$ show OpenMinis/MinisSkills
This repository is a monorepo of 'skills' for the Minis AI assistant platform, designed to extend the assistant's capabilities with domain-specific workflows, API integrations, and automation scripts. Each skill is a self-contained directory with a SKILL.md (instruction set for the AI), executable scripts (Python/shell), reference documentation, and evaluation test cases. The skills cover a wide range of tasks: social media management (Weibo, Twitter/X, Xiaohongshu, Telegram, Bilibili), media processing (YouTube downloader, PDF conversion, TTS, image generation), financial data retrieval (US/Korea/China stocks, fund flows), productivity (Notion API, todoocard e-paper, whenpeak energy prediction), video composition (HyperFrames framework), and system utilities (Android dev environment, Cloudflare DNS, qBittorrent). The architecture is modular and agent-driven: the AI selects a skill based on user intent, reads its SKILL.md, and invokes the provided scripts via shell_execute. Output is typically JSON for machine consumption. The codebase demonstrates strong engineering practices with structured skill definitions, evaluation frameworks, and reusable patterns like cookie-based auth, SQLite message stores, and deterministic animation analysis. However, many skills depend on reverse-engineered or unofficial APIs, hardcoded paths tied to the Minis iOS environment, and external tools (ffmpeg, pandoc, typst), introducing maintenance and portability risks.
The LLM identified 4 files worth highlighting for reuse:
A standalone Node.js script that parses HTML files containing GSAP animations, enumerates all tweens, detects staggers, dead zones, and collision overlaps, and generates an ASCII timeline visualization. It uses cheerio for DOM parsing and is fully self-contained, making it reusable for any GSAP-based animation project to audit and debug animation sequences.
A Node.js script that uses Puppeteer to capture screenshots of web pages and sharp to sample background pixels, then computes WCAG contrast ratios against foreground text. It exits with a non-zero code on AAA failures, making it suitable for CI pipelines. The script is self-contained and can be extracted to audit any web page for color contrast compliance.
A Python module providing a SQLite-backed message store with full-text search, timeline queries, and top sender aggregation. It uses only the standard library (sqlite3, datetime, json) and exposes a clean API for inserting, searching, and retrieving messages. This pattern is reusable for any application needing a lightweight, local message database with search capabilities.
A self-contained HTML file that renders an interactive Leaflet map with marker clustering, a geolocation button, and a bottom info card. It includes all CSS and JavaScript inline, handles iOS safe areas, and supports deep links to native map apps. This template can be reused directly in any project requiring a mobile-friendly map with multiple markers and location services.