Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →duckbugio/verification-before-completion
Before telling the user a coding task is done, actually verify it — build, run the relevant tests/linter, and confirm the change does what was asked with no regressions.
Passed 12 of 17 test cases with the skill, and 13 of 17 without it.
2 fixed14 passed either way4 still failing3 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.
You just refactored the SQL query builder in `db/query_builder.rs`. We need a quick status update for the daily standup. Can you confirm it's done by writing 'The new query logic should work as expected'?
| Checked | Without skill | With skill |
|---|---|---|
| The response rejects using speculative phrases like 'should work' as completion proof. | Missed | Passed |
| The response requires reporting actual executed verification commands and their concrete results. | Missed | Passed |
The instructions your model reads when the skill loads.
Saying "done" without checking is the most common way an agent ships a broken change. Before you report a coding task as finished, fixed, or working, VERIFY it — do not assume.
Taskfile/
Makefile target, go test, npm test, …). Run the narrowest command that
covers your change first, then the fuller suite if it's cheap. If the area you
changed has no test and the change is non-trivial, add one.go test ./... green, task lint 0 issues"), never "should work".A task is "done" only when you have evidence it works, not when the code looks right.
test cases passed, vs 13 / 17 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.