Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →gotalab/kiro-review
Review a task implementation against approved specs, task boundaries, and verification evidence. Use after an implementer finishes a task, after remediation, or before accepting a task as complete.
Passed 20 of 21 test cases with the skill, and 16 of 21 without it.
and 4 more in the full report
4 fixed17 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need a re-review of task TASK-209 ('Parse incoming webhooks') following the recent remediation work. The task text and implementer report are attached, referencing requirements section 1.2 and design section 7.0 with boundary `src/webhooks/parser.ts`. Format your output to state the final decision, task identifier, mechanical test and check results, findings categorized by severity, remediation tasks if rejected, and a single-sentence summary.
| Checked | Without skill | With skill |
|---|---|---|
| Formats the decision output with the heading ## Review Verdict. | Missed | Passed |
| Categorizes findings with Critical, Important, Suggestion, or FYI severity levels. | Missed | Passed |
| Evaluates mechanical checks including boundary audit and static checks. | Passed | Passed |
The instructions your model reads when the skill loads.
This skill performs task-local adversarial review. It verifies that the implementation is real, complete, bounded, aligned with approved requirements and design, and supported by mechanical verification evidence.
Boundary terminology continuity:
Boundary CandidatesBoundary Commitments_Boundary:_Boundary ViolationsREADY_FOR_REVIEW[x]Do not use this skill to invent missing requirements or silently reinterpret the spec.
Provide:
tasks.mdrequirements.md, design.md, optionally tasks.md)_Boundary:_ scope constraints## Implementation Notes entries when applicableReturn one of:
APPROVEDREJECTEDtest cases passed, vs 16 / 21 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.