New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Readme Generation

by SpecterOps in SpecterOps/skills

Generate a professional README.md for a project. An agent skill from SpecterOps/skills.

Apache-2.0Auto-check passedDevelopment

Install Readme Generation

skills CLI
$ npx skills add SpecterOps/skills --skill readme-generation -a claude-code

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

GitHub CLI
$ gh skill install SpecterOps/skills readme-generation --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/SpecterOps/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/workflows-development/skills/readme-generation .claude/skills/readme-generation && 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
readme-generation
GitHub stars
702
Token cost
~1.7k tokens
SKILL.md length
396 words
Files
4 (incl. assets)
Skills in repo
38
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate a professional README.md for a project. An agent skill from SpecterOps/skills.

  • Works in 4 steps: Acquire the codebase → Deep scan the project → Determine project type and style → …
  • A project needs a README
  • SKILL.md covers Steps, Usage, Output Formats and Requirements, plus 16 more sections
  • Calls git and gh

What it does

Readme Generation is an agent skill from SpecterOps/skills. Generate a professional README.md for a project. Works on local codebases and remote GitHub repos. Use when a project needs a README, when an existing README is outdated, or when documenting someone else's tool.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including assets (for example `agents/openai.yaml`).

It sits in Development, covering Technical documentation. It works with GitHub and Git. The repository describes itself as: A marketplace for LLM skills. The licence is Apache-2.0.

When your agent uses it

  • A project needs a README
  • An existing README is outdated
  • Documenting someone elses tool

Example prompts

  • “/readme-generation”

Requirements

  • Python 3
  • Node.js
  • Docker

Workflow steps

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

  1. Acquire the codebase
  2. Deep scan the project
  3. Determine project type and style
  4. Generate README using the appropriate template

What it can do on your machine

Read from SKILL.md and the folder at commit e655f93. 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

    No URLs in SKILL.md. Its commands use git and gh, which can reach the network depending on how they are called.

    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

Readme Generation loads about 1.7k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 396 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 SpecterOps/skills at commit e655f93, republished under its Apache-2.0 licence (© SpecterOps). 396 words, ~1,682 tokens.

Download SKILL.mdSave it as .claude/skills/readme-generation/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
readme-generation
description
Generate a professional README.md for a project. Works on local codebases and remote GitHub repos. Use when a project needs a README, when an existing README is outdated, or when documenting someone else's tool.
metadata.author
GhostWorks

README Generator

Analyze a codebase and produce a complete, professional README.md.

Parse the user's input to determine:

  • Target: a local path, a remote GitHub repo (e.g., fortra/impacket), or current directory (default)
  • Style: security-tool, library, cli, webapp, minimal, or auto-detect (default)
  • Update mode: if the user says "update" or the project already has a README, preserve custom sections

Common patterns:

  • $readme-generation → generate for current directory, auto-detect style
  • $readme-generation ~/projects/mytool → generate for local path
  • $readme-generation fortra/impacket → clone and generate for remote repo
  • $readme-generation --style security-tool → force a specific style
  • $readme-generation --update → update existing README, keeping custom sections

Steps

1. Acquire the codebase
  • If a remote repo is given: gh repo clone owner/repo /tmp/readme-target and work from there
  • If a local path is given: use that directory
  • Otherwise: use current working directory
2. Deep scan the project

Read and analyze these files (skip any that don't exist):

Project metadata:

  • pyproject.toml, setup.py, setup.cfg — Python project info, dependencies, entry points
  • Cargo.toml — Rust project info
  • go.mod — Go module info
  • package.json — Node.js project info
  • Makefile, Justfile — Build commands
  • Dockerfile, docker-compose.yml — Container setup
  • .github/workflows/ — CI/CD configuration

Source code (sample, don't read everything):

  • Entry points: main.py, cli.py, main.go, main.rs, src/main.*, cmd/
  • Top-level source files for imports and structure
  • CLI argument definitions (argparse, typer, cobra, clap)
  • Config file examples

Existing docs:

  • Current README.md (if updating)
  • CONTRIBUTING.md, CHANGELOG.md, LICENSE
  • docs/ directory contents

Git context:

  • git log --oneline -30 — recent activity and feature descriptions
  • git tag --sort=-v:refname | head -5 — version history
  • git remote -v — origin URL
Show full SKILL.md (152 more words)Show less
3. Determine project type and style

Auto-detect from user input or infer:

SignalType
nmap/scanning/enum imports, --target flagssecurity-tool
Library with no CLI, published to PyPI/crateslibrary
CLI with subcommands, --help outputcli
Web framework (Flask, FastAPI, Express, Next.js)webapp
Few files, single purposeminimal
4. Generate README using the appropriate template
Security Tool Template
markdown
# [Name]

[One-line description of what it does and why you'd use it]

## Features

- [Key capability 1]
- [Key capability 2]
- [Key capability 3]

## Installation

[Package manager install or build from source — include both if applicable]

## Quick Start

```bash
[Single command showing the most common usage]

Usage

[Full --help output or manual command reference]
Examples
bash
# [Description of scenario 1]
[command]

# [Description of scenario 2]
[command]

# [Description of scenario 3]
[command]

Output Formats

[If the tool supports multiple output formats, show examples of each]

Requirements

  • [Runtime dependencies]
  • [System requirements]
  • [Required access/permissions]

Building from Source

bash
[Build steps]

License

[License type and link]


#### Library Template
```markdown
# [Name]

[One-line description]

## Installation

```bash
[pip install / cargo add / go get command]

Quick Start

python
[Minimal working example — 5-10 lines]

API Reference

[Module/Class Name]
function_name(params) -> return_type

[Description and example]

Configuration

[Config options if applicable]

Contributing

[How to contribute, run tests, submit PRs]

License

[License]


#### CLI Template
```markdown
# [Name]

[One-line description]

## Installation

```bash
[Install command]

Usage

[Command syntax overview]
Commands
command-name

[Description, flags, example]

Configuration

[Config file location and format if applicable]

Examples

[2-3 real-world usage scenarios]

License

[License]


#### Webapp Template
```markdown
# [Name]

[One-line description]

## Tech Stack

- [Frontend framework]
- [Backend framework]
- [Database]
- [Deployment]

## Getting Started

### Prerequisites

[Required software and versions]

### Setup

```bash
[Clone, install deps, configure, run — step by step]
Environment Variables
VariableDescriptionDefault
VAR_NAMEWhat it doesdefault

Development

bash
[Dev server, test, lint commands]

Deployment

[How to deploy]

License

[License]


#### Minimal Template
```markdown
# [Name]

[One-line description]

## Usage

```bash
[Primary usage command]

Install

bash
[Install steps]

License

[License]


### 5. Writing guidelines

- **First line matters most** — the description after `# Name` should explain what the tool does AND why someone would use it, in one sentence
- **Show, don't tell** — real command examples over descriptions of what's possible
- **Copy-pasteable** — every code block should work if pasted into a terminal
- **No filler** — skip badges, excessive formatting, or sections with no content
- **Accurate dependencies** — only list what's actually required, pulled from the project files
- **Version-aware** — if the project has tags, reference the latest version in install commands

### 6. Update mode

When updating an existing README (user said "update" or `--update`):

1. Read the existing README fully
2. Identify **custom sections** — any section not in the standard template (acknowledgments, special notes, contributor lists, etc.)
3. Regenerate the standard sections with current project data
4. **Preserve custom sections in their original position** — do not delete or rewrite them
5. If a standard section has user-added content beyond what the template provides (e.g., extra examples), keep the user additions and only update the generated parts
6. Show a diff summary of what changed before writing

### 7. Output

- Write the README to the project directory
- If working on a remote repo in `/tmp/`, also copy the output to the current directory as `README-[project-name].md`
- Report the file path and a brief summary of what was generated

© SpecterOps, Apache-2.0. 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 (assets) in plugins/workflows-development/skills/readme-generation of SpecterOps/skills.

  • SKILL.md
  • agents/openai.yaml
  • assets/icon.png
  • assets/icon.svg

Open the folder on GitHubat commit e655f93

Compare with similar skills

Readme Generation 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.

Readme Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Readme Generation this skillSpecterOps/skills702—~1.7kAutomated safety check: PassApache-2.0
Releaseemanuelcasco/pi-mono-extensions106—~2.3kAutomated safety check: PassMIT
Prepare PR FilesQwenLM/qwen-code28k—~538Automated safety check: PassApache-2.0
GitHub Code ReviewRedWoodOG/Hermes-Desktop1775 repos~3.4kAutomated safety check: NotesMIT
GitHub Repojdevalk/skills104—~1.5kAutomated safety check: PassMIT
GitHub Release Assistantaiskillstore/marketplace4301 repos~477Automated safety check: PassNone

Similar skills

  • Release

    emanuelcasco/pi-mono-extensions

    Release a new version of pi-extensions: bump individual package versions (independent mode), update CHANGELOGs and READMEs, create per-package git tags, publish a GitHub release, and publish…

    106 GitHub stars~2.3k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Prepare PR Files

    QwenLM/qwen-code

    Writes a PR title file and a template-filled PR body file from the current branch diff, without pushing, commenting or creating the pull request.

    28k GitHub stars~538 tokensUpdated today
    DevelopmentAuto-check passed

  • GitHub Code Review

    RedWoodOG/Hermes-Desktop

    Review code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review.

    177 GitHub starsUsed in 5 repos~3.4k tokens
    DevelopmentAuto-check: notes

  • GitHub Repo

    jdevalk/skills

    Audits and improves GitHub repository quality — README structure, community health files, .github directory setup, issue/PR templates, metadata, releases, and branch hygiene.

    104 GitHub stars~1.5k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • GitHub Release Assistant

    aiskillstore/marketplace

    Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push.

    430 GitHub starsUsed in 1 repo~477 tokens
    DevelopmentAuto-check passed

  • Release

    oliver-kriska/claude-elixir-phoenix

    CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release.

    565 GitHub stars~1.7k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

More from SpecterOps/skills

All 38 skills in this repo

  • Codex Activity Report

    SpecterOps/skills

    Generate a normalized UTC timeline and evidence-based narrative from Codex activity artifacts.

    702 GitHub stars~805 tokensUpdated 14 days ago
    Auto-check passed

  • Com Proxy Triage

    SpecterOps/skills

    A skill your agent uses when the user wants to triage Windows COM proxy/hijack candidates by capturing HKCU\Software\Classes\CLSID\{...}\InProcServer32 NAME NOT FOUND lookups for a process, mapping…

    702 GitHub stars~1.5k tokensUpdated 14 days ago
    Auto-check passed

  • Cwe Code Review

    SpecterOps/skills

    Perform CWE-grounded security code reviews and precise weakness mapping using a locally derived MITRE CWE corpus, relationship graphs, mapping notes, detection methods, mitigations, and schema…

    702 GitHub stars~2.4k tokensUpdated 14 days ago
    Auto-check passed

  • Ghostwriter Oplog

    SpecterOps/skills

    A skill your agent uses for Ghostwriter operation log entries from Codex, including config guidance, quick notes, evidence-backed entries, and guided oplog capture through the Ghostwriter MCP tools.

    702 GitHub stars~665 tokensUpdated 14 days ago
    Auto-check passed

  • Nmap Parse

    SpecterOps/skills

    Parse nmap scan output and generate actionable recon notes. An agent skill from SpecterOps/skills.

    702 GitHub stars~738 tokensUpdated 14 days ago
    Auto-check passed

  • Osint Recon

    SpecterOps/skills

    Perform OSINT and external reconnaissance for approved targets.

    702 GitHub stars~813 tokensUpdated 14 days ago
    Auto-check passed

Works with

Categories

Questions about Readme Generation

What does Readme Generation do?

Generate a professional README.md for a project. An agent skill from SpecterOps/skills. Readme Generation is an agent skill from SpecterOps/skills.md for a project.

When should I use Readme Generation?

Readme Generation fits situations like: A project needs a README; an existing README is outdated; documenting someone elses tool.

How do I install Readme Generation in Claude Code?

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

How do I install Readme Generation in Codex?

Run `npx skills add SpecterOps/skills --skill readme-generation -a codex`. Or copy the skill folder (plugins/workflows-development/skills/readme-generation in SpecterOps/skills) into .agents/skills/readme-generation in your project. Codex loads it when a task matches its description.

Can I use Readme Generation 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 SpecterOps/skills --skill readme-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/readme-generation, .gemini/skills/readme-generation, .github/skills/readme-generation and .opencode/skills/readme-generation in your project.

What does Readme Generation need to run?

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

Does Readme Generation access the network?

SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Readme Generation 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 Readme Generation use?

Readme Generation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Readme Generation use?

About 1.7k tokens (SKILL.md is roughly 6.7k 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 Readme Generation?

Skills that share tags, products or a category with Readme Generation: Release (emanuelcasco/pi-mono-extensions, 106 stars), Prepare PR Files (QwenLM/qwen-code, 28k stars), GitHub Code Review (RedWoodOG/Hermes-Desktop, 177 stars) and GitHub Repo (jdevalk/skills, 104 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Readme Generation?

SpecterOps (a GitHub organization) maintains it in SpecterOps/skills, which has 702 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on September 23, 2026.

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