readme-generator
>-
Works with
--- name: readme-generator description: >- license: MIT --- ## README Generator Analyze a project's structure, tech stack, and code to generate a comprehensive, well-organized README.md. ## Workflow 1. **Scan the project structure** ```bash find . -maxdepth 3 -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/dist/*" | head -80 ``` Identify the project type: Library, CLI Tool, Web Application, API Service, or Monorepo. 2. **Detect the tech stack** Read config files (`package.json`, `tsconfig.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`, `Dockerfile`). Extract: language, framework, test runner, linter, bundler, deployment target. 3. **Identify key entry points and exports** Read main source files to understand what the project does — exported functions, CLI commands, API endpoints. 4. **Extract existing documentation hints** Look for JSDoc/docstrings, existing partial README, CHANGELOG, LICENSE, CONTRIBUTING. 5. **Generate the README** with these sections: - **Title and Badges** (license, language, version, CI status) - **Description** (2-3 sentences) - **Features** (bulleted key capabilities) - **Prerequisites** (runtime versions, required accounts) - **Installation** (actual commands from package.json scripts) - **Configuration** (environment variables, config files) - **Usage** (real code examples matching the actual API) - **API Reference** (if applicable — table of endpoints/functions) - **Project Structure** (key directories tree) - **Scripts** (table of npm/make commands) - **Contributing** (dev setup, testing, PR process) - **License** (type with link) 6. **Write the README** If a README exists, ask to replace or merge. ## Rules - Always read actual source code — never guess at what the project does - Match README complexity to project size - Use real values (actual script names, actual dependencies, actual ports) - Include working code examples that reflect the actual API - If no tests exist, suggest adding them in Contributing - Keep tone professional but approachable - Do not include irrelevant sections (no API Reference for a CLI tool)
More Writing & Documentation skills
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
repo-intake-and-plan
lllllllama/rigorpilot-skills
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
