← ClaudeAtlas

review-replylisted

Unified PR review triage — fetch, normalize, and batch-action bot comments
mmnto-ai/totem · ★ 13 · Code & Development · score 73
Install: claude install-skill mmnto-ai/totem
<!-- totem:skill-start --> Triage PR review comments from all bots for PR $ARGUMENTS. ## Phase 1: Fetch & Categorize (Deterministic) Run the triage command to fetch, normalize, deduplicate, and categorize all bot comments: ```bash pnpm totem triage-pr $ARGUMENTS ``` This outputs a categorized inbox grouped by blast radius (Security → Architecture → Convention → Nits) with cross-bot deduplication already applied. The heavy lifting is done in TypeScript — no LLM math needed. **STOP HERE.** Present the output to the user and wait for them to specify actions. Do NOT proceed to Phase 2 until the user replies. ## Phase 2: Execute Actions (Bulk Support) The user may type individual IDs (e.g., `fix 4, 11`) OR use bulk actions: - `fix all security` - `defer all nits` - `extract all architecture` ### `fix <numbers | category>` Mark items as will-fix. No API calls — just acknowledge. The user will make code changes next. ### `defer <numbers | category> [ticket]` Auto-reply on the PR acknowledging the deferral: - **CodeRabbit items:** Reply inline to each thread with "Tracked in #NNN" or "Deferred — not blocking for this PR." - **GCA items:** DO NOT reply inline. Batch ALL GCA responses into ONE issue comment: `@gemini-code-assist` followed by a numbered list addressing each finding. Use `gh pr comment $ARGUMENTS --body-file -` and pipe the comment body via stdin. - **SARIF items:** No reply needed (our own tool). ### `nit <numbers | category>` Same as defer but reply tex