productivity▌

Vision-driven browser automation using your real Chrome browser, preserving sessions and login state. \n \n Operates entirely from screenshots without requiring DOM access; interacts with all visible elements regardless of technology stack \n Connects to desktop Chrome via Midscene Extension through Chrome DevTools Protocol, never taking over mouse or keyboard \n Supports multi-step workflows including navigation, form filling, data extraction, UI testing, and screenshot capture \n Requires visu

Vision-driven desktop automation for native apps using natural language commands and screenshots. \n \n Controls macOS, Windows, and Linux desktops entirely from visual input; no DOM or accessibility labels required \n Operates synchronously with a screenshot-analyze-act loop: connect, observe screen state, execute high-level actions via natural language prompts, then disconnect \n Requires a vision-capable AI model (Gemini, Qwen, Doubao, or similar) configured via environment variables; support

Convert documents, spreadsheets, presentations, images, audio, and web content to Markdown for LLM processing. \n \n Supports 15+ formats including PDF, Word, PowerPoint, Excel, HTML, CSV, JSON, XML, images with OCR, audio with transcription, ZIP archives, YouTube URLs, and EPub \n Preserves document structure including headings, tables, lists, and links in the converted Markdown output \n Optional Azure Document Intelligence integration ( -d flag) for improved extraction on complex or scanned P

Enforces Sentry conventional commit format with proper types, scopes, and issue references. \n \n Requires feature branch creation before committing to main or master; uses the create-branch skill to manage branch workflow \n Supports 12 commit types (feat, fix, ref, perf, docs, test, build, ci, chore, style, meta, license) with clear subject line rules and footer patterns for issue references \n Includes Co-Authored-By attribution for AI-generated changes and handles breaking changes with expli

Submit or update Wall of Apps entries via App-Store-Connect-CLI with dry-run preview and confirmation flow. \n \n Supports two submission paths: standard App Store flow using app ID, or manual flow using TestFlight link and app name \n Includes dry-run mode to preview changes before applying with --confirm flag \n Generates PR-based submissions that modify docs/wall-of-apps.json with built-in guardrails against unrelated entry changes \n Run commands from the App-Store-Connect-CLI repository roo

Declarative Vue 3 framework for building 3D scenes with Three.js components. \n \n TresCanvas root component wraps WebGL renderer; all Three.js classes available as Vue components with Tres prefix (e.g., TresMesh , TresPerspectiveCamera ) \n Core packages: @tresjs/core (required), @tresjs/cientos (OrbitControls, model loaders, materials), @tresjs/post-processing (bloom, glitch, depth-of-field effects) \n Props are reactive; changes automatically update the 3D scene; use primitive component to in

Persistent memory systems for LLM conversations with tiered storage and intelligent retrieval. \n \n Implements three memory types: short-term (immediate context), long-term (historical facts), and entity-based (facts about specific entities) \n Provides memory retrieval and consolidation capabilities to surface relevant memories without overwhelming context windows \n Addresses critical concerns including unbounded memory growth, retrieval relevance, and strict user isolation to prevent cross-u

Use the voice-call plugin to start or inspect calls (Twilio, Telnyx, Plivo, or mock).

Search A-Share/HK/US stock tickers and retrieve historical price data (OHLCV).

6 production-ready project management skills with Atlassian MCP integration.