Commit Graph

3 Commits

Author SHA1 Message Date
Ralph Furman
c3f6d9e9fa Fix YAML frontmatter — quote description, replace colon with em-dash
Unquoted colon in 'calibrated confidence: will say' broke strict YAML parsing.
CC's parser is lenient but fix for robustness.
2026-03-20 02:07:27 +00:00
Ralph Furman
9720278412 math-olympiad: forbid web access in deep mode
Deep-mode allows bounded local computation but must NOT use WebFetch
or WebSearch. Finding the solution on AoPS is not solving the problem.
Adds explicit NO WEB prompt block and orchestrator self-restraint note.

Found by Ralph's test run (skill solved 5/6 then started fetching
dgrozev.wordpress.com and artofproblemsolving.com for P6).
2026-03-20 00:39:08 +00:00
Ralph Furman
3c9bf4ff5d Add math-olympiad skill — adversarial verification for competition math
The skill that addresses the Proof-or-Bluff gap: self-verified 85.7% IMO
becomes <5% under human grading. Uses fresh-context verifiers armed with
specific failure patterns (not generic 'check logic').

Validated: 17/18 IMO+Putnam 2025 solved, 0 false positives, 2 novel proofs.
See eval data in anthropic monorepo sandbox/sandbox/ralph/math_skills/.
2026-03-19 23:17:36 +00:00