readme-style
User's README style preferences — ultra-terse, action-focused, <50 lines. Use when writing or reviewing any README file.
What this skill does
# README Style User preferences and corrections for writing READMEs. Claude knows how to write READMEs; this documents what makes THIS user's style different. ## Core Philosophy **Ultra-terse:** ~20-50 lines is ideal. Never more than 100 **Action-focused:** Show commands with inline comments, minimal prose **No fluff:** Skip troubleshooting, file structure, version history ## Structure Pattern ````markdown # Project Name One-liner description. ## Overview - What it does (bullet 1) - What it does (bullet 2) ## Skills Setup ``` /plugin:setup # walks through configuration ``` Main Actions ``` /plugin:do-thing # does the thing /plugin:do-thing with args # does the thing with these args /plugin:do-other selective stuff # does other with just the selective stuff ``` ```` **Key characteristics:** - Opening: Project name + single-line description - Overview: 2-3 terse bullets describing what it does - Commands: Grouped code blocks with inline `#` comments - That's it. Nothing more. ## What to Include **Include ONLY:** - ✓ Project name (H1) - ✓ One-liner description - ✓ Terse bullet points (2-3) describing what it does - ✓ Commands grouped by purpose (Setup, Main Actions, etc.) - ✓ Inline `#` comments explaining each command - ✓ Minimal section headers (just enough to group commands) ## What to EXCLUDE **Exclude ALL of these common README elements:** - ❌ Detailed feature descriptions - ❌ Philosophy/design sections - ❌ "How it works" explanations - ❌ Workflow examples - ❌ Troubleshooting guides - ❌ File structure documentation - ❌ Version history or changelog - ❌ Resource links or references - ❌ "Components" sections listing agents/skills - ❌ Verbose installation instructions - ❌ Contribution guidelines - ❌ License information - ❌ Prerequisites sections - ❌ Configuration details (beyond setup command) ## Before/After Examples ### Bad (Standard README Approach) ```markdown # Development Workflow Plugin Comprehensive tooling for Git and GitHub workflows with intelligent automation. ## Features This plugin provides: - **Smart Git Operations**: Streamlined commit workflows with automatic formatting - **GitHub Integration**: Seamless PR creation and issue management - **Workflow Automation**: Pre-commit hooks and quality checks ## Components ### Agents - `pr-creator` - Creates pull requests with proper formatting - `commit-helper` - Assists with commit message formatting ### Skills - `git-workflow` - Documents git workflow preferences - `github-workflow` - GitHub interaction patterns ### Commands - `/pr` - Create pull request - `/commit` - Smart commit with formatting ## How It Works The plugin integrates with your local git repository to provide enhanced workflow capabilities. It uses the GitHub CLI when available and falls back to the GitHub MCP server for API operations... [... continues for 50+ more lines ...] ``` **Issues:** - ❌ Too verbose (100+ lines) - ❌ "Features" section with prose descriptions - ❌ "Components" section listing internals - ❌ "How It Works" section explaining architecture - ❌ Prose explanations instead of code examples ### Good (Our Preferred Style) ````markdown # DMV Git and GitHub workflow preferences for Claude. ## Overview - Tells Claude the user's commit message format (terse, no emojis, no attribution) - Tells Claude to prefer gh CLI over GitHub MCP when available - Documents pre-commit hook retry logic (edge case handling) ## Commands Setup ``` /dmv:setup # walks through git and GitHub configuration ``` Main Actions ``` /pr # create pull request from current branch /pr --draft # create draft pull request /commit "message" # commit with user's preferred format /github:issue <number> # fetch and analyze issue ``` ```` ## Command Block Formatting **Pattern:** ````markdown Group Label ``` /command # what it does /command with args # what it does with args /command:subcommand # what the subcommand does ``` ```` **Details:** - Group label as plain text (not heading): `Setup`, `Main Actions`, `Analysis` - Code block with commands left-aligned - Inline `#` comments right-aligned (use spaces to align) - One blank line between groups - No prose explanations outside code blocks ## Anti-Pattern Detection **If you see these in a README draft, flag for removal:** - "Features" heading followed by prose - "Components" section listing agents/skills - "How It Works" explanations - "Philosophy" or "Design" sections - "Installation" steps (beyond setup command) - "Troubleshooting" section - "Prerequisites" section - "File Structure" documentation - Workflow examples with step-by-step prose - Version history or changelog - Contribution guidelines ## The Transformation Rule **Standard README approach:** ``` Explain what it does → List features → Document components → Show examples ``` **Our approach:** ``` One-liner → 2-3 bullets → Commands with comments → Done ```
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.