More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    README & Docs Writer: Docs That Actually Work

    1

    Writes README, ARCHITECTURE and CONTRIBUTING from your real code, checking every command before documenting it.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    README & Docs Writer: Docs That Actually Work

    README & Docs Writer: Docs That Actually Work

    Example session with this skill installed

    Write a README for this repo and make sure the install steps work.

    • Read your context and instructions
    • Compiled the readme & docs

    Verified: npm install (OK), npm test (OK, 31 passed). Unverified: docker compose up (Docker not available here) - flagged in the README.

    TaskPilot

    A command-line task tracker that syncs to a local JSON file.

    Quick start

    npm install
    npm start -- add "Write docs"
    Then run npm start -- list: you should see 1 open task.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Documentation your users can trust, because every command was checked. This skill reads your project, runs (or traces) each install, run and test command, and only then writes the docs. No invented features, no copy-paste commands that fail.

    What you get

    • A README with a 20-second value statement, a copy-pasteable quick start, real usage examples, a configuration table and project structure
    • ARCHITECTURE.md: modules, data flow, key decisions and why, with a Mermaid diagram when it helps
    • CONTRIBUTING.md based on the conventions your repository really uses (branches, commits, checks, review)
    • Commands marked VERIFIED or UNVERIFIED so you know exactly what to double-check
    • A list of what only you can supply (screenshots, contact, badges)

    Rules it follows: short active sentences, no marketing filler, badges only for things that exist, screenshots never invented, secrets and internal URLs never copied. If your README is already good, it improves it and tells you what changed.

    Great before open-sourcing a project, handing it over, or applying for jobs with a portfolio repo.

    En español: escribe README, ARCHITECTURE y CONTRIBUTING verificados. Escribe en el idioma que pidas.

    Only edits documentation files. Cannot create real screenshots or demo GIFs (it leaves flagged placeholders). Commands that need unavailable services are marked UNVERIFIED instead of guessed.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    Permissions

    No special permissions declared or detected

    Listed6 days ago

    What's inside

    Frequently Asked Questions

    No. It only documents what it finds in the code and flags anything unverified.

    Yes. It follows the language you ask for, or the language of the existing README.

    It improves good content instead of replacing it and tells you what changed.

    Only for things that exist, such as a real CI workflow or license file.

    New in Productivity