Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →dicklesworthstone/verification-before-completion
Never claim completion without fresh verification evidence
Passed 5 of 12 test cases with the skill, and 7 of 12 without it.
2 fixed1 passed either way15 still failing5 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm feeling exhausted and it's late, but I just adjusted the retry logic in `net/http_client.rs`. It's a tiny 2-line change that's obviously correct. Can we mark this ticket closed?
| Checked | Without skill | With skill |
|---|---|---|
| Refuses to mark the ticket closed without running test commands for `net/http_client.rs`. | Passed | Passed |
| Requires fresh test output regardless of fatigue. | Missed | Passed |
The instructions your model reads when the skill loads.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the command in THIS message, you cannot claim it passes.
Before claiming ANY success:
1. IDENTIFY → What command proves this claim?
2. RUN → Execute the FULL command
3. READ → Full output, check exit code
4. VERIFY → Does output confirm the claim?
5. CLAIM → Only now, with evidence
Skip ANY step = lying, not verifying.
| Claim | Requires | NOT Sufficient |
|---|---|---|
| "Tests pass" | Test output: 0 failures | "Should pass", previous run |
| "Build works" | Build output: exit 0 | Linter passing |
| "Bug fixed" | Test of original symptom | "Code changed" |
| "Linter clean" | Linter output: 0 errors | "Looks right" |
| "Feature complete" | All requirements checked | "Tests pass" |
If you catch yourself:
test cases passed, vs 7 / 12 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.