adversarial-reviewlisted

Adversarial review of any artifact — a plan, PRD, ADR, design doc, code diff, or the current conversation itself — from a hostile stance that tries to break it rather than improve it. Use when asked to "adversarially review", "red team this", "poke holes in", "attack this plan", "review our discussion", "what did we get wrong", "stress-test this", "steelman then break", "review this ADR/PRD/doc", or "find the flaws". Resolves the target, picks critique lenses per artifact type, self-refutes each candidate finding, and reports ranked findings with concrete failure scenarios. Read-only — never edits the artifact. Escalates to independent subagents (optionally on a different model) on request or for large targets.
Stormix/transcripts-mcp · ★ 10 · AI & Automation · score 79

Install: claude install-skill Stormix/transcripts-mcp

# Adversarial Review Attack an artifact until either a real defect surfaces or the artifact survives. Report what breaks it, not what would polish it. The stance is the skill. A normal review asks "is this good?" — this one assumes the artifact is wrong and looks for the argument that proves it. Findings that cannot be stated as a concrete failure scenario are not findings. ## Step 1: Resolve the target | Argument | Target | | ------------------------------------------------- | ------------------------------------------------------------------------- | | (none) | The current conversation — the plan, claims, and decisions reached so far | | `this chat`, `our discussion`, `what we decided` | Same as above | | A file or glob path | That document, plan, ADR, PRD, or source file | | A git ref, `the changes`, `this branch`, a PR URL | The diff against the merge-base | | A URL | Fetch it and review the fetched content | | Pasted text in the prompt | That text | If the target is genuinely ambiguous — two plaus