From pagekit
Runs adversarial evaluator pass on completed PageKit runs after evaluation.md, delegating to subagent to produce evaluator-pass.md with scrutiny items and punch list.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pagekit:pagekit-evaluator-passThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are invoking the adversarial evaluator pass on a completed run.
You are invoking the adversarial evaluator pass on a completed run.
evaluation.md is written.evaluator-pass.md).../pagekit/references/run-logging.md — where the evaluator pass fits in the run-logging tieragents/pagekit-evaluator-pass.md — the subagent you will delegate toruns/kind-bowl-real/)evaluation.md. If not, the evaluator pass is premature — finish the evaluation first.pagekit-evaluator-pass subagent. Pass the run-folder path.runs/<name>/evaluator-pass.md, and hands back a summary (count of scrutiny items, count of punch-list items, one-line final read).A strong evaluator pass:
If the subagent's output is general rather than specific, ask it to retry with more direct reference to the run's artifacts.
pagekit-claim-checkerpagekit-claim-checker reviews the draft line by line at a chosen severity.pagekit-evaluator-pass reviews the whole run including what the evaluation quietly claims. Different target, different voice.npx claudepluginhub hnshah/pagekit --plugin pagekitEvaluates TandemKit Generator output against specs using Codex as second opinion. Autonomous verification loops via bash state watchers and signals until pass or user intervention.
Reviews evaluation results for Claude Code skills. Presents judge scores and skill outputs for human feedback, then proposes SKILL.md improvements based on user input.