Evidence before final
Skill lubochka/xiigen-general-skills/agent-skills/evidence-before-final
Open-source AI agent skills for safer Claude, Codex and Cursor coding workflows
npx -y skills add lubochka/xiigen-general-skills --skill evidence-before-finalAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Prevent claiming completion without proof. Use before final responses, handoffs, releases, or review closure.
SKILL.md
0.9 KB, as published. Nobody here has run it
Evidence Before Final
Purpose
Prevent claiming completion without proof.
When to Use
Use before final responses, handoffs, releases, or review closure.
Inputs
Commands from the target project profile, changed files, review notes, smoke tests, and generated reports.
Steps
- Identify claims that require proof.
- Run only relevant verification.
- Separate evidence from approval.
- Report unchecked risks plainly.
Gates
Every completion claim has evidence or is marked unverified.
Evidence
File checks, command outputs, review passes, smoke tests, or manual acceptance records.
Anti-Patterns
Using screenshots, commits, or reports as automatic approval.
Related
claim-verification, executor-cannot-self-finish