Machine learning

会话观察者（v4.2 草案）：为一段 agent 工作（Claude Code、Codex、Kimi、dsh 会话，可以多个）建立并维护一份认知——任务地图：你要什么 → 走到哪 → 还在主线上吗 → 卡在哪 → 下一步，项目里现成的…

Fetch any web page and get clean, LLM-ready Markdown back, via String Web Access.

Chat / code generation via tokenhop using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.

Generate vector embeddings via tokenhop /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search…

Speech-to-text via tokenhop /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models.

Provides AI and machine learning techniques for CTF challenges.

Deploy, inspect, warm, cache, and troubleshoot the Modal + ComfyUI image backend and Hugging Face storage.

Triggers on keywords RAG, GraphRAG, vector database, agentic RAG, semantic search

A pipeline for generating 3D assets from text descriptions using AI image generation and Trellis 3D reconstruction, with cloud inference support…

This project is an AI-powered aimbot that uses machine learning models to detect and aim at targets in games through screen capture analysis.

This project is an AI-powered FPS aimbot that uses computer vision and machine learning to detect and aim at enemy players in first-person shooter games.

Use this skill when you need to design LLM evaluation datasets, judges, metrics, and human-review boundaries; triggers include LLM Eval 设计 and llm evaluation…

Use this skill when you need to design LLM evaluation datasets, judges, metrics, and human-review boundaries; triggers include llm evaluation design.

Use this skill when you need to test LLM behavior, failure modes, and evidence-based quality boundaries; triggers include llm testing.

Use this skill when you need to test LLM behavior, failure modes, and evidence-based quality boundaries; triggers include LLM 测试 and llm testing.

Expert-level AgentScope developer skill for building production-ready LLM agents.

Develop the first correct Ascend Triton kernel from a PyTorch reference or a GPU Triton implementation.

Best practices for LLM-assisted coding.

Refuse an arena.ai scrape.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Also use for async Python patterns, Pydantic schemas for LLM structured outputs, retry strategies for LLM calls, background AI jobs, or any service combining…

TypeDoc plugin that generates AI agent skills (SKILL.md) from TypeScript API documentation Use when working with agent-skills, ai, documentation, llm…

0-arg local-mode PR babysitter.

LLM tool-calling + MCP + agent skill for Binance USD-M Futures.