github-readme-and-profile-writing
Skill1 starsChanged 42 days agoMITView on GitHub
Writes and improves GitHub READMEs for projects, skills, organizations, and personal profiles—clear positioning, install and quick start, visual proof, badges, and one next action. Use when creating, auditing, or rewriting a README or profile README.
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Verify URLs; test install and quick start on a clean environment when possible.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GitHub README and Profile Writing
Serve the primary reader first, then discovery, trust, contribution, and appropriate conversion.
Before writing
Inspect the repository first. Ask only what changes the README: audience, status, intended action, canonical URLs, approved claims, screenshots or demos, license, support channel, services, and type (project, organization, skill, profile). Keep the user's wording. Never invent metrics, testimonials, users, revenue, partners, or capabilities, and never publish secrets, private client details, or unapproved logos. For personal profiles, read profile-readme.md.
Structure
Default order: what it is and who it helps → why it matters → fastest install or try → minimal working example → proof (demo, screenshot, architecture, status) → deeper docs and contribution → one next action (use, star, feedback, contribute, contact, hire). Include only sections with real content; a short complete README beats a long placeholder.
- Project: problem → value → install → quick start → features → demo → architecture → roadmap → contributing → license.
- Skill: purpose → install command → starter prompt → workflow → optional companions → limitations → related skills → feedback.
- Organization: mission → products or services → proof → open source → contact.
Proof and badges
Put one strong, current, public proof near the top when the project is visual: screenshot, short GIF/video, or live demo for UI; rendered example or playground for libraries; terminal session for CLIs; request/response or architecture diagram for APIs. Meaning stays in text with descriptive alt text; no decorative image walls.
Badges are optional proof: three to six at most, accurate and linked—release, CI, meaningful coverage, license, docs or demo, authoritative package/download counts. No fake stars, visitor counters, animated walls, or per-dependency badges.
Discoverability
Plain category phrase in the title, first sentence, and one heading; descriptive headings, links, alt text, topics, canonical URLs; natural synonyms; link the specific project first, then the repo root; no keyword stuffing, hidden text, or boilerplate. Keep the repo description, topics, website, social preview, CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md, license, templates, and changelog aligned—link deeper docs instead of duplicating them, and never link empty placeholders.
Before publishing
Verify URLs; test install and quick start on a clean environment when possible; label current, beta, planned, and deprecated features; check links, alt text, code fences, narrow-width and dark-mode rendering. Services and affiliate links appear only when relevant and clearly labeled.
Output
Propose structure and content before overwriting an existing README unless direct replacement is authorized. Include a link checklist, missing evidence, and suggested follow-up assets.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

