A 6-skill engineering toolkit that runs natively across Claude Code, Gemini CLI, and OpenAI Codex. Design principle: telegraph style, opinionated, zero filler. Includes debug-hypothesis (scientific debugging), spec-driven-dev (6-gate development), wiki-aggregate (multi-source research with citation tracking), and nano-banana (Gemini image generation). MIT licensed.
Open →A Claude Code Skill that generates geometric SVG logos from a brand name and concept, then uses Gemini Flash Image to produce 12 professional background exhibition images. Outputs 6+ design variants plus an interactive HTML showcase in one run. 689 stars, MIT licensed.
Open →Google's open-source AI file type detection — the system behind Gmail, Drive, Safe Browsing, and VirusTotal. Uses deep learning to read full file content patterns instead of magic bytes, catching disguised malicious files. ~99% accuracy across 200+ formats, ~5ms per file on CPU, multi-language SDK (Python, Rust, JS, Go). Main limitation: encrypted/compressed files get low confidence, and it's ~100-1000x slower than `file`.
Open →14 high-quality diagram and visualization Claude Code Skills covering 5 rendering engines (Vega-Lite/Vega, PlantUML, JSON Canvas, HTML/CSS, Infographic YAML). One-line install, compatible with Claude Code, Codex, Cursor, and GitHub Copilot. 70+ infographic templates, enterprise-grade UML and architecture diagram support. MIT licensed.
Open →