Loading...
Loading...
Found 21 Skills
Use when substantive documents (reviews, analyses, synthesis documents) need adversarial review to strengthen arguments, identify weak points, and challenge assumptions before editorial polish (mandatory for Writer → Devil's Advocate pairing protocol)
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
Transform technical jargon into clear explanations using before/after comparisons, metaphors, and practical context
Technical design interview + adversarial review → living doc Technical Design section ready to implement. Stateful: detects existing sections and resumes where needed. Triggers: 'architect this,' 'how should we build,' 'design the tech,' post-define/design. Not for: scoping (explore), requirements (define), UX (design).
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Four LLM reviewers challenge changes from independent angles.
Run adversarial review on a PM artifact via the pm-critic sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-critic); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads subagents/pm-critic.md and executes the system prompt inline. Returns findings graded P0/P1/P2/P3 with concrete fix suggestions per finding, plus a layered Status Summary section and machine-readable Status YAML block per master plan D26.
Adversarial critique of a research draft or paper using an isolated critic context. The critic must have no access to the current conversation history — context isolation, not model identity, is what makes the review independent. Use when a draft is complete or partially complete, after each writing round, or when `write` invokes it automatically. Returns FATAL/MAJOR/MINOR issues, a structured score (0–10), and a PROCEED/REFINE/PIVOT recommendation. Caps at 4 rounds. Trigger phrases: "review paper", "critique draft", "check citations", "adversarial review".
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review isn't enough.
Use OpenAI Codex from inside Claude Code for code reviews, adversarial reviews, and delegating tasks to Codex as a subagent.