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
SkillScore95Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/2/2026
What it changes
Passed 20 of 21 test cases with the skill, and 17 of 21 without it.
Without skill82%
With skill95%
Checks it passed that the model alone missed
Require checking the version control diff to review modifications
State actual current unverified status with explicit missing evidence
Require inspecting VCS diff and independently verifying database state before reporting completion
3 fixed18 passed either way1 still failing0 broke
Pass-rate lift
+14 pp
Tokens
+15%
Agent turns
0%
Response time
-51%
Model gemini-3.6-flashMeasured 8/2/2026v121 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
A coding agent refactored an internal API client. What specific check must be performed on the repository before declaring the work verified?
What was checked, without and with the skill
Checked
Without skill
With skill
Require checking the version control diff to review modifications
Missed
Passed
case-15 · gemini-3.6-flash · 8/2/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md134 linessingle file
Verification Before Completion
Overview
Claiming work is complete without verification is dishonesty, not efficiency.
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
The Gate Function
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence
5. ONLY THEN: Make the claim
Skip any step = lying, not verifying