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.
Open →An AI Skill that guides academic paper framework figure design through a 13-step collaborative prompt workflow. Features an Atlas reference gallery of common figure types and an 'explore wide, refine locally, lock final' design logic. Primarily built for ChatGPT Web and Codex. Open-source.
Open →AI multi-agent pipeline built specifically for academic papers. Upload a PDF or LaTeX source, get an editable PowerPoint with original figures preserved. Three-role architecture (Strategist, Executor, Critic) with 4-pass deep reading, SVG-to-PPTX conversion, and optional icon semantic search. Early-stage but architecturally impressive. MIT license.
Open →AI Agent Skill for automated patent technical disclosure document generation. Full pipeline: patent point mining, CNIPA novelty search, sanitized disclosure document generation, self-check, and multi-round revision. Outputs .md + .docx dual format. Follows AgentSkills standard, works in Claude Code and Cursor. Focused on Chinese patent system (CNIPA). MIT licensed.
Open →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.
Open →