Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Statistical test selection, assumption checking, and APA-formatted reporting. Use when analyzing experimental results or writing results sections.

Statistical test selection, assumption checking, and APA-formatted reporting. Use when analyzing experimental results or writing results sections.

Use when working with WizTelemetry Notification extension for KubeSphere, including installation, configuration, troubleshooting, notification channel setup, alert routing, and silence management.

KubeSphere Volcano job management Skill. Use when user asks to create, list, update, delete Jobs (Volcano Jobs), manage Queues, create PyTorch/TensorFlow/MPI training jobs, or troubleshoot Volcano scheduling issues in KubeSphere. Includes built-in YAML templates, scheduling policy recommendations, and best practices for resource configuration. Handles both KubeSphere API and kubectl operations.

KubeSphere OpenKruise management Skill. Use when user asks to install or enable OpenKruise, check OpenKruise status, view kruise pods/logs/CRDs, create or update SidecarSet, manage sidecar injection, create or update CloneSet, perform in-place update or batch rollout, uninstall or remove OpenKruise, or troubleshoot Kruise Pod, CRD, and webhook issues in KubeSphere.

Use when configuring Jenkins in KubeSphere DevOps, including agent customization, LDAP/OIDC integration, build artifact retrieval, or troubleshooting Jenkins issues

基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill

Create, update, or review Picoclaw skills. Use when writing a new skill, modifying an existing SKILL.md, turning a repeated workflow into a reusable skill, or organizing scripts, references, and assets for a skill.

Use and extend alias analysis in LLVM 22. Covers querying AAResults from a function pass, using IR-level hints (noalias, TBAA) as the preferred approach, writing a custom AA analysis with the New Pass Manager, and common ModRef patterns.

Add DWARF debug info to an existing LLVM 22 IR frontend. Covers DIBuilder setup, compile unit, function subprograms, local variable declarations, source locations on instructions, and module flags.

Add a New Pass Manager (NPM) pass to an LLVM 22 in-tree or out-of-tree project. Covers FunctionPass, ModulePass, LoopPass, and CGSCCPass kinds, registration, pipeline wiring, CMake, and lit testing.

Interprets lab results, checks drug interactions, evaluates symptoms, and explains medical reports in plain language. Use when the user provides lab values, asks about medications, describes symptoms, or wants a medical report explained.

Configure GitHub settings, collaboration files, Actions, releases, and deployments. Use for setup or changes to those surfaces; excludes provider infrastructure and product code.

Generates access tokens, handles token refresh, and manages bearer authentication for external APIs in BC. Use when implementing OAuth Client Credentials flow, Authorization Code flow, or API authentication with token caching.

Real-time web search and structured local-business/Places search using PennyAPI over x402. Use for fresh web results, recent facts, current events, research, verification, fact checking, and for finding businesses, restaurants, stores, services, local leads, addresses, ratings, phone numbers, websites, and coordinates. Penny Lite costs $0.001 per search call; Premium Search and Places cost $0.004 per call on Base USDC.