Machine learning

分析 Android 项目源码，用 LLM 从多维度生成 AI 自动化测试所需的先验知识文档，打包上报测试平台。核心价值：让 AI 测试 Agent 在运行前就知道「测什么、怎么断言、有哪些陷阱」。触发词：「分析我的 Android 项目」「生成测试画像」「理解这个 App 的业务」「提取测试先验知识」「帮我分析…

Use when user asks if hippo is working, running, healthy, or needs debugging.

Manage the ClaudeClaw-Plus MCP bridge — register plugins, monitor health, audit invocations, debug cross-process calls, generate plugin templates.

基于Sorftime MCP的深度选品调研。通过LLM Agent执行多维度分析：数据采集→属性标注→交叉分析→竞品VOC→壁垒评估→选品决策评估。交互式执行，输出Markdown报告和Dashboard看板。

vLLM: high-throughput LLM serving, OpenAI API, quantization.

HuggingFace hf CLI: search/download/upload models, datasets.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.

Use when creating, validating, exporting, embedding, or automating D2/D2Lang diagrams, .d2 files, diagram-as-code architecture diagrams, CLI watch/render…

Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and…

Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search…

Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models.

Make a website or product readable and callable by AI agents rather than only by browsers — Markdown mirrors of every page, Accept-header content negotiation…

Query the APITube News API — authenticate, search and filter worldwide news articles by keyword, entity, sentiment, source, country and date, and parse the…

Use when a project needs OpenTelemetry instrumentation for Fixter, when verifying an existing OTel setup points to Fixter, or when adding LLM observability.

Guide for installing, configuring, and managing Tailscale, headscale, and the Tailscale product family.

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.

Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb.

Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb.

Wire Hermes LLM providers, fallback chain, Telegram gateway.

Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.

Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback.