From gh-toolkit
Use before tagging a release or merging important work, when the user wants a thorough, multi-agent, adversarial review that won't rubber-stamp the code. Triggers on "adversarial review", "pre-release review", "review before tagging", "multi-agent review", "red-team this", "tear this apart", "find every bug before we ship", "verify findings", "review with multiple reviewers", "is this really ready to release". Runs N reviewers across distinct dimensions, then adversarially verifies each finding before acting — fixing real issues with regression tests, recording declined findings with reasons. Run it as the gate before `v1.0.0`.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gh-toolkit:gh-adversarial-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A pre-release gate that finds real problems and refuses to act on fake ones. The defining move:
A pre-release gate that finds real problems and refuses to act on fake ones. The defining move: every finding is adversarially verified before it's fixed, and every fix gets a regression test. No finding is trusted just because a reviewer is confident.
Before tagging a release (the v1.0.0 gate from gh-repo-mission), before merging a large branch,
or whenever "looks fine" isn't good enough.
Spawn several independent reviewers, each owning a distinct dimension so coverage doesn't collapse into one lens. Typical dimensions:
Each reviewer returns findings as {title, location, severity, why-it's-a-bug, repro}.
For every finding, run an independent check whose default is to refute it. A finding survives only if it reproduces. Concretely:
For high-stakes findings, use multiple verifiers with different lenses (does-it-reproduce, security-impact, is-it-intended) and require a majority to confirm.
For each confirmed finding:
For every finding you do not fix (didn't reproduce, intended behavior, out of scope, accepted risk), write a one-line decline with the reason. Declines are part of the record — they show the finding was considered, not missed.
A short report:
READY TO TAG only if no confirmed-unfixed findings remain; otherwise BLOCKED
with the blockers listed.v1.0.0: more reviewers, 3+ independent verifiers per finding, and a final
completeness critic asking "what dimension didn't we review, what claim went unverified?".gh-repo-mission bakes into every mission.gh-publish only proceeds once the verdict is
READY TO TAG.npx claudepluginhub aymandakir-gh/gh-claude-toolkit --plugin gh-toolkitCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.