Agent Skills Hub

btca-cli

Operate the btca CLI for source-first code research. Manage git, local, and npm resources to ground AI answers in actual codebase context rather than outdated documentation.

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.

web-search-free

Free AI-powered web search via Exa MCP. Includes deep research, company/people lookup, and code context without API keys.

tax-advisor

AI-powered tax advisor providing expert guidance on 2025 Japanese tax regulations, deductions, and financial planning for freelancers and employees.

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

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.

analyzing-research-documents

Systematically extract insights, decisions, and constraints from research documents, technical papers, and architectural design files.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.

gemini-vision

Implement Google Gemini API vision capabilities for image/document analysis including captioning, object detection, segmentation, and multi-image comparison.

copy-editing

Systematically improve marketing copy through a 7-pass editing framework to boost clarity, tone, and conversion impact.

gemini-video-understanding

Perform advanced video analysis using Google's Gemini API: summarize content, transcribe audio, extract timestamps, clip segments, and analyze YouTube URLs or local files with support for multiple models and long contexts.