- Home
- Skills
- Technical Documentation
- readme generator
More screenshots
Works with the AI Agents you already use
readme generator
Generate and audit evidence-grounded READMEs by inspecting repository source code and manifests.
Free
readme generator
Example session with this skill installed
Audit my current README.md against the repository files and generate a corrected version that only includes verified scripts and env vars.
- Read your context and instructions
- Compiled the readme generator
I have audited the repository and found 2 stale scripts in the README (build:prod and deploy) that are no longer in package.json. I also detected a missing DATABASE_URL environment variable required by src/db/client.ts that was not documented.
Updated README.md
Project Phoenix — Backend Service
A Node.js microservice for processing asynchronous telemetry data using Fastify and Redis.
Requirements
- Node.js v18.x or higher
- Redis v7.0+
- PostgreSQL v14+
Configuration
Create a .env file in the root directory. The following variables are required for the application to start:
| Variable | Source | Purpose |
|---|---|---|
DATABASE_URL | src/config/db.ts | PostgreSQL connection string |
REDIS_HOST | src/config/cache.ts | Redis server hostname |
API_KEY | src/middleware/auth.ts | Third-party service authentication |
Available Scripts
Based on the package.json manifest, you can run the following commands:
# Install dependencies
npm install
# Start development server with hot-reload
npm run dev
# Run unit tests via Vitest
npm run test
# Build the project for production
npm run build
Project Structure
src/api/: Fastify route definitions.src/db/: Prisma schema and client configuration.src/workers/: Background job processing logic.tests/: Integration and unit test suites.
License
MIT License - see the LICENSE file for details.
Next steps
- Review the newly added
DATABASE_URLsection to ensure the description matches your deployment environment. - Remove the deprecated
deploy.shscript if it is no longer needed. - Verify that the Redis version requirement matches your production cluster.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Writing READMEs manually leads to "documentation rot" where scripts, environment variables, and setup steps drift from the actual code. Developers often waste time troubleshooting outdated instructions or inventing generic sections that don't reflect the repository's reality.
What it does
- Performs a repository-wide inventory of manifests, lockfiles, and source trees to establish a source of truth.
- Maps every documented command to an actual script or entry point found in the codebase.
- Identifies project types and ecosystems automatically to generate relevant sections without generic filler.
- Detects and redacts sensitive credentials, tokens, and private keys during the documentation process.
- Audits existing READMEs to flag stale claims and unsupported environment variables against the current state of the repo.
Why this beats prompting it yourself
Most LLMs hallucinate "standard" setup commands like npm install or python main.py regardless of what is actually in your repo. This skill enforces a strict evidence hierarchy, ensuring every instruction is backed by a file, script, or config entry, preventing the creation of plausible-sounding but broken documentation.
Use cases
- Generating a comprehensive README for a new repository based on the initial scaffold.
- Auditing a legacy project to find and fix broken installation steps or missing environment variables.
- Documenting complex monorepos by mapping entry points and scripts across multiple packages.
- Standardizing documentation across a team by enforcing evidence-based reporting.
Cannot verify external API endpoint availability or third-party service status. Requires repository access to perform inventory.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
4 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 2 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected