readme-creator
Writes or rewrites README.md files tailored to the project type (CLI, library, app, framework, monorepo, or skill bundle). Discovers project context, selects the right structure, writes section by section, and validates against quality checks. Use when creating a README, writing a README from scratch, rewriting a bad README, bootstrapping project documentation, or asking "write a README for this project."
What this skill does
# README Creator Write or rewrite a README.md tailored to the project type and audience. ## Reference Files | File | Read When | |------|-----------| | `references/section-templates.md` | Phase 3: choosing structure and writing sections for a specific project type | | `references/quality-checklist.md` | Phase 5: validating the finished README against quality standards | | `references/badges-and-shields.md` | Phase 4: adding badges after the main content is written | ## README Workflow Copy this checklist to track progress: ```text README progress: - [ ] Phase 1: Discover project context - [ ] Phase 2: Choose README structure - [ ] Phase 3: Write sections - [ ] Phase 4: Add badges and extras - [ ] Phase 5: Validate quality ``` ### Phase 1: Discover project context Read the project before asking questions. Explore files to detect the project type: - Read `package.json`, `Cargo.toml`, `pyproject.toml`, `go.mod`, or equivalent for name, description, license, dependencies, scripts, and bin field. - Read existing README.md (if rewriting). - Scan directory structure to understand architecture. Classify into one of seven project types: | Type | Signals | |------|---------| | CLI tool | `bin` field in package.json, `src/cli.ts`, commander/yargs dependency | | Library / package | `main`/`exports` in package.json, no bin field, `src/index.ts` | | Web app | `next.config.ts`, `vite.config.ts`, framework dependency, no npm publish | | Framework | Plugin/middleware architecture, configuration API, extensibility points | | Monorepo (published) | `turbo.json` or `pnpm-workspace.yaml`, packages published to a registry | | Monorepo (private) | `turbo.json` or `pnpm-workspace.yaml` with `"private": true`, no registry publish | | Skill bundle | `skills/` directory with SKILL.md files | Ask the user only for what cannot be discovered from the code: - What problem does the project solve? (the "why") - Who is the target audience? - Any sections to include or exclude? ### Phase 2: Choose README structure Load `references/section-templates.md`. Select sections based on the project type: | Section | CLI | Library | App | Framework | Monorepo (pub) | Monorepo (priv) | Skills | |---------|-----|---------|-----|-----------|----------------|-----------------|--------| | Title + one-liner | yes | yes | yes | yes | yes | yes | yes | | Badges | yes | yes | -- | yes | yes | -- | -- | | Features / highlights | yes | yes | yes | yes | -- | -- | yes | | Install | yes | yes | -- | yes | yes | -- | -- | | Quick start / usage | yes | yes | yes | yes | yes | yes | yes | | Options / API reference | yes | yes | -- | yes | -- | -- | -- | | Configuration | opt | opt | yes | yes | opt | -- | -- | | Environment variables | -- | -- | yes | -- | -- | -- | -- | | Packages / workspaces table | -- | -- | -- | -- | yes | yes | -- | | Skills table | -- | -- | -- | -- | -- | -- | yes | | Requirements | yes | yes | opt | yes | opt | yes | -- | | Common commands | -- | -- | -- | -- | opt | yes | -- | | Contributing | opt | opt | opt | opt | opt | opt | opt | | License | yes | yes | yes | yes | yes | opt | opt | ### Phase 3: Write sections Load `references/section-templates.md`. Write each section following the template for the detected project type. Key principles: - Title is the project name. One-liner directly below, no heading. - Feature list above the fold (before Install) so readers see value before effort. - Install: single fastest path first. `npm install -g` for CLIs, `npm install` for libraries. - Usage: 3-5 runnable examples, simplest first. Real values, not `foo` or `example`. - Every code block must be copy-pasteable and runnable without modification. - A reader should be able to install and run something within 60 seconds. - Progressive disclosure: basic first, advanced later or in linked docs. ### Phase 4: Add badges and extras Load `references/badges-and-shields.md`. Add badges only if the project is published to a registry. Place directly below the title and one-liner. Maximum 4 badges. Skip badges entirely for private apps, unpublished projects, and skill bundles. ### Phase 5: Validate quality Load `references/quality-checklist.md`. Run through every applicable check. Fix issues before finalizing. After fixes, reread the README top to bottom to confirm it flows naturally. ## Anti-patterns - Do not write a README longer than the codebase warrants - Do not include a table of contents for READMEs under 100 lines - Do not use "About" or "Introduction" as the first heading - Do not ship the default create-next-app or create-vite README - Do not include badges for unpublished projects - Do not include a "Features" section that restates the one-liner - Do not write "This project is..." or "This is a..." — describe what it does directly - Do not include empty Contributing or Acknowledgements sections - Do not use `foo`, `bar`, or `test` as example values ## Skill Handoffs | When | Run | |------|-----| | After README is written, audit prose quality | `docs-writing` | | If project needs AGENTS.md / CLAUDE.md | `agents-md` |
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.