collectiveai-team/botica / skills/review/review-refute
review-refute
VerifiedReview role that challenges findings against the diff, reachable entry points, reproductions and existing checks. Records contrary evidence and validates deterministic duplicates. Use after the other review-<role> skills ran, or when review-panel reaches its last step.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.7 KB |
| agents/openai.yaml | config | 103 B |
| references/REVIEW.md | markdown | 1.2 KB |
| references/output.md | markdown | 2.9 KB |
references/REVIEW.md
View on GitHub---
role: refute
applies:
paths: []
tiers: [low, medium, high]
stages: [local, ci]
blocking: P1
max-findings: 50
covered: {}
---
## Check always
<!-- botica:covered -->
<!-- /botica:covered -->
- Each finding of `P0` and `P1` gets an attempt against the files of the target or of `HEAD` (a
command of `git` on the machine of the author, a read of the file in CI), not only a reading of
its text.
- A finding refuted as `pre-existing` names the commit of the target where its lines already were,
and says that no line of the diff changes what reaches them.
- A finding about something absent or removed (a missing criterion, a behaviour with no test, a
deleted test or check) is judged by whether the diff should have added it, never as
`pre-existing`.
- A finding that only a run of code could reproduce stays `confirmed`, and its `how_to_verify`
has a step that a person runs.
## Do not report
- New findings. This role refutes; it does not review the diff again.
## Evidence
Each refutation gives the command that the role ran or the file and line that disproves the
finding. `max-findings` is the number of findings that the role judges; `refute.json` keeps every
finding of the inputs.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |