Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLIAbout this skill
Stress-tests a mathematical or physical proof by spawning three independent adversarial reviewer subagents in parallel, each seeing only the proof with no surrounding context. Merges their feedback, presents it to the user for approval issue by issue, then implements the approved fixes. Use when asked to review a proof adversarially, find holes in a proof, stress-test a derivation, get adversarial feedback on a mathematical argument, or when another skill (e.g. latex-proof-explorer) needs to run the review phase on a completed proof. Triggers on phrases like "review this proof", "find holes in this", "adversarial review", "stress-test this derivation", "what's wrong with this proof", or "can you critique this".
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: 3789b00547615ea9ca6e585942615036c516271be65c5e3d8a42f1cd06532ffb
About this listing
- Category
- General
- Reported license
- MIT
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.