How do I install the Github Pr Finding Triage skill?

Run npx skillmds@latest add bnema/github-pr-finding-triage in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Github Pr Finding Triage safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Github Pr Finding Triage?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Github Pr Finding Triage free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Github Pr Finding Triage?

bnema (@bnema) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Github Pr Finding Triage by bnema — Agent Skill

Name: Github Pr Finding Triage
Author: bnema

Github Pr Finding Triage

Use when turning the github-pr-review-comments JSONL index, including CodeRabbit PR review comments captured there, into an action queue with must-fix, verify-first, duplicate, informational, and human-decision buckets.

bnema aab549a 2.4 KB Updated Sep 17, 2026

File contents

GitHub PR Finding Triage

Use after github-pr-review-comments has produced a commentIndexJsonl file.

This is classification of reviewer claims, not proof that the claims are valid. Verify code before changing behavior.

Do not downgrade refactoring, cleanup, or maintainability findings merely because they are inconvenient or behavior still works; apply code-review-release/subskills/thermo-nuclear-code-quality-review/SKILL.md before dismissing them.

Command

# Build step (one-time or when tools change):
tsc --project $HOME/.agents/skills/github/tools/tsconfig.json

# Then run:
node $HOME/.agents/skills/github/tools/dist/pr-finding-triage.js --index /tmp/...comments.jsonl --repo OWNER/REPO --pr PR_NUMBER

Outputs:

JSON summary on stdout
private Markdown report in /tmp
private full JSON report in /tmp

Recommended workflow

Run pr-review-comments and confirm it is complete (ok: true, no pagination gaps).
Run this triage tool on the JSONL index.
Start with must_fix, then verify_first, then needs_human_decision.
Do not skip probably_duplicate without checking duplicateOfId and context.
Feed the triage JSON into pr-review-verification before implementing fixes.

Caveats

The classifier is heuristic. It prioritizes actionability and safety over cleverness. A must_fix means “reviewer appears to claim this is important,” not “the code is definitely wrong.”

---name: github-pr-finding-triagedescription: Use when turning the github-pr-review-comments JSONL index, including CodeRabbit PR review comments captured there, into an action queue with must-fix, verify-first, duplicate, informational, and human-decision buckets.---# GitHub PR Finding TriageUse after `github-pr-review-comments` has produced a `commentIndexJsonl` file.This is **classification of reviewer claims**, not proof that the claims are valid. Verify code before changing behavior.Do not downgrade refactoring, cleanup, or maintainability findings merely because they are inconvenient or behavior still works; apply `code-review-release/subskills/thermo-nuclear-code-quality-review/SKILL.md` before dismissing them.## Command```bash# Build step (one-time or when tools change):tsc --project $HOME/.agents/skills/github/tools/tsconfig.json# Then run:node $HOME/.agents/skills/github/tools/dist/pr-finding-triage.js --index /tmp/...comments.jsonl --repo OWNER/REPO --pr PR_NUMBER```Outputs:- JSON summary on stdout- private Markdown report in `/tmp`- private full JSON report in `/tmp`## Categories- `must_fix`: reviewer text claims critical/major/security/failing/broken behavior.- `verify_first`: inline or uncertain findings that need local code verification before action.- `probably_duplicate`: same normalized path/line/severity/body preview as an earlier finding.- `informational`: nitpick/trivial/info/style-only comments. Not for structural maintainability findings unless verified against the thermo-nuclear quality bar.- `needs_human_decision`: API/product/UX/tradeoff or low-confidence comments.Each finding includes:- `derivedSeverity`- `confidence`- `classificationBasis`- `rationale`- original GitHub node ID, body, URL, path/line metadata## Recommended workflow1. Run `pr-review-comments` and confirm it is complete (`ok: true`, no pagination gaps).2. Run this triage tool on the JSONL index.3. Start with `must_fix`, then `verify_first`, then `needs_human_decision`.4. Do not skip `probably_duplicate` without checking `duplicateOfId` and context.5. Feed the triage JSON into `pr-review-verification` before implementing fixes.## CaveatsThe classifier is heuristic. It prioritizes actionability and safety over cleverness. A `must_fix` means “reviewer appears to claim this is important,” not “the code is definitely wrong.”

Frequently asked questions