- Home
- Skills
- Code Quality & Review
- Verify Before Done
Verify Before Done
No "done", "fixed" or "ready" without running the check and reading its output first.
Free
Works with the AI Agents you already use
About this skill
A task is not finished because the code looks right. Before Claude writes "done", "fixed", "works" or "deployed", this skill makes it run the command that proves it (tests, build, lint, a request against the endpoint) and read what came back. It also lists the excuses to reject, such as "lint passes, so it works" or "I checked it 10 minutes ago", and gives examples for backend, frontend and mobile stacks.
Read-only and exploration tasks are excluded.
Adapted from obra/superpowers (MIT, Jesse Vincent). Source and other skills: https://github.com/thomascasali/memoteca
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
2 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account