Agent Skills Hub

product-tryon-visualization

Generate realistic virtual product try-on visualizations to help customers evaluate fit, drape, and scale before purchasing.

skill-architect

Expert consultant for designing and building high-quality, consistent AI agent skills. Guides you through discovery, architecture, and creation phases to ensure reliable, composable, and efficient skill delivery.

code-search-selector

Intelligent tool selector for code search. Routes queries between semantic (claudemem) and native tools (Grep/Glob) to optimize efficiency, token usage, and search accuracy.

structured-outputs-advisor

Expert advisor for implementing Anthropic's structured outputs. Choose between JSON mode and strict tool use for guaranteed schema compliance and validated agentic workflows.

codebase-analyzer

Automates the creation and maintenance of CLAUDE.md files. It monitors codebase evolution and keeps project memory in sync with file changes, structure, and build commands.

ADK Developer

A comprehensive guide and reference for building, orchestrating, and deploying AI agents using the Google Agent Development Kit (ADK).

statsmodels

Statistical modeling and econometrics library for Python. Performs OLS, GLM, mixed models, ARIMA, diagnostics, and inference for rigorous scientific analysis.

mcp-research

Retrieve current, source-backed technical information using MCP tools to resolve queries about libraries, APIs, SDKs, and evolving tech ecosystems.

memory-hygiene

Audit, prune, and maintain vector memory for Clawdbot. Prevents token waste, clears junk data, and automates memory hygiene via LanceDB maintenance.

repomix

Package entire code repositories into single, AI-optimized files. Ideal for providing codebase context to LLMs like Claude, ChatGPT, and Gemini for analysis, security audits, and bug investigations.

deep-research

A systematic, multi-angle web research agent. Use for deep investigation, complex queries, and as a mandatory pre-research step before content generation to ensure evidence-backed, high-quality results.

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.