farhanhidayatulhaq-max/GAMUKIS / .agents/skills/teamwork-review
teamwork-review
VerifiedUse for final review or integration of one or more agents' outputs, validating combined diffs against PRD requirements, contracts, auth and permissions, and regressions, then reporting an APPROVE or REQUEST_CHANGES verdict.
Teamwork Review
- Gather context: task PRD/brief,
DISPATCH.md, all relatedhandoff.mdfiles, and the combined diff (not per-agent diffs). - Verify against active repository paths. Do not review copies in scratch or temporary directories; record any discrepancies between such copies and active files.
- Verify that:
- Every PRD requirement is satisfied, backed by
path:lineevidence or verification results. - Cross-service contracts have not changed without an Architect decision; legacy routes and response keys remain intact.
- Auth and permissions: administrative actions route through
authenticateAny+requirePermission; validation occurs on the server; teachers are not elevated to admin privileges. - Project invariants in the
gamukis-prd-guardskill are strictly respected. - No modifications from other agents were overwritten, no credentials were leaked, and no files outside dispatch boundaries were touched.
- Every PRD requirement is satisfied, backed by
- Execute only checks permitted by the task. Mark unexecuted checks as "not executed"; never infer that unrun tests passed.
- Treat agent claims ("tests passing", "complete") as unverified findings until corroborated with source evidence.
- Report in the reviewer's
handoff.mdadhering to this structure:- Verdict:
APPROVEorREQUEST_CHANGES - Blockers (each item:
path:line, issue description, expected remediation) - Non-blockers
- Verification: executed / not executed
- Constraints: aspects requiring live services (MySQL, Firebase, Midtrans) or active authenticated sessions
- Verdict:
- The lead updates
teamwork/INDEX.mdfollowing the verdict. "Done" reported by an individual agent does not indicate completed integration.
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: 471k | 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 |