, maintainable linting with auto-fixes.
This skill reviews code as adversary to uncover bugs, security gaps, and hidden risks before deployment.
This skill enforces verification before completion by guiding you to run fresh checks and cite evidence for every claim.
This skill helps you write text that sounds human and concrete by avoiding AI telltales and emphasizing specifics.
This skill fetches source code for npm, PyPI, crates.io or GitHub repos to give AI agents deeper implementation context.
This skill helps you tailor OpenCode configuration across global and project scopes using opencode.json, agents, commands, MCP, tools, plugins, themes, and
This skill helps audit, clean up, and improve inline code documentation by enforcing self-documenting code and WHY-focused comments.
