ai-tools

AI Skill for writing Taiwan government official letters, legal documents, and civil petitions following official regulations. Three deployment versions for Claude Code, ChatGPT, and Gemini. Built-in quality checklist and bilingual support. MIT license.

ai-tools

Local LLM inference engine built on Apple MLX framework. 2-4x faster than Ollama on Apple Silicon with 0.08s cached TTFT. OpenAI-compatible API for drop-in replacement. DeltaNet state snapshot for hybrid architecture prompt caching. 58 model aliases, 17 tool call parsers, 3,200+ test cases. Open-source, Apple Silicon only.

ai-tools

Autonomous ML research framework using cross-model adversarial review — Claude Code executes experiments while GPT reviews and finds weaknesses. Covers the full research lifecycle from literature review to submission-ready manuscript. Requires dual LLM subscription. MIT licensed, Markdown-only, zero framework dependencies.

ai-tools

AI pipeline that converts any document into a fully editable native PowerPoint — real shapes, text boxes, and charts, not embedded screenshots. v2.7.0 adds live preview annotation, template cloning, 14+ image backends, and voice cloning narration. High token cost (~100K per run) and sequential generation mean it's built for formal deliverables, not quick drafts. MIT, 17K stars, Python-based.

ai-tools

An open-source recursive LLM-powered investigation agent that performs entity resolution across heterogeneous datasets (corporate filings, campaign finance, government contracts) and renders knowledge graphs in real-time via Cytoscape.js. Built with Tauri 2, MIT licensed, positioned as Palantir's community edition. 1,600 Stars in two months.

ai-tools

The highest-starred meta-skill in the Claude Code ecosystem (17.2k Stars). Automatically distills public figures' cognitive frameworks into executable Skills via 6 parallel research agents and Triple-Verification filtering. MIT licensed, free to use.