Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ccplugins/caveats-and-status
Use when about to report any nontrivial task as complete — requires closing with a Caveats & status section stating what was verified, what was assumed, and what's unresolved.
Passed 7 of 15 test cases with the skill, and 3 of 15 without it.
and 5 more in the full report
6 fixed5 passed either way12 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Refactor thread safety logic in rust_queue/src/lib.rs. You ran 'cargo test' and all 12 concurrency tests passed. Conclude with a structured status breakdown.
| Checked | Without skill | With skill |
|---|---|---|
| The response places cargo test execution under verified. | Missed | Passed |
| The response places production stress testing under not covered. | Missed | Passed |
The instructions your model reads when the skill loads.
"Done" without a status check is a guess wearing a confident voice. This skill defines the closing format every nontrivial completed task uses, so what wasn't verified is always visible rather than buried in an upbeat summary.
Core principle: state what you checked, not just what you did.
Any response that reports a task as complete, fixed, or passing — code changes, file scaffolding,
investigations with a conclusion. Skip it for pure Q&A with no action taken, and for the quick
flow's trivial one-liners where the verification step itself already says everything needed (don't
pad a two-line change with a boilerplate section that adds nothing).
End the response with:
**Caveats & status**
- Verified: <what you actually ran/observed, with the result>
- Assumed: <anything taken on faith because it couldn't be checked here>
- Not covered: <what's explicitly out of scope or unverified>
Omit a line entirely if it's genuinely empty (e.g. "Assumed: none" is fine to state plainly, but don't stretch to fill a line that has nothing real to say).
test cases passed, vs 3 / 15 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.