agentleFS
tuanda2912tuanda2912/cairn/.claude/skills/create-readme/SKILL.md

create-readme

Skill0 starsChanged 5 months agoMITView on GitHub

Create or refresh a polished, well-structured README.md for the current project. Use when the user wants a README written, improved, restructured, or "made to look good / put in good shape". Reviews the whole project, leads with features, uses a badge row + GitHub admonitions, keeps it concise and scannable, and omits LICENSE/CONTRIBUTING/CHANGELOG (those get their own files).

28 other projects use a version of this, 22 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use readme-i18n, design-md and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • klauswgSkill

    readme-i18n

    Use when the user wants to translate a repository README, make a repo multilingual, localize docs, add a language switcher, internationalize the README, or update localized README variants in a GitHub-style repository.

    Also in 4 projects that use this

  • klauswgSkill

    design-md

    Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files

    Also in 4 projects that use this

  • GoogleSkill

    improve-codebase-architecture

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    Also in 5 projects that use this

  • StrayDragonSkill

    ui-ux-pro-max

    UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

    Also in 5 projects that use this

  • VercelSkill

    agent-browser

    Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

    Also in 4 projects that use this

  • AnasX7Skill

    design-taste-frontend

    Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Decide the audience and the one-sentence pitch: before drafting. The tagline is the hardest line to get right — make it concrete, not …

    line 26
  2. Distinctive:

    Not every project needs every section — drop the ones that don't apply rather than padding them.

    line 57
  3. Very specific:

    No invention: If a fact isn't verifiable in the repo, leave it out or mark it > TODO:.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/create-readme — write a README that's worth reading

You're a senior open-source engineer who writes READMEs that are appealing, informative, and easy to scan. Review the whole project first, then produce (or reshape) a README.md the maintainer would be proud to pin to the repo's front page.

Adapted from the github/awesome-copilot create-readme skill, with cross-referenced best practices from make a README, standard-readme, and the sibling create-llms / create-tldr-page skills folded in.

Process

  1. Read the project before writing a word. Inspect the manifest (package.json, pyproject.toml, Cargo.toml, go.mod, …), entry points, config, existing docs (README, docs/, CLAUDE.md, wiki/), and the file tree. Skim the most important source to learn what it actually does. Every claim in the README must trace to something real in the repo — never invent features, commands, or badges.
  2. Look for an existing README and a logo/icon. Improve in place rather than discarding good content. If the repo has a logo/icon (an image in assets/, docs/, .github/, or a distinctive emoji already in use), put it in the header.
  3. Decide the audience and the one-sentence pitch before drafting. The tagline is the hardest line to get right — make it concrete, not buzzwordy.
  4. Draft following the structure below, then tighten.
  5. Self-check against the checklist at the end. Read it once as a newcomer would.

Structure to produce

Order matters — lead with what hooks a reader, defer the deep config.

  1. Header — # Project + logo/icon if one exists.
  2. Badge row — only badges that are true and useful (license, build/CI, package version, language/runtime version, code style). Prefer shields.io. Don't fabricate a CI/coverage badge that doesn't exist.
  3. One-line description — a blockquote tagline saying what it is and why it matters.
  4. Nav / table of contents — a one-line ·-separated set of anchor links if the README is long (roughly > 4 H2 sections). Skip it for short READMEs.
  5. Short intro paragraph — 2–4 sentences expanding the tagline (the problem it solves, who it's for).
  6. Features — a bullet list of concrete capabilities, lead-bolded (**Thing.** explanation). This is the section readers scan first; make each bullet earn its place.
  7. Requirements / Prerequisites — runtimes, accounts, external tools (only if non-trivial).
  8. Installation — the copy-paste commands to get it on a machine.
  9. Usage / Quick start — the most common path, as a runnable example first (the create-tldr-page lesson: show before you explain). Then options/flags as a table.
  10. Examples — a few realistic scenarios if the tool warrants them.
  11. How it works / Architecture — only if it genuinely aids understanding; keep it tight or link out.
  12. Configuration — options table, if any.
  13. Project layout — a categorized file/dir map for anything non-obvious. Writing it so an LLM could navigate the repo from it (the create-llms lesson) makes it better for humans too.
  14. Links out — point to CONTRIBUTING.md, SECURITY.md, LICENSE, full docs — as a short note or admonition, not as dedicated sections (see rules).

Not every project needs every section — drop the ones that don't apply rather than padding them.

Rules (hard)

  • No LICENSE / CONTRIBUTING / CODE_OF_CONDUCT / CHANGELOG sections. Those have dedicated files. A license badge and a one-line "see CONTRIBUTING.md" pointer are fine; a full heading is not.
  • Don't overuse emojis. A single icon in the header is plenty. No emoji-per-bullet.
  • Use GFM + GitHub admonitions where they earn their place: > [!NOTE], > [!TIP], > [!IMPORTANT], > [!WARNING], > [!CAUTION]. Use [!WARNING] / [!CAUTION] for real footguns, not decoration.
  • Concise and scannable. Aim for ~200–1500 words of prose; if it sprawls past that, move depth into a docs/ page and keep the README focused on install + usage + links. Favor tables and short bullets over walls of text.
  • No invention. If a fact isn't verifiable in the repo, leave it out or mark it > TODO:.
  • Match the project's voice. Mirror the naming and tone already present in the codebase/docs.

Inspiration

Borrow structure, tone, and density from these (don't copy verbatim):

Final checklist

  • Header has the title and (if available) a logo/icon.
  • Badge row is present and every badge is true.
  • Tagline states what it is and why it matters, in one line.
  • Nav line present iff the README is long; every anchor resolves to a real heading.
  • Features lead the body; each bullet is concrete and lead-bolded.
  • Install + a runnable quick-start example appear early.
  • Admonitions used for the genuinely important/dangerous notes only.
  • No LICENSE/CONTRIBUTING/CHANGELOG sections — links/badges instead.
  • Emojis minimal; tone matches the project.
  • Every claim traces to the repo; nothing invented.
  • Reads cleanly top-to-bottom as a newcomer; under ~1500 words of prose.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.