Install any skill in seconds. Free to start, no credit card required.
Get Started Free →An evidence gate that must pass before claiming any task is complete. Use this at the end of every coding task, right before saying "done", "fixed", "implemented", or "should work", and whenever tempted to assume code works without running it. Applies to features, bug fixes, refactors, config changes, and one-off scripts alike. If work is being handed back to a human, this gate comes first.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 106% | 0% |
| case-05 | ✓→✗ | ▼ Worse | 43% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 1% | 0% |
| case-02 | ✓→✓ | = Same ✓ | -11% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 44% | 0% |
"Should work" is the most expensive phrase in agentic coding. Every unverified claim converts the human's one review pass into a debugging session, and after two of those they stop trusting anything you say. The standard is simple: evidence or it did not happen.
Run every check that applies to the change. Actually run them; predicting their output is exactly the failure this skill exists to prevent.
git status and git diff show only intended changes. No stray files, no leftover debug code, no accidental formatting churn across files you never meant to touch.Then the task is not done. Go back to work; do not negotiate with the gate, do not present the failure buried in the middle of a success narrative, and do not disable the check that failed. A red gate reported honestly costs a little pride. A green lie costs the relationship.
Other measured skills in the registry, with their headline benchmark lift.