Agent Skills Hub

create-unit-test

Create and run unit tests for AnySoftKeyboard following project architecture guidelines (Robolectric, naming, location).

response-compliance

Run OpenResponses API compliance tests to validate schema adherence, streaming responses, and endpoint reliability for LobeHub integrations.

claude-copilot

Analyze markdown documentation files to ensure compliance with predefined AI token budgets and optimize content for efficient AI ingestion.

security-hardening

Comprehensive security audit and hardening for AI agents: credential scanning, PII protection, prompt injection defense, and workspace config optimization.

paperbanana

Generate publication-quality statistical plots from CSV or JSON data files using AI-driven automated visualization.

food-diorama-skill

Generate artistic 3D city-themed food diorama images using Google Gemini API. Creates Pop Mart style four-quadrant layouts featuring iconic dishes, cultural symbols, and city-specific heritage elements.

office-sprite

Generate and process 16-bit pixel art office assets for the Claude Office Visualizer using Nano Banana MCP and multi-pass ImageMagick workflows.

product-management

AI-native product management tool for startups. Features automated competitor research, gap analysis using the WINNING filter, PRD generation, and GitHub Issues integration for prioritized, signal-based roadmap planning.

scientific-visualization

Meta-skill for generating publication-ready scientific figures, multi-panel layouts, and journal-compliant visualizations using Python's matplotlib, seaborn, and plotly libraries.

eval

Evaluate Deca agent prompts and behavioral consistency through automated test runners, manual LLM judgment, and structured reporting.

tweet-rl-tracker

A Notion-based tracking system for tweet performance to enable data-driven content experimentation using reinforcement learning principles.

rag-engineer

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