Agent Skills Hub

solo-validate

End-to-end startup idea validation using S.E.E.D. niche checks, STREAM 6-layer analysis, and Devil's Advocate inversion to generate PRDs.

claude-code

Standardized skill for Claude Code agents to dynamically query OpenRouter model recommendations and metadata via the Claudish CLI.

conversion-psychology

Psychology of conversion for video and sponsored content. Uses emotional triggers, social proof, scarcity, and persuasion principles to optimize scripts and enhance audience engagement.

mcp-research

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

developer-growth-analysis

Analyzes Claude Code chat history to identify coding patterns and skill gaps, curates personalized learning resources from HackerNews, and sends progress reports to Slack.

page-cro

Analyze and optimize marketing pages for higher conversion rates. Includes frameworks for homepages, landing pages, and pricing pages to improve messaging, UX, and CTAs.

rag-engineer

Architect and optimize production-grade RAG systems. Master embedding models, vector databases, chunking strategies, and retrieval pipelines for high-accuracy LLM applications.

scikit-learn

Classical machine learning with scikit-learn. Use for classification, regression, clustering, dimensionality reduction, preprocessing, model evaluation, and building robust ML pipelines in Python.

neo4j-cypher

Expert guidance for Neo4j Cypher queries and MCP server tools, focusing on schema introspection, graph operations, and efficient database development workflows.

resume-assistant

A 5-agent AI career assistant for resume building, job matching, interview prep, and growth planning.

daily-brief

Generate personalized, verified daily news briefings tailored to your interests, projects, and competitive landscape with strict 7-day source freshness.

llmfit-advisor

Analyze local system hardware (RAM, CPU, GPU/VRAM) to receive expert recommendations for optimized local LLM models, quantization settings, and performance estimates.