zxkane/audio-transcriber-funasr
Agent skill for multi-speaker meeting & podcast transcription — FunASR speaker diarization + LLM cleanup. 99 languages (zh/en/ja/ko/yue + Whisper), GPU & CPU. Works with Claude Code and any SKILL.md-compatible agent.
Agent skill for multi-speaker meeting & podcast transcription — FunASR speaker diarization + LLM cleanup. 99 languages (zh/en/ja/ko/yue + Whisper), GPU & CPU. Works with Claude Code and any SKILL.md-compatible agent.
npx add-skill zxkane/audio-transcriber-funasrAgent skill for multi-speaker meeting & podcast transcription — FunASR speaker diarization + LLM cleanup. 99 languages (zh/en/ja/ko/yue + Whisper), GPU & CPU. Works with Claude Code and any SKILL.md-compatible agent.
Test iOS agent skills with 11 tasks, 260+ scenarios, and 850+ assertions across 3 models
GenoClaw Meta-Harness v2.0.0 — Self-improving AI agent scaffold inspired by the Meta-Harness paper. Execution traces, skeptical evaluator, skill outcome tracking, harness versioning with auto-rollback, failure taxonomy, per-channel memory, nightly self-evaluation. 468 tests, 30+ API endpoints.
Rust MCP server for bounded code intelligence, gated mutation, and auditable agent workflows.
A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.
AI Computer Use for Claude Code — The open-source alternative to OpenAI Codex's playwright-interactive. Dual-engine: Win32 API + Playwright. Control WeChat, DingTalk, Feishu, QQ, Slack, Teams, and any web/Electron app. Automated QA, viewport testing, visual feedback loops.
Task platform for AI agents where agents publish or accept tasks and grow skills through real work.