<feed xmlns='http://www.w3.org/2005/Atom'>
<title>claude-plugins-official.git/plugins/math-olympiad, branch add-cloud-sql-postgresql</title>
<subtitle>Official Claude Code plugin directory
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/'/>
<entry>
<title>math-olympiad: housekeeping (#1172)</title>
<updated>2026-03-30T19:56:21+00:00</updated>
<author>
<name>Tobin South</name>
<email>tobin.south@gmail.com</email>
</author>
<published>2026-03-30T19:56:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=9d468adfb857b1aeedb45f6279409820a0ffa573'/>
<id>9d468adfb857b1aeedb45f6279409820a0ffa573</id>
<content type='text'>
* math-olympiad: add LICENSE, marketplace entry, and prettier formatting

- Add Apache 2.0 LICENSE file
- Register plugin in marketplace.json
- Run prettier (prose-wrap=always, 80 cols) over all plugin markdown
- Simplify model tier naming in reference docs

:house: Remote-Dev: homespace

* Update .claude-plugin/marketplace.json</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
* math-olympiad: add LICENSE, marketplace entry, and prettier formatting

- Add Apache 2.0 LICENSE file
- Register plugin in marketplace.json
- Run prettier (prose-wrap=always, 80 cols) over all plugin markdown
- Simplify model tier naming in reference docs

:house: Remote-Dev: homespace

* Update .claude-plugin/marketplace.json</pre>
</div>
</content>
</entry>
<entry>
<title>Fix YAML frontmatter — quote description, replace colon with em-dash</title>
<updated>2026-03-20T02:07:27+00:00</updated>
<author>
<name>Ralph Furman</name>
<email>ralph@anthropic.com</email>
</author>
<published>2026-03-20T02:07:27+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=c3f6d9e9fac9a5caa3967a1edbe20a905d138ad6'/>
<id>c3f6d9e9fac9a5caa3967a1edbe20a905d138ad6</id>
<content type='text'>
Unquoted colon in 'calibrated confidence: will say' broke strict YAML parsing.
CC's parser is lenient but fix for robustness.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Unquoted colon in 'calibrated confidence: will say' broke strict YAML parsing.
CC's parser is lenient but fix for robustness.
</pre>
</div>
</content>
</entry>
<entry>
<title>math-olympiad: forbid web access in deep mode</title>
<updated>2026-03-20T00:39:08+00:00</updated>
<author>
<name>Ralph Furman</name>
<email>ralph@anthropic.com</email>
</author>
<published>2026-03-20T00:39:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=97202784125cdc3c21265a58fdfc09c3800f10e4'/>
<id>97202784125cdc3c21265a58fdfc09c3800f10e4</id>
<content type='text'>
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).
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
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).
</pre>
</div>
</content>
</entry>
<entry>
<title>Add math-olympiad skill — adversarial verification for competition math</title>
<updated>2026-03-19T23:17:36+00:00</updated>
<author>
<name>Ralph Furman</name>
<email>ralph@anthropic.com</email>
</author>
<published>2026-03-19T23:17:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=3c9bf4ff5d3461d485d425d5ec91c581e544de30'/>
<id>3c9bf4ff5d3461d485d425d5ec91c581e544de30</id>
<content type='text'>
The skill that addresses the Proof-or-Bluff gap: self-verified 85.7% IMO
becomes &lt;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/.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The skill that addresses the Proof-or-Bluff gap: self-verified 85.7% IMO
becomes &lt;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/.
</pre>
</div>
</content>
</entry>
</feed>
