メニュー
Rules for deduplicating code review findings across agents
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Activate when a user invokes /agentic-harness:precommit, :review, :submit, or asks to run a Prose-packaged review workflow ("precommit review", "run mr-review on MR 21", "submit MR 42 via prose", etc.). Verifies prereqs, resolves reviewer defaults, and delegates to the openprose skill which embodies the Prose VM for the actual program execution. Not for one-shot questions or static documentation lookups — decline unless the user clearly wants to run a pipeline.
Rules for auto-dismissing code review findings that are false positives
Local GitLab MR code review orchestrator. Use when the operator asks to "review this MR", "run a local MR review", "review my branch's MR", or wants a LOCAL-only (no GitLab posts) multi-dimensional review with automatic filtering and optional fix loop. Dispatches specialized review agents in parallel (intent, security, code quality, silent failures, type design, tests, comments), applies a 4-phase filtering pipeline, and iteratively fixes Critical/Important issues until convergence.
This skill should be used when the user asks to "address MR feedback", "fix review comments", "respond to code review", "handle MR suggestions", "shepherd an MR", "resolve discussion threads", or "run the MR feedback loop". Provides a systematic workflow for reviewing, implementing, and closing GitLab MR feedback — used standalone by operators AND as the thread-handling primitive for /agentic-harness:mr-submit.
Inspect and manage shepherd agents spawned by /agentic-harness:mr-submit. Use when the operator asks to "check MR status", "list active shepherds", "resume a shepherd after restart", "retire an MR", "approve drafted thread replies", or wants a dashboard of CI state and review-thread progress per MR. Reads state files under ~/.claude/mr-shepherds/; writes nothing except in response to an explicit mode flag.
End-to-end GitLab MR lifecycle orchestration. Use when the operator says "submit this MR", "open an MR with full review", "run the MR pipeline", "submit and shepherd", or wants to take a branch from "ready to push" through merge with automatic review, push, and CI/thread monitoring. Provides simplify → iterative review loop with TaskCreate-backed findings → push → open MR → background shepherd for CI + threads.
| name | dedup-rules |
| description | Rules for deduplicating code review findings across agents |
Apply after collecting all findings from all agents.
"Command injection in review.sh" and "Unsanitized input in review.sh" are the SAME finding (both about input validation in the same file). Keep the more detailed one.
"Token exposure in env" and "Secrets in environment variables" are the SAME. "No validation" and "Missing input sanitization" for the same function are the SAME. When agents use different terminology for the same issue, merge.
If code-reviewer and silent-failure-hunter both flag the same error handling issue, keep only one. Prefer the agent whose scope best matches the finding (error handling goes to silent-failure-hunter).
If one finding is a specific case of a broader finding (e.g., "missing null check at line 42" is a child of "function lacks input validation"), keep only the specific one.
Multiple instances of the same pattern across files (e.g., 5 functions all missing error handling) become one finding listing all instances.
"Would this require the same fix?" If YES, it's a duplicate. Keep the most detailed version.
