>

Build AI agents with Claude Agent SDK in TypeScript. Covers V1 query() API for batch workflows and V2 session API for interactive apps. Includes tool configuration, hooks, MCP servers, and...

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained...

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained...

Use this when creating new projects, generating documentation, cleaning/organizing a repo, suggesting architecture, deploying containers and services, naming files/folders, or when the user...

Autonomous coding agent that breaks features into small user stories and implements them iteratively with fresh context per iteration. Use when asked to: build a feature autonomously, create a...

|

|

Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data,...

Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data,...

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection,...

Guide for Convex backend development fundamentals including function types (queries, mutations, actions), layered architecture, HTTP actions, and the core mental model. Use when building Convex...

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...

Create, update, and improve Claude Code agent files following Anthropic's official best practices. Use when user mentions "agent", "AGENT.md", "create agent", "update agent", "improve agent",...

|

|

|

Central hub for managing user preferences, learning patterns, and adapting skill behavior based on historical feedback. Enables "tell me once" paradigm where the system remembers and adapts.