math-olympiad
"Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no conf
Profile →npx skills add anthropics/claude-plugins-official --skill math-olympiad --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Math Olympiad Solver ## The five things that change outcomes 1. **Strip thinking before verifying** — a verifier that sees the reasoning is biased toward agreement. Fresh context, cleaned proof only. 2. **"Does this prove RH?"** — if your theorem's specialization to ζ is a famous open problem, you have a gap. Most reliable red flag. 3. **Short proof → extract the general lemma** — try 2×2 counterexamples. If general form is false, find what's special about THIS instance. 4. **Same gap twice → step back** — the case split may be obscuring a unified argument. Three lines sometimes does what twelve pages couldn't. 5. **Say "no confident solution"** — wrong-and-confident is worse than honest abstain. --- **Tool policy**: Solvers and verifiers use THINKING ONLY in the tight-budget workflow. Competition math is reasoning. Computation is for deep mode (§6c), and even then bounded — a recurrence that's doubly-exponential can't be computed past n~30, work mod 2^m instead. --- ## When to use which approach | Problem | Approach | Verification | | ---------------------------------------------------- | ------------------------------------------------------------------------------ | ----------
- The five things that change outcomes
- When to use which approach
- For a full problem set
- The Workflow
- 1. Interpretation check (30 seconds, catches 50/63 of one class of errors)
- 2. Generate candidates with internal refinement (parallel, thinking only)
- 3. Clean the solution (context isolation — the #1 lever)
- 4. Adversarial verify (fresh context, pattern-armed)
- 5. Rank and vote-verify (asymmetric + early exit)
- 5b. When one case won't close — step back before grinding
- 6. Revise (if needed)
- 6c. Deep mode (when tight-budget abstains)
- 7. Calibrated abstention
- 8. Presentation pass (after correctness is established)
What does the math-olympiad skill do?
"Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no conf
How do I install it?
Run `npx skills add anthropics/claude-plugins-official --skill math-olympiad --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From anthropics/claude-plugins-official, a repository with 33,027 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.