Loading
Loading
written by Forgecat

Solve competition math (IMO, Putnam, USAMO) with adversarial verification that catches what self-verification misses. Fresh-context verifiers attack proofs with specific failure patterns. Calibrated abstention over bluffing.
npx forgecat install @forgecat/anthropics_claude-plugins-official_math-olympiad
| Field | Value |
|---|---|
| Author | Anthropic |
| Original repository | https://github.com/anthropics/claude-plugins-official/tree/main/plugins/math-olympiad |
| Version | 0.0.0 |
| Original commit | 7e401ed |
| License | Apache-2.0 |
| Source platform | Claude Code plugin |
| Platform | Status |
|---|---|
| Claude Code | Tested |
| Cursor | Partial |
| Codex | Partial |
written by original source
Competition math solver with adversarial verification.
Self-verification gets fooled. A verifier that sees the reasoning is biased toward agreement. arXiv:2503.21934 ("Proof or Bluff") showed 85.7% self-verified IMO success drops to <5% under human grading.
17/18 IMO+Putnam 2025 problems solved, 0 false positives, 2 novel proofs found. See the skill's eval data in the anthropic monorepo.
/plugin install math-olympiad@claude-plugins-official
> Solve this IMO problem: [statement]
The skill auto-triggers on "IMO", "Putnam", "olympiad", "verify this proof", etc.
None
forgecat
View CreatorNone