10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 587 ms
skillpoteto/noodlerecord
- adversarial-review
Adversarial code review using cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesized verdict with findings and lead judgment. Triggers: "adversarial review".
- adversarial-review
skillalirezarezvani/claude-skillsrecord
- adversarial-reviewer
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 sp
- adversarial-reviewer
skilljuliusbrussee/cavekitrecord
- review
Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence (file:line or source); unverifiable ones a
- review
skillevoscientist/evoskillsrecord
- paper-review
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: three passes (adversarial deep read; 5-aspect checklist — contribution sufficiency, writing clarity, results quality, testing completeness, method design; mechanical consistency scans and ex
- paper-review
- 5OP Adversarial Pressure MCPfound in code, not yet checkedno passport yet
- adversarial_review
Use when structural review is requested but the calling model has not isolated one relation. The model behind the tool selects candidate breaks and smallest fixes from one artifact. The calling model triages each; no style review, scoring, or decisions.
- adversarial_review
- 6panel-review MCP serverfound in code, not yet checkedno passport yet
- panel_review
Run an adversarial panel review across models in parallel and return each verdict.
- panel_review
skillzenstory-ai/oh-story-claudecoderecord
- story-review
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn;缺失/异常 agents 或 spawn 失败时自动降级 solo,参考文件不可读时使用内置 rubric fallback。触发方式:/story-review、/审查、「审查一下」「帮我审一下」。
- story-review
skillngmeyer/skillsrecord
- council-review
Run any question, plan, PR, or code through a Diverse Multi-Agent Debate (DMAD) council of 5 AI advisors with distinct reasoning methods. Advisors collaborate, peer-review each other anonymously, and a chairman synthesizes a verdict. Empirically outperforms adversarial debate (M3MADBench 2026, DMAD
- council-review
- 9adversarial-ai-code-review-platformfound in code, not yet checkedno passport yet
MCP servermanreetbhatia/adversarial-ai-code-review-platform
- review_code
- review_diff
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.