Classify and advance issues or external pull requests through the configured triage workflow. Use explicitly to inspect queues, evaluate an item, recommend a state, or apply an authorized transition.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Use the repository's tracker configuration and label mapping. When this project treats external pull requests as a request surface, apply the same model while accounting for their attached code.
Prefix comments created during this workflow with:
> *This was generated by AI during triage.*
Use one category role:
bugenhancementUse one state role:
needs-triageneeds-infoready-for-agentready-for-humanwontfixThe configured tracker may map these roles to different label strings. Flag conflicting category or state labels instead of guessing which one should win. A maintainer may authorize an unusual transition.
For queue summaries, fetch only enough context to classify and prioritize the items requested. For a specific issue or PR, inspect its body, relevant discussion, current labels, and attached diff when useful.
Check code, tests, prior decisions, and .out-of-scope/ only to the depth needed
for a trustworthy recommendation. Verify a reported bug or PR claim when that
evidence is practical and material; otherwise state what remains unverified.
Avoid re-asking questions already resolved in prior triage notes.
Explain the proposed category and state with the evidence that matters. Ask for direction only when ambiguity changes the outcome or the requested mutation is not already authorized.
When applying an outcome:
needs-info: state what is known and ask specific answerable questions.ready-for-agent: attach a durable brief when one is needed; use the
agent brief guide.ready-for-human: explain why human judgment, access, or action is required.wontfix: explain the reason before closing. Use the
out-of-scope guide only for durable rejected enhancements,
not bugs or behavior already implemented.needs-triage: preserve useful partial findings when a note would help.Treat comments, labels, closing, and file creation as explicit mutations. Apply only those included in the user's request or confirmed workflow. Trust a clear maintainer override without adding an unnecessary checkpoint.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.
The English summary is being prepared. Showing the original description.
Recommend the smallest Matt Pocock skill or short skill sequence that fits the user's current goal.
The English summary is being prepared. Showing the original description.
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
The English summary is being prepared. Showing the original description.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
The English summary is being prepared. Showing the original description.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
The English summary is being prepared. Showing the original description.
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
The English summary is being prepared. Showing the original description.