Waits for a PR's checks and reviews to finish, then reports the unresolved review threads, the failing checks and the gaps in the PR description. Use when the user asks to check a PR, whether a PR is ready, or what the Greptile review found.
Builds a change end to end, from the issue to a reviewed draft PR. Implement, review, hunt invariants, QA in real projects, open the PR, act on the bot reviews, then hand over to a human.
Gets a blind review of a diff or a PR from a model of another provider (Claude, GPT, Gemini), then checks and compares its findings. Use when the user asks for a second opinion, an adversarial review, or a review by another model.
Triage and resolve GitHub PR review comments one by one, interactively for humans and without asking for review bots. Use when the user asks to handle, address, respond to, or resolve PR review comments, or mentions reviewer feedback on a pull request.
Tests a change the way a user meets it, in real projects or the real tool, and compares the result on the base and on this head. Use when the user asks for real-world QA, to try a change in real projects, or to check that it works outside the tests.
Reviews the changes since a fixed point (commit, branch or merge-base) on two axes, in parallel subagents. Standards: does the code follow this repo's guidelines? Spec: does it do what the issue asked? Use when the user asks to review a branch, a PR or work…
Adversarial hunt for broken invariants in the changes since a fixed point. A subagent writes inputs that try to break each property the design promises, and a finding counts only with a test that fails on this head. Use when the user asks for an invariants…
Creates a pull request following Storybook conventions. Use when creating PRs, opening pull requests, or submitting changes for review.