productivity▌

Comprehensive skill for automating audio/video transcription and content processing.

Build voice AI agents with natural conversations, multiple LLM providers, custom tools, and web embedding. \n \n Supports five LLM providers (OpenAI, Anthropic, Google, ElevenLabs, custom) with 30+ model options and configurable voice personalities \n Extend agents with webhook tools (server-side API calls), client tools (browser-side actions), and built-in system tools like call transfer and end-call \n Embed agents in web applications via HTML widget or JavaScript SDK with React hooks for real

Ultra-fast Python package installer and resolver written in Rust, 10-100x faster than pip. \n \n Drop-in pip replacement with virtual environment and Python version management built in \n Supports dependency locking with uv.lock for reproducible builds, monorepo workspaces, and seamless migration from pip, poetry, and pip-tools \n Includes uv run for executing scripts and tools without manual venv activation, plus parallel package installation and global caching for speed \n Integrates with CI/C

ln-628-concurrency-auditor

Automate iOS and Android app interactions with snapshot-based discovery and selector-driven replay. \n \n Supports iOS simulators/devices and Android emulators/devices with session-bound automation, multi-tenant remote daemon mode, and device-scope isolation for QA workflows \n Core commands: snapshot for UI discovery with refs, press / fill / scroll for interactions, open / close for app lifecycle, install / reinstall for binary deployment \n Includes utilities for logging, network inspection,

sentry-pr-code-review

Composition patterns for building flexible, maintainable React components. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. These patterns make codebases easier for both humans and AI agents to work with as they scale.

Extract clean content from specific URLs using Tavily's extraction API. \n \n Supports up to 20 URLs per request with optional query-based reranking to focus on relevant content chunks \n Two extraction modes: basic for fast text extraction, advanced for JavaScript-rendered pages and structured data \n Automatic OAuth authentication via browser on first run, or manual API key configuration in settings \n Returns markdown or plain text format with optional image URLs and configurable timeout up t

TransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models. Created by Neel Nanda and maintained by Bryce Meyer, it provides clean interfaces to inspect and manipulate model internals via HookPoints on every activation.

Guides backlink profile analysis: assessing quality, identifying issues, and planning improvements.