Integrates Agent Skills into LLMs by discovering skills in a configured directory and progressively loading their instructions and resources on demand through a structured disclosure pattern.
A tool that implements Claude Shannon's problem-solving methodology to help break down complex problems into structured steps including problem definition, constraints, modeling, validation, and implementation.
A TypeScript MCP server delivering a vendored 'dangerous skills' corpus and adversarial fixtures over MCP for security-research testing, supporting SEP-2640 skill delivery with archive-safety hardening.
Provides utilities to help maintain MCP repositories, including testing tools, parameter type support, and multiple transports (STDIO, SSE, Streamable HTTP).
Exposes 238 dry-run tools across Workers, R2, D1, KV, Queues, Turnstile, and email products, letting clients discover and select capabilities through a flat list, hierarchical toolset and workflow groups, or skills. Every tool call returns the API request it would send, so agents can compose and validate operations without touching a live account.
Enables AI-assisted code review with bias mitigation strategies through cross-model evaluation and bias-aware prompting. Detects AI-generated code from commit authors and provides structured reviews with security, performance, and maintainability analysis.