Results for “ilm”

Fetches current weather data for Belgian locations using the KMI/IRM meteo.be API.

Query Belgian weather data from the KMI/IRM meteo.be API, including current conditions, forecasts, radar, warnings, and UV index for Belgian locations.

Computes the InfoLM metric from torchmetrics for evaluating text generation against ground truth, with configurable information measures and sentence-level scoring.

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送交互卡片（Interactive Card）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、发送交互卡片时使用。

Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员时使用。

Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and interactive modes with model selection, config persistence, and file input handling.

Builds RAG and agent applications with LlamaIndex, covering installation, LlamaParse, and LlamaAgents.

Guides machine learning development with experiment tracking, hyperparameter optimization, model registry, and MLOps pipeline integration.

Idefics2: An 8B Parameters Multimodal Model

统一的 IMA OpenAPI 技能，支持笔记管理和知识库操作。 当用户提到知识库、资料库、笔记、备忘录、记事，或者想要上传文件、添加网页到知识库、 搜索知识库内容、搜索/浏览/创建/编辑笔记时，使用此 skill。 即使用户没有明确说"知识库"或"笔记"，只要意图涉及文件上传到知识库、网页收藏、 知识搜索、个人文档存取（如"帮我记一下"、"搜一下知识库里有没有XX"），也应触发此 skill。

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件（支持大文件分片下载）、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。

Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.

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

ML / research person pack for Content Factory. Use when the user says person ml, @person-ml, ML person, research scientist person, or LLM researcher person. Auto-loads ml-research-engineer, llm-researcher, ai-research-scientist plus experiment-tracking, evaluation, cf-llm-model-usage.

Call 100+ LLMs through a single OpenAI-compatible interface with LiteLLM — use completion/acompletion/embedding with any provider (Anthropic, OpenAI, Google, Groq, Ollama, etc.), run a proxy server for team rate-limiting and cost tracking, load-balance across providers.

Operates AI infrastructure as a production dependency: manages GPU utilization, MCP servers, LLM gateways, inference pipelines, token costs, semantic caching, and model observability.

Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness

Use when extracting per-position residue-height and indel-rate data from a profile HMM for sequence-logo visualization.

LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)

Generates ultra-minimalist, editorial-style web interfaces with warm monochrome palettes, typographic contrast, bento-grid layouts, and muted pastel accents, rejecting generic SaaS design trends.

Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian vault or git-tracked notes repo. Use when raw sources such as web articles, papers, meeting notes, transcripts, screenshots, or past analyses need to be turned into an interlinked knowledge base with immutable source files, LLM-written wiki pages, `index.md`, `log.md`, schema rules in `AGENTS.md` or `CLAUDE.md`, source summaries, query notes, and recurring lint passes. Triggers on: llm-wiki, personal wiki, obsidian wiki, research vault, knowledge base, source ingest, persistent notes, wiki maintenance, source summaries, query filing.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Build web interfaces that fuse Swiss typographic design with military terminal aesthetics, using rigid grids, extreme type scale contrast, utilitarian color, and analog degradation effects for data-heavy dashboards, portfolios, or editorial sites.

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Rebuild Knowledge Vault index.md from disk truth per capture-llm-wiki schema. Use when vault structure drifted or after bulk ingest of pursuit folders. Karpathy LLM wiki maintenance skill.

LaCLIP: Improving CLIP Training with Language Rewrites

Configures Flutter app internationalization with ARB files, dynamic locale switching, and date/number formatting.

Designs an edit blueprint and uncertainty register for video projects, following a narrative loop and schema constraints.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Complete user guide for the IoM (Implant-over-Middleware) C2 framework. Covers architecture concepts, basic operations, startup parameters, authentication configuration, troubleshooting, documentation resources, and community feedback. Trigger conditions: use this skill when the user asks about how IoM works, command usage, architecture concepts, configuration methods, how to troubleshoot issues, where to find documentation, or how to file an issue. Should also trigger for questions like "how do I connect", "what is a session", "I got an error", or "is there documentation".

Establishes a three-layer knowledge distillation architecture for an Obsidian-based wiki, defining categories, projects, page templates, and operational workflows for maintaining a persistent knowledge base.

Compute aerospace environment properties including atmosphere (ISA, COESA, NRLMSISE-00, non-standard, CIRA), gravity (spherical harmonic, WGS84, zonal, centrifugal), horizontal wind (HWM), magnetic field (WMM, IGRF), geoid height, geocentric radius, space weather data, planetary ephemeris, Earth orientation (polar motion, nutation, delta-UT1, CIP). Use when computing atmospheric density, temperature, pressure, gravity vectors, wind profiles, magnetic field components, geoid undulation, solar flux indices, planet positions, or Earth orientation parameters for aerospace vehicle analysis, spacecraft environment modeling, or navigation corrections.