Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/agent-cross-review
Structured cross-review protocol between specialized agents. Ensures scope alignment, priority calibration, and domain-aware feedback.
Passed 22 of 22 test cases with the skill, and 14 of 22 without it.
and 5 more in the full report
8 fixed14 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
An expert agent notices an optional code refactoring opportunity in `utils/string.py` that would slightly improve readability but does not affect correctness or maintainability. Which priority tier applies?
| Checked | Without skill | With skill |
|---|---|---|
| Categorizes minor readability improvements under MINOR priority tier | Missed | Passed |
The instructions your model reads when the skill loads.
Protocol for structured collaboration between specialized agents.
Review in domain, defer on scope.
Each agent excels in their specialty. Cross-review catches blind spots without overstepping boundaries.
Before reviewing, identify:
## Cross-Review Context
| Item | Value |
|------|-------|
| Reviewer | {agent-name} |
| Author | {agent-name} |
| Artifact | {file or output} |
| Review Type | Technical / Structural / Integration |
| Reviewer Type | Review Focus | Defer On |
|---|
test cases passed, vs 14 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.