Agent skill

GitHub Readme

by thatrebeccarae in thatrebeccarae/claude-marketing

Generate, audit, or update GitHub READMEs with project-type-aware structure, voice calibration, and SEO/AEO discoverability guidance.

MITAuto-check passedMarketing & SEO

Install GitHub Readme

skills CLI
$ npx skills add thatrebeccarae/claude-marketing --skill github-readme -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install thatrebeccarae/claude-marketing github-readme --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/github-readme .claude/skills/github-readme && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
github-readme
GitHub stars
162
Token cost
~2.9k tokens
SKILL.md length
1,142 words
Files
4
Skills in repo
55
Repo updated
First seen
Licence
MIT

At a glance

Generate, audit, or update GitHub READMEs with project-type-aware structure, voice calibration, and SEO/AEO discoverability guidance.

  • Works in 5 steps: Parse and Validate → Scan the Repo → Detect Project Type → …
  • Tasks that involve Technical documentation
  • SKILL.md covers Install, When to Use, Modes and Step 0: Parse and Validate, plus 9 more sections
  • Calls git and gh; reaches img.shields.io

What it does

GitHub Readme is an agent skill from thatrebeccarae/claude-marketing. Generate, audit, or update GitHub READMEs with project-type-aware structure, voice calibration, and SEO/AEO discoverability guidance. Three modes: generate (new), audit (check existing), update (patch). Detects repo type and adapts sections, tone, and badges accordingly.

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `EXAMPLES.md` and `REFERENCE.md`).

It sits in Marketing & SEO, covering Technical documentation, AI search optimization and Performance reviews. It works with GitHub, TypeScript and Git. The repository describes itself as: A full marketing department for Claude Code. Skill packs for Klaviyo, Shopify, GA4, Looker Studio, paid media, and more. Audit, optimize, and report using natural language. The licence is MIT.

When your agent uses it

  • Tasks that involve Technical documentation
  • Tasks that involve AI search optimization
  • Tasks that involve Performance reviews

Example prompts

  • “/github-readme”

Requirements

  • Python 3
  • Node.js
  • Docker

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Parse and Validate
  2. Scan the Repo
  3. Detect Project Type
  4. Discoverability Audit
  5. Generate / Audit / Update

What it can do on your machine

Read from SKILL.md and the folder at commit a8a63ec. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • img.shields.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

GitHub Readme loads about 2.9k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 1,142 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from thatrebeccarae/claude-marketing at commit a8a63ec, republished under its MIT licence (© thatrebeccarae). 1,142 words, ~2,919 tokens.

Download SKILL.mdSave it as .claude/skills/github-readme/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
github-readme
description
Generate, audit, or update GitHub READMEs with project-type-aware structure, voice calibration, and SEO/AEO discoverability guidance. Three modes: generate (new), audit (check existing), update (patch). Detects repo type and adapts sections, tone, and badges accordingly.
license
MIT
origin
custom
author
Rebecca Rae Barton
author_url
https://github.com/thatrebeccarae
metadata.version
2.0.0
metadata.category
devops
metadata.domain
github
metadata.updated
2026-03-19
metadata.tested
2026-03-19
metadata.tested_with
Claude Code v2.1

GitHub README Generator

Generate, audit, or update repository READMEs with project-type detection, voice calibration, discoverability guidance, and scored quality audits.

Install

bash
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/github-readme ~/.claude/skills/

When to Use

  • Starting a new public repo and need a solid README from scratch
  • Auditing an existing README for quality, discoverability, and security issues
  • Updating a README after the repo has evolved (new deps, features, structure)
  • Preparing a repo for public release and want discoverability optimized

Modes

/github:readme generate [repo-path]   # Scan repo, detect type, generate README
/github:readme audit [repo-path]      # Score existing README (read-only, 0-100)
/github:readme update [repo-path]     # Re-scan, silent audit, patch with approval

Default repo-path is the current working directory if omitted.


Step 0: Parse and Validate

Expect: /github:readme {mode} [repo-path]

  1. Extract mode — generate, audit, or update. Any other value or missing → error with usage hint. STOP.
  2. Extract repo-path — second argument, or current working directory if omitted.
  3. Validate — confirm path exists, is a directory, and contains .git. If not → error. STOP.

Store repo_path (absolute) and mode.


Step 1: Scan the Repo

Gather context by reading available files. Skip gracefully if a file does not exist.

Package/config files (tech stack detection):

  • package.json — Node/TypeScript/React
  • Cargo.toml — Rust
  • pyproject.toml, setup.py, requirements.txt — Python
  • go.mod — Go
  • tsconfig.json — TypeScript confirmation
  • Dockerfile, docker-compose.yml — containerization
  • Makefile, justfile — build system
  • .github/workflows/ — CI/CD

Directory structure:

  • Run ls at repo root for top-level layout
  • Note: src/, bin/, lib/, scripts/, docs/, tests/, skills/, templates/, plugins/, .github/

Existing docs:

  • README.md, CONTRIBUTING.md, SECURITY.md, LICENSE, ARCHITECTURE.md, CHANGELOG.md, CODE_OF_CONDUCT.md, llms.txt

Git remote:

  • Run git -C {repo_path} remote get-url origin
  • Extract {owner} and {repo} from the URL
  • Determine public/private: .public-repo marker → public; -dev suffix or no marker → ask user

Step 2: Detect Project Type

Classify the repo into exactly one type based on scan signals:

TypeSignals
tool/CLIHas bin field in package.json, CLI entry points, man pages, command parsers (yargs, clap, cobra)
library/SDKHas main/exports/module field, published to npm/PyPI/crates.io, no CLI entry
collection/marketplaceContains multiple independent items: skills/, templates/, plugins/, recipes/ directories with 3+ subdirectories
web-appHas React/Vue/Svelte/Next/Nuxt, server framework (Express, FastAPI, Actix), deployment config (Vercel, Dockerfile)
personal/experimentalSmall repo (<20 files), no package publishing config, no CI, no semver tags

If ambiguous, ask the user to confirm. Store as project_type.


Step 3: Discoverability Audit

Before generating or auditing README content, check these repo-level discoverability signals. Present findings and suggestions to the user.

Repo name:

  • Is it keyword-rich and searchable? (e.g., markdown-lint-action > my-linter)
  • Flag generic names: app, project, tool, my-thing

GitHub About/description:

  • Read via gh repo view if available
  • Should be 3-8 words, front-loaded with primary keyword
  • Suggest improvement if missing or generic

Topics:

  • GitHub allows up to 20 topics
  • Suggest relevant topics based on detected tech stack, project type, and domain
  • Include both broad (typescript, cli) and specific (markdown-parser, github-action) topics

Social preview image:

  • Flag if missing — suggest creating one (1280x640px recommended)

llms.txt (optional):

  • If repo is a library/SDK or tool/CLI, suggest generating an llms.txt file
  • Purpose: helps LLMs understand and recommend the project accurately

Present discoverability suggestions. User can accept, skip, or defer. These do NOT block README generation.


Step 4: Generate / Audit / Update

Generate Mode

4a. Check for existing README — if present, confirm overwrite or suggest update mode instead.

4b. Select sections based on project type (see Section Menu below).

4c. Voice calibration:

  • Default: professional product voice — clear, direct, no hedge language, no marketing fluff
  • Personal/experimental repos OR explicit user opt-in: first-person voice allowed
  • Never: passive voice in problem statements, emojis in prose, marketing fluff

4d. Generate each section:

  • Title + description — derive name from package config or directory; one-line bold description under 120 chars
  • Badges — see Badge Selection below
  • Getting Started / Install — prerequisites with versions, install steps, first-run command. Under 20 lines.
  • Type-specific sections — per Section Menu. Only include if enough scanned context exists.
  • "Why" section (personal/experimental only) — ask user for 2-3 sentences. Do not fabricate.
  • License — read LICENSE file type. One line linking to the file.

4e. Run PII/infrastructure scrub (see below). Remove violations before writing.

4f. Write {repo_path}/README.md and display summary.

Audit Mode (read-only)

Read existing README. Do NOT modify any files.

Run quality-signal checks and score against weighted rubric:

CategoryWeightChecks
Clarity25Clear one-line description? Title is descriptive?
Usability25Working install/setup command? Code examples? Getting started under 20 lines?
Credibility15Badges present? Badge URLs resolve? License section present?
Currency15Version numbers match package config? Tech stack matches repo? No stale links?
Security20No PII or infrastructure leaks? No API keys/tokens? No private hostnames/IPs?

Scoring: Each category scored 0-100, final score = weighted average.

=== README Audit: {repo-name} ===
Score: {X}/100

Clarity:      {X}/25
Usability:    {X}/25
Credibility:  {X}/15
Currency:     {X}/15
Security:     {X}/20

PASS:
  - {passing checks}

WARN:
  - {warnings with specific detail}

FAIL:
  - {failures with specific detail and fix suggestion}
Show full SKILL.md (426 more words)Show less
Update Mode
  1. Re-scan repo (Step 1) to detect current state
  2. Run silent audit — store results, do not display
  3. Generate update plan — diff-style, grouped by category:
    • [STRUCTURE] — missing/outdated sections, badge changes
    • [CONTENT] — stale version numbers, outdated tech references
    • [VOICE] — hedge language, marketing fluff, passive voice
    • [SECURITY] — PII/infra violations (applied automatically)
  4. Show preview — numbered list of proposed changes
  5. User approval — y (all), N (cancel), or comma-separated numbers
  6. Apply, run final PII scrub, write file, display summary

Section Menu by Project Type

Sectiontool/CLIlibrary/SDKcollectionweb-apppersonal
Title + descriptionRequiredRequiredRequiredRequiredRequired
BadgesRequiredRequiredRequiredRequiredOptional
Getting Started / InstallRequiredRequiredRequiredRequiredRequired
Usage / CommandsRequired--------
API Reference--Required------
Catalog / Index----Required----
FeaturesRecommendedRecommended--Required--
ConfigurationRecommendedRecommended--Recommended--
Architecture------Recommended--
Why I Built This--------Required
Who This Is ForRecommendedRecommendedRecommended----
ContributingRecommendedRequiredRecommendedRecommended--
LicenseRequiredRequiredRequiredRequiredRequired

Voice Guidelines

TypeDefault ToneExample Opening
tool/CLIDirect, practical"Fast Markdown linting for CI pipelines."
library/SDKTechnical, precise"A typed HTTP client for the Stripe API."
collectionOrganized, scannable"50+ reusable GitHub Actions workflows."
web-appProduct-focused, clear"Real-time project dashboard with team analytics."
personalFirst-person, opinionated"I needed a better way to track reading habits."

Always: direct, specific, opinionated, short paragraphs (4 sentences max). Never: hedge language, marketing fluff, passive voice in problem statements, emojis in prose.


Badge Selection

Based on detected tech stack, generate 1-3 tech badges + license badge minimum.

Use style=for-the-badge for all badges. Generic patterns:

markdown
![License](https://img.shields.io/github/license/{owner}/{repo}?style=for-the-badge)
![GitHub Stars](https://img.shields.io/github/stars/{owner}/{repo}?style=for-the-badge)
![TypeScript](https://img.shields.io/badge/TypeScript-3178C6?style=for-the-badge&logo=typescript&logoColor=white)
![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=python&logoColor=white)
![Node.js](https://img.shields.io/badge/Node.js-339933?style=for-the-badge&logo=nodedotjs&logoColor=white)
![React](https://img.shields.io/badge/React-61DAFB?style=for-the-badge&logo=react&logoColor=black)

Badge order: tech stack (left) → stars → license (right).


PII / Infrastructure Scrub

Run in ALL modes. Scan generated or existing README text for:

  • Private hostnames
  • IP addresses (especially 10.x, 172.16-31.x, 192.168.x, 100.x Tailscale)
  • Internal network/VLAN names
  • Device identifiers or serial numbers
  • Client or employer names that should not be public
  • Personal email addresses
  • API keys or tokens (sk-, token_, ghp_, Bearer, long alphanumeric strings)
  • Internal Docker/service config (private port mappings, container names)
  • SSH config references (aliases, private key paths)

If violations found: list each, remove or redact, show user what was removed. Security violations are never optional — applied automatically in update mode.


Key Principles

  • Detect, don't assume. Scan the repo and adapt structure to what actually exists.
  • Professional by default. First-person voice is opt-in, not the default.
  • Discoverability matters. Repo name, description, topics, and llms.txt are part of the README story.
  • Quality over completeness. Fewer well-written sections beat bloated README with empty placeholders.
  • Security is non-negotiable. PII/infra scrub runs in every mode, every time.
  • Audit mode is read-only. Never modify files during an audit.

© thatrebeccarae, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in skills/github-readme of thatrebeccarae/claude-marketing.

  • SKILL.md
  • EXAMPLES.md
  • LICENSE
  • REFERENCE.md

Open the folder on GitHubat commit a8a63ec

Compare with similar skills

GitHub Readme next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

GitHub Readme compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
GitHub Readme this skillthatrebeccarae/claude-marketing162—~2.9kAutomated safety check: PassMIT
Docs Seekereinverne/dotfiles1211 repos~1.4kAutomated safety check: PassGPL-3.0
GitHubkostja94/marketing-skills1k—~4.5kAutomated safety check: PassMIT
Liveagent Code ReviewStack-Cairn/LiveAgent2.2k—~2kAutomated safety check: PassMIT
Kanvibe Release Deployrookedsysc/kanvibe143—~12kAutomated safety check: NotesAGPL-3.0
Release TS SDKaptos-labs/aptos-ts-sdk116—~864Automated safety check: PassCustom licence

Similar skills

  • Docs Seeker

    einverne/dotfiles

    Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration.

    121 GitHub starsUsed in 1 repo~1.4k tokens
    Marketing & SEOAuto-check passed
  • GitHub

    kostja94/marketing-skills

    When the user wants to use GitHub for SEO, parasite SEO, GEO, open source marketing, README optimization, or curated Awesome lists.

    1k GitHub stars~4.5k tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Liveagent Code Review

    Stack-Cairn/LiveAgent

    Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation.

    2.2k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Kanvibe Release Deploy

    rookedsysc/kanvibe

    A skill your agent uses whenever releasing or deploying KanVibe desktop from a clean, up-to-date dev checkout: ask only for the target version and release-note approval, then let the AI update…

    143 GitHub stars~12k tokensUpdated today
    DevelopmentAuto-check: notes
  • Release TS SDK

    aptos-labs/aptos-ts-sdk

    A skill your agent uses when cutting a release of @aptos-labs/ts-sdk or @aptos-labs/confidential-asset.

    116 GitHub stars~864 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • GitHub PR Description

    lucasvieirasilva/nx-plugins

    Generates a GitHub Pull Request description for this repository from the commits on the current branch, filling in .github/PULLREQUESTTEMPLATE.md (Current Behavior / Expected Behavior / Related…

    153 GitHub stars~1.4k tokensUpdated 9 days ago
    DevelopmentAuto-check passed

More from thatrebeccarae/claude-marketing

All 55 skills in this repo
  • Google Analytics

    thatrebeccarae/claude-marketing

    Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements.

    162 GitHub starsUsed in 4 repos~1.3k tokens
    Auto-check: notes
  • Content Creator

    thatrebeccarae/claude-marketing

    Comprehensive content marketing toolkit with brand voice analysis, SEO optimization scripts, content frameworks, social media strategy, and content calendar planning.

    162 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Klaviyo Analyst

    thatrebeccarae/claude-marketing

    Klaviyo marketing operations and analyst expertise. An agent skill from thatrebeccarae/claude-marketing.

    162 GitHub stars~5k tokensUpdated 4 mo ago
    Auto-check: notes
  • Klaviyo Developer

    thatrebeccarae/claude-marketing

    Klaviyo API and developer integration expertise. An agent skill from thatrebeccarae/claude-marketing.

    162 GitHub stars~4.9k tokensUpdated 4 mo ago
    Auto-check: notes
  • Looker Studio

    thatrebeccarae/claude-marketing

    Looker Studio (formerly Google Data Studio) expertise. An agent skill from thatrebeccarae/claude-marketing.

    162 GitHub stars~3.6k tokensUpdated 4 mo ago
    Auto-check: notes
  • Shopify

    thatrebeccarae/claude-marketing

    Shopify e-commerce platform marketing expertise. An agent skill from thatrebeccarae/claude-marketing.

    162 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check: notes

Questions about GitHub Readme

What does GitHub Readme do?

Generate, audit, or update GitHub READMEs with project-type-aware structure, voice calibration, and SEO/AEO discoverability guidance. GitHub Readme is an agent skill from thatrebeccarae/claude-marketing. Generate, audit, or update GitHub READMEs with project-type-aware structure, voice calibration, and SEO/AEO discoverability guidance.

When should I use GitHub Readme?

GitHub Readme fits situations like: tasks that involve Technical documentation; tasks that involve AI search optimization; tasks that involve Performance reviews.

How do I install GitHub Readme in Claude Code?

Run `npx skills add thatrebeccarae/claude-marketing --skill github-readme -a claude-code`. Or copy the skill folder (skills/github-readme in thatrebeccarae/claude-marketing) into .claude/skills/github-readme in your project. Claude Code loads it when a task matches its description.

How do I install GitHub Readme in Codex?

Run `npx skills add thatrebeccarae/claude-marketing --skill github-readme -a codex`. Or copy the skill folder (skills/github-readme in thatrebeccarae/claude-marketing) into .agents/skills/github-readme in your project. Codex loads it when a task matches its description.

Can I use GitHub Readme in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add thatrebeccarae/claude-marketing --skill github-readme -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/github-readme, .gemini/skills/github-readme, .github/skills/github-readme and .opencode/skills/github-readme in your project.

What does GitHub Readme need to run?

Going by SKILL.md and its folder, GitHub Readme needs the command-line tools its instructions call (git and gh). Our summary lists: Python 3; Node.js; Docker.

Does GitHub Readme access the network?

SKILL.md names 1 domain. In commands or code: img.shields.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is GitHub Readme safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does GitHub Readme use?

GitHub Readme is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does GitHub Readme use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to GitHub Readme?

Skills that share tags, products or a category with GitHub Readme: Docs Seeker (einverne/dotfiles, 121 stars), GitHub (kostja94/marketing-skills, 1k stars), Liveagent Code Review (Stack-Cairn/LiveAgent, 2.2k stars) and Kanvibe Release Deploy (rookedsysc/kanvibe, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains GitHub Readme?

thatrebeccarae (a GitHub user) maintains it in thatrebeccarae/claude-marketing, which has 162 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on May 14, 2026.

Source: thatrebeccarae/claude-marketing on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.