traiage-review — Claude Code skill: what it does, how to install
Traiage-review prioritizes repository changes and pinpoints files that human reviewers must inspect first.
npx skills add NeoLabHQ/context-engineering-kit --skill traiage-review -a claude-codeWhat traiage-review does
The skill operates strictly as an orchestrator agent. It inspects repository state to pick the right review workflow: local working tree diffs, branch changes against origin/main or origin/master, or an isolated commit hash. It triggers four specialized sub-agents in parallel (change-story-agent, change-impact-agent, change-failure-agent, and change-expectation-agent) to score failure likelihood.
The final candidate list blends top picks from each agent with five random files selected by an internal Python sampling script. The orchestrator is restricted to read-only git operations and does not alter working tree files. If you run it on the clean default branch without local diffs, it terminates immediately.
What it helps with
- prioritize high-risk files across large git pull requests
- filter out routine edits during local diff inspection
- evaluate failure risk for a specific commit hash
- generate a balanced random sample of modified files for audit
Example prompts for the agent
- Prioritize files needing review in my local git changes using traiage-review
- Run traiage-review on this branch against origin/main
- Use traiage-review to inspect the latest commit
How to install traiage-review
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill traiage-review -a claude-code2Manually: put the files in place
~/.claude/skills/traiage-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/traiage-review/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill traiage-review -a codex2Manually: put the files in place
.agents/skills/traiage-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill traiage-review -a cursor2Manually: put the files in place
.cursor/skills/traiage-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NeoLabHQ/context-engineering-kit traiage-review2Manually: put the files in place
.github/skills/traiage-review/SKILL.md1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill traiage-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/traiage-reviewManually: put the files in place
.devin/skills/traiage-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill traiage-review -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about traiage-review
How to install traiage-review in Claude Code?
Run npx skills add NeoLabHQ/context-engineering-kit --skill traiage-review -a claude-code in your terminal. The skill is placed into ~/.claude/skills/traiage-review/SKILL.md.
What does traiage-review do?
It orchestrates four sub-agents to rank changed files and surface those most likely to break tests or fail review. The final output gives a focused file list so reviewers can skip routine diffs.
Can traiage-review modify repository files or git history?
No. The orchestrator is strictly prohibited from running mutating git commands or editing code, relying solely on read-only git calls and a Python sampling script.
