Menu
Review completed work against success criteria and flag issues
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Generate a wide field of ideas, then pressure-test them. Five generators diverge, two challengers prune the weak ones, three synthesizers rank what survives.
Three-agent adversarial bug finder. Hunter overclaims every issue it can find, Skeptic disproves what it can, Referee arbitrates what survives. Scoring incentives force each role to behave honestly.
Dialectic process for reviewing, brainstorming, comparing tradeoffs, or stress-testing plans. Configurable modes, agent counts, and expert lenses.
Execute a pre-defined plan using implementation agents (no design changes)
Capture structured learnings (gotcha, pattern, decision, bug-fix) as JSONL per project. Cross-project searchable.
Assume the plan failed — then explain why. Three pessimists write failure narratives, two optimists rebut, a risk assessor weighs which failure modes are real.
Basé sur la classification professionnelle SOC
| name | review |
| description | Review completed work against success criteria and flag issues |
| user-invocable | true |
| disable-model-invocation | false |
| argument-hint | ["what to review - file","feature","or recent work"] |
Evaluate completed work against its success criteria. Find problems before they compound.
What to review: $ARGUMENTS
If no arguments, review whatever was most recently implemented in the conversation.
/verify hasn't been run on the target, suggest running it first — /verify catches completeness issues, /review catches quality issues. Different concerns.Read @review-dimensions.md for what to check based on the type of work (code, data, writing).
Launch the review using a fresh-context subagent (use the code-reviewer agent persona for code). The reviewer should NOT share the implementer's assumptions.
Read @output-format.md for how to organize findings.
/dialectic-review for adversarial depth/dialectic-review --premortem before proceeding with fixesRead @rules.md for review rules and gotchas.