More screenshots
Works with the AI tools you already use
code documentation engineer
A code-first documentation engineer that audits and writes docs based on implementation, not assumptions.
Secure checkout via Stripe
See it in action
You say
Audit the current repository documentation against the implementation. Focus on the API endpoints and environment variables. List any contradictions or missing requirements.
Your agent does
Documentation Audit Summary:
- API: Stale. POST /v1/auth claims to return a JWT, but implementation returns a session cookie.
- Config: Missing. 4 environment variables in
config/loader.goare not in .env.example. - Action: Updated README.md and corrected API docstrings.
What you get
About this skill
The problem
Existing documentation is often stale, incomplete, or based on outdated assumptions. Developers waste time tracing code to verify if the README or API docs actually match the implementation.
What it does
- Analyzes project structure, entry points, and execution flows to establish a source-of-truth mental model.
- Audits existing READMEs and docstrings to identify contradictions, stale info, and missing sections.
- Generates API documentation by tracing routes through controllers and services to verify actual behavior.
- Maps database schemas, environment variables, and infrastructure config directly from source files.
- Produces documentation audit reports highlighting critical gaps and security-sensitive findings.
Why this beats prompting it yourself
Generic prompts often hallucinate features based on file names. This skill enforces a "code-first" rule, refusing to document any behavior that cannot be verified in the source, ensuring 100% accuracy.
Use cases
- Generating a comprehensive README for a legacy repository with zero documentation.
- Auditing a complex API to ensure the public docs match the actual validation rules and response codes.
- Onboarding new engineers by creating verified architecture diagrams and data flow maps.
- Identifying accidentally committed secrets or credentials in config files before deployment.
Known limitations
Will not document behavior that cannot be established from available evidence. Explicitly flags low-confidence findings rather than guessing.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Creator
2 skills on Agensi
A full-stack software engineer with 6+ years building enterprise-grade systems across EdTech, fintech, and public-sector domains. Specializes in React, Next.js, Node.js, TypeScript, PHP, and Rust, with hands-on experience integrating AI models, payment gateways, and government tax APIs into production systems used by real organizations across Southern Africa. "Curiosity is a catalyst for progress. Dare Mighty Things." - Dawood F.MK
Frequently Asked Questions
Popular in Code Review

Production Code Readiness Reviewer
A rigorous production-readiness auditor that identifies logic defects, security risks, and test gaps in code changes.

inline-comment
Best way to steer your agents, effortlessly.

agent skill security scanner
Audits agent skills and MCP manifests for prompt injection, data exfiltration, and over-permissioned access.
code-reviewer
Reviews your code for bugs, security vulnerabilities, logic errors, performance issues, and style violations. Organizes findings by severity and suggests fixes with code examples.