knowledge/readme-md-creator/SKILL.md
Create, update, rewrite, or shorten repository README.md files so they stay concise, well-sectioned, non-redundant, and written in clear English. Use when the user asks to create a new README, improve or refresh an existing one, standardize structure and tone, remove bloat, or add practical setup and usage guidance, selective badges or callouts, and small ASCII architecture diagrams only when the architecture or flow is important to understanding the project.
npx skillsauth add aeondave/malskill readme-md-creatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create or update README.md files that help a new reader answer three questions fast:
Optimize for scannability, correctness, and restraint.
Before writing anything:
README.md if it exists.docs/, CONTRIBUTING.md, LICENSE, SECURITY.md, or CHANGELOG.md, link to them instead of duplicating them.Do not invent commands, features, badges, architecture, deployment targets, or screenshots.
When the repository already has a README.md, treat the existing content as the starting point:
CONTRIBUTING.md, LICENSE, CHANGELOG.md).Skip this step when creating a README from scratch.
A good header usually contains:
Keep the header compact. The reader should reach the first meaningful content quickly.
Use only the sections that help the reader act. Prefer 5–9 top-level sections for most repositories.
High-value sections, in typical order:
Omit sections that add noise. Do not add LICENSE, CONTRIBUTING, CHANGELOG, or similar sections when dedicated files already exist; link to them only when useful.
If the README is getting long, trim it and push detail into dedicated docs.
The README must be written in English, concise, divided into short sections with descriptive headings, free of repetition across sections, and specific rather than generic.
Prefer:
Avoid:
Write features as concrete outcomes, not technology lists:
Write getting-started steps as imperative copy-paste commands:
npm install && npm startTailor the README to the repository shape.
Prioritize: what problem it solves, installation, smallest working example, common usage patterns, compatibility constraints.
Prioritize: purpose, install methods, command synopsis, common examples. Option references only if short; otherwise link elsewhere.
Prioritize: what the app does, architecture only if it helps understanding, prerequisites, local setup, how to run, configuration, troubleshooting.
Prioritize: workspace purpose, high-level directory map, how to choose or run a package/sample, links to per-package docs.
Add architecture only when the system has multiple meaningful parts, non-obvious flow, or integration boundaries that are easier to grasp visually.
Decision order:
ASCII diagrams must be narrow (~80–100 chars), focused on one flow, accompanied by a short explanation, and based on verified components.
Do not add decorative ASCII art or massive pseudo-enterprise diagrams.
If you need examples or decision rules, load ./references/ascii-architecture.md.
Use GitHub Flavored Markdown.
Allowed and useful: headings, bullets and numbered lists, fenced code blocks with language tags, relative links, tables only when they improve scanning.
For GitHub alerts / callouts:
Before finishing, check:
./references/section-patterns.md — section selection rules and compact README patterns by project type../references/ascii-architecture.md — when to include ASCII architecture, when not to, and compact diagram patterns.assets/readme-template.md — lean starter template for a new README.md; replace every placeholder with repo-specific facts before saving.development
White-box auditing methodology for AI-generated ('vibe-coded') applications. Focuses on modern stack misconfigurations (Supabase, Next.js, Vercel).
development
Hybrid AI/Deterministic SAST methodology for discovering zero-day vulnerabilities in source code. Orchestrates structural search with AI-driven data flow and sink validation.
development
Auth assessment: hardware/embedded methodology; UART/JTAG/SWD/SPI/I2C, firmware extraction, boot/debug paths, embedded OS evidence.
devops
Container methodology: Identifying containerization limits, Docker/K8s misconfigurations, and executing escapes to the host node.