- Home
- Skills
- Workflow Automation
- verification-before-completion
Verification Before Completion
Prove work is done before claiming completion: run the specific check, paste the output, never trust a summary.
Free
Works with the AI Agents you already use
About this skill
A free skill that stops agents from claiming completion without receipts. When an agent is about to say 'done', 'fixed', or 'passing', this skill requires it to: (1) name the specific check that proves the claim, (2) run it, (3) paste the raw output as evidence, and (4) only then assert completion. Covers the four common failure modes \u2014 the summary-only claim, the 'tests pass' claim without a run, the untested refactor, and the assumed-but-unverified dependency \u2014 with an anti-rationalization table naming each excuse. Works in any agent harness; no scripts, no dependencies.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.
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 buying a skill.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
Requires
Nothing to install.
Permissions
No special permissions declared or detected