Triage externally reported bugs and feature requests, suggest a fast human acknowledgment, investigate the evidence, and prepare a private recommendation for the maintainer. Use for contributor or user reports, not implementation or internal backlog grooming.
Review PRs from external contributors, understand their motivation, investigate deeply, and recommend a practical path to merge with minimal contributor back-and-forth. Use for external contribution reviews, not ordinary internal branch reviews.
Use when the user wants work packaged for review (e.g. "review packet", "/review-packet", "prepare this for review", "make it easy to review this PR set / design / research"). Builds a decision-first page that pairs every claim with the evidence for it.
Use when the user asks to take a task end-to-end autonomously (e.g. "autodev", "/autodev", "build this on autopilot"). Runs the full chain — plan → implement → review → PR → converge — stopping only at real decisions.
Use when the user asks how competitors, similar tools, or OSS projects handle a problem, or wants an evidence-backed implementation, product, UX, feature, positioning, or marketing comparison.
Use when the user asks for a cross-review by Claude (e.g. types "claude-review", "/claude-review", or "have Claude review this"). Invokes Claude Code headlessly to review the current branch/changes, prints Claude's findings verbatim, then triages them…
Use when the user asks to plan a task before coding (e.g. "plan-loop", "/plan-loop", "plan this out first"). Draft a detailed plan, cross-review it with Claude, triage skeptically, iterate, then gate for sign-off.
Use when the user wants the current code proactively reviewed and fixed (e.g. "review-loop", "/review-loop", "review what I have and fix it"). Self + cross-model review → triage → fix → update PR, loop until clean.