Loading...
Loading...
Found 21 Skills
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".
AFK adversarial code-review loop: Cursor agent CLI critic (grug + thermo-nuclear) produces structured findings; Codex validator confirms or pushbacks on regression risk; parent adjudicates and commits fixes per finding until clean. Config at ~/.config/adversarial-review/config.toml. Use for adversarial review, clean code loop, or unattended branch hardening.
Devil's Advocate stress-testing for code, architecture, PRs, and decisions. Surfaces hidden flaws through structured adversarial analysis with metacognitive depth. Use for high-stakes review, stress-testing choices, or when the user wants problems found deliberately. NOT for routine code review (use engineering:code-review). Triggers on "스트레스 테스트", "stress test", "devil's advocate", "반론", "이거 괜찮아", "문제 없을까", "깊은 리뷰", "critical review", "adversarial".
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
Use when testing plans or decisions for blind spots, need adversarial review before launch, validating strategy against worst-case scenarios, building consensus through structured debate, identifying attack vectors or vulnerabilities, user mentions "play devil's advocate", "what could go wrong", "challenge our assumptions", "stress test this", "red team", or when groupthink or confirmation bias may be hiding risks.
Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.
Systematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with parallel agents, self-validation, and optional adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".
Devil's Advocate stress-testing for code, architecture, PRs, and decisions. Surfaces hidden flaws through structured adversarial analysis with metacognitive depth. Use for high-stakes review, stress-testing choices, or when the user wants problems found deliberately. NOT for routine code review (use engineering:code-review). Triggers on "스트레스 테스트", "stress test", "devil's advocate", "반론", "이거 괜찮아", "문제 없을까", "깊은 리뷰", "critical review", "adversarial".
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.