Verification Before Completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Install this if you want stricter evidence-based completion reporting. Be aware that it may cause the agent to run tests, builds, linters, or similar verification commands before saying work is complete, so guide it when those commands are slow, expensive, or have side effects.

Type: OpenClaw Skill Name: verification-before-completion Version: 0.1.0 The skill bundle's primary purpose is to enforce a strict 'verification before completion' policy on the AI agent. The `SKILL.md` file contains detailed instructions and principles aimed at preventing the agent from making unverified claims of success, emphasizing evidence-based reporting. There is no evidence of malicious intent, data exfiltration, unauthorized command execution, persistence mechanisms, or prompt injection designed to subvert the agent for harmful purposes. Instead, the instructions promote rigorous self-verification and honesty, which are beneficial behaviors for an AI agent.