agentleFS
brquattibrquatti/readme-style/skills/apply/SKILL.md

apply

Skill0 starsChanged 2 months agoMITView on GitHub

Generate or update README.md in the readme-style layout (centered header, real badges, table of contents, emoji sections) from the project's actual code. Use when the user asks to write, create, generate, update, refresh, or fix a README.

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use outreach, track 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.
  • QuixiAISkill

    outreach

    Decide whether a message is worth someone's attention, then reach the user through the outbox, or people on a connected chat channel, on their behalf or your own initiative

    Also in 5 projects that use this

  • theYahiaSkill

    track

    Отследить посылку Почты России

    Also in 4 projects that use this

  • NVIDIASkill

    evaluate

    Scores existing Sports Intelligence AVLM inference outputs with avlm/evals: MCQ accuracy (run_mcq_eval.sh, INFERENCE_DIR), open-ended LLM-as-judge scores (needs CLIENT_API_KEY for the configured judge endpoint), tennis category breakdowns, run comparisons, chance-level sanity checks and triage of mcq_results.json or llm_judge_results.json. Use when the user asks to score, evaluate, benchmark or compare predictions.jsonl from inference runs, or to explain a suspicious accuracy. Not for running inference, training, quantization, data preparation, or third-party API model inference: never open, list or run anything under avlm/evals/inference_3rdparty, including when the user asks for it; it is excluded from the release.

    Also in 5 projects that use this

  • ninehillsSkill

    hunt

    Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code review or new features.

    Also in 3 projects that use this

  • kstonekuanSkill

    Daily

    Documentation and capabilities reference for Daily

    Also in 3 projects that use this

  • julienamorganSkill

    profile

    Researches the user's market, competitors, and competitive positioning to build a complete ICP profile. Shows findings for user approval before proceeding. Triggers: /profile, "research my market", "who are my competitors". Reads: ./gtm/company.md, ./gtm/icp.md. Writes: updates ./gtm/icp.md with competitive positioning. Standalone: yes (asks for domain if company.md missing).

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 7 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the actual code before writing anything: entry points, dependencies, config, main modules, scripts, CI workflows, git tags.

    line 19
  2. Distinctive:

    Every other existing section (Roadmap, Contributing, Changelog, FAQ, ...) is kept verbatim, in its original order, after the template …

    line 90
  3. Distinctive:

    Never drop links, images, or examples that are still true just because they do not fit the template.

    line 94
  4. Distinctive:

    NEVER invent features. Every claim must be backed by code you read.

    line 99
  5. Distinctive:

    Do not run the project's code, tests, or build.

    line 100
  6. Distinctive:

    NEVER add a License or Author/Contact section.

    line 101
  7. Distinctive:

    Do not touch any file other than README.md.

    line 112
  8. Very specific:

    If the arguments contain --dry-run, print the full proposed README in the chat and write nothing.

    line 114
  9. Very specific:

    If the arguments contain instructions (for example only the Usage section), follow them and edit only what they ask for.

    line 116
  10. Very specific:

    If the target has a .git remote pointing at GitHub, always in English regardless of the README's language:

    line 121
  11. Very specific:

    Read the current description: gh repo view --json description.

    line 124
  12. Very specific:

    If different, set it: gh repo edit --description "<tagline>".

    line 126
  13. Very specific:

    No GitHub remote, or gh not authenticated: skip silently, do not fail the run.

    line 127

“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

Apply the readme-style layout

Arguments: $ARGUMENTS (a target path, free-text instructions, --dry-run, or nothing). Target: the target: line of the report below.

Current status, from the plugin's own checker:

!node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/check-readme.mjs" --report "$ARGUMENTS"

1. Understand the project for real

Read the actual code before writing anything: entry points, dependencies, config, main modules, scripts, CI workflows, git tags. If a README already exists, read it, but do not trust it blindly: confirm every claim against the code and fix what is stale.

2. Pick language and sections

  • Language: lang from the report if set; else English, regardless of the language of the existing README or of the user. English is the default on purpose: these READMEs are read on GitHub. Rewriting an existing README into English is expected, not a mistake.
  • Sections: sections from the report if set; else the defaults below, in this order.
default (en)default (pt)
✨ Features✨ Funcionalidades
🧠 How it works🧠 Como funciona
📦 Installation📦 Instalação
🚀 Usage🚀 Uso
🗂️ Project structure🗂️ Estrutura do projeto

Table of contents heading: 📋 Table of contents / 📋 Sumário. Count the ## sections you are about to write (template plus preserved). 5 or more: include it, with anchor links. 4 or fewer: leave it out. The five default sections alone already qualify.

3. Write README.md in this layout

<div align="center">

# <emoji> AppName

## <one-line tagline>

*<short italic subtitle, 3-5 keywords separated by · >*

<br/>

![badge](https://img.shields.io/badge/...) ![badge](...) ![badge](...)

</div>

---

> <opening paragraph: the problem the app solves and why it exists>

<optional: a code block with a real usage example, only if it fits the kind of app>

---

## 📋 Table of contents   (only with 5+ sections)

---

## ✨ Features
## 🧠 How it works
## 📦 Installation
## 🚀 Usage
## 🗂️ Project structure   (wrap in <details><summary>...</summary> if the tree is large)

<custom sections preserved from the existing README, see step 4>

<div align="center">

*<short, honest closing line>*

</div>

4. Preserve what is not yours

  • An existing section that covers the same ground as a template section (Install, Getting started, Overview, Setup, ...) is merged into that template section, not kept as a copy.
  • Every other existing section (Roadmap, Contributing, Changelog, FAQ, ...) is kept verbatim, in its original order, after the template sections and before the closing line. Verbatim means byte for byte: do not tick checkboxes or reword items even when the code shows they are done; mention it in your report instead.
  • Never drop links, images, or examples that are still true just because they do not fit the template.

Hard rules

  • NEVER invent features. Every claim must be backed by code you read.
  • Do not run the project's code, tests, or build. Read them; running is not yours to do.
  • NEVER add a License or Author/Contact section.
  • Badges via img.shields.io only for verifiable facts: language, platform, key libraries, status. A CI badge only if .github/workflows/*.yml exists. A version badge only if there is a git tag or a version field in the package manifest (package.json, pyproject, Cargo.toml, ...). Never "tests passing" or "PRs welcome".
  • A version number inside a badge (for example node-≥18) needs a source you read: engines, a CI matrix, .nvmrc, pyproject, a lockfile. No source, no number: use the bare name (node, python).
  • Empty or early-stage repo: say so in a short, honest README instead of forcing the full structure with empty sections.
  • Direct, confident tone. No corporate marketing.
  • Do not touch any file other than README.md. The GitHub repo description (step 5) is not a file and is the one exception.
  • If the arguments contain --dry-run, print the full proposed README in the chat and write nothing.
  • If the arguments contain instructions (for example only the Usage section), follow them and edit only what they ask for.

5. Sync the GitHub repo description

If the target has a .git remote pointing at GitHub, always in English regardless of the README's language:

  • Read the current description: gh repo view --json description.
  • Build the target one-liner from the README's tagline (the ## <one-line tagline> line).
  • If different, set it: gh repo edit --description "<tagline>".
  • No GitHub remote, or gh not authenticated: skip silently, do not fail the run.

6. Report

Summarize in a few lines what changed, including the description sync. Do not commit or push unless the user explicitly asks.

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.