Skip to content
anyai.fyi

Skills for “llm”

60 skills match · 187 ms · understood as category: Chatbots & Assistants

Also searched as: language, model, chatbot

Skill neon neondatabase/agent-skills

…here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase…

Data & Databases 266k installs curated Worth a look
Match 2.6
Skill caveman-discover juliusbrussee/caveman

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

Agents & Workflows 126k installs No risky patterns found
Match 2.5
Skill caveman-setup juliusbrussee/caveman

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

DevOps & Cloud 125k installs Worth a look
Match 2.5
Skill claude-api anthropics/skills

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it…

Agents & Workflows curated Worth a look
Match 2.4
Skill migrating-ai-sdk-to-common-ai astronomer/agents

…with the official Airflow AI provider - migrating LLM decorators (@task.llm, @task.agent, @task.llm_branch, @task.embed), switching from model strings/objects to connection-based LLM configuration, updating…

Development curated Worth a look
Match 2.4
Skill architect-for-startups aws/agent-toolkit-for-aws

…before it ships (cost-regression-check), self-hosted LLM batch inference (self-hosted-llm-batch-inference), or migration intent (`gcp-to-aws`, `azure-to-aws`, `heroku-to-aws`,…

Development curated No risky patterns found
Match 2.4
Skill tao-finetune-huggingface-model NVIDIA/skills

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the user wants to fine-tune a HuggingFace model (full or LoRA),…

Agents & Workflows curated Worth a look
Match 2.4
Skill neon-ai-gateway neondatabase/agent-skills

One API and one credential for frontier and open-source LLMs and embedding models, built into your Neon branch and powered by Databricks. Use when a user wants to call an LLM, generate embeddings, add AI/chat/an agent…

Development curated Worth a look
Match 2.4
Skill domino-genai-tracing dominodatalab/domino-claude-plugin

Trace and evaluate GenAI applications (LLM calls, agents, RAG pipelines, multi-step AI systems) in Domino with the Domino agents SDK, using the @add_tracing decorator, span and trace evaluators, DominoAgentContext /…

Agents & Workflows curated No risky patterns found
Match 2.4
Skill add-lens redis/agent-skills

…so every agent turn is one trace in the Lens UI with its LLM calls, tokens, tool calls, memory and document retrievals, and which of them entered the prompt. Detects how the agent runs (LangGraph or ADK attach,…

Agents & Workflows curated Worth a look
Match 2.4
Skill redis-semantic-cache redis/agent-skills

Redis LangCache guidance for semantic caching of LLM responses on Redis Cloud — calling search/set via the SDK or REST API, tuning the similarity threshold, separating caches per task type, and filtering with custom…

Development curated No risky patterns found
Match 2.4
Skill serving-llms-on-epyc amd/skills

Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda. Use for "vLLM on CPU", "zentorch serving", or an EPYC CPU endpoint, including on a host that also has AMD Instinct…

DevOps & Cloud curated No risky patterns found
Match 2.1
Skill azure-aigateway microsoft/azure-skills

Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add…

Development 714k installs curated No risky patterns found
Match 2.0
Skill google-agents-cli-eval google/agents-cli

…the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code…

Agents & Workflows 575k installs Worth a look
Match 2.0
Skill airunway-aks-setup microsoft/azure-skills

Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster",…

DevOps & Cloud 508k installs curated No risky patterns found
Match 2.0
Skill neon-postgres neondatabase/agent-skills

…or search. New backends, Auth, files, Functions, and LLM calls go to the parent `neon` skill. Live queries, reactive UIs, and realtime data go to `neon-realtime`. Also use for "@neondatabase/serverless",…

Data & Databases 313k installs curated Worth a look
Match 2.0
Skill caveman-evidence-review juliusbrussee/caveman

Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.

Development 126k installs No risky patterns found
Match 1.9
Skill typesafe-ai typesafe-ai/skills

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building,…

Development 101k installs No risky patterns found
Match 1.9
Skill cost-cutter milad-ahmd/agent-skills

…Vercel, Netlify, Supabase, Firebase, OpenAI and other LLM APIs, databases, CDNs) by analyzing billing exports and infrastructure code, then ranks savings by dollars and effort with exact fixes and risks. Use when…

DevOps & Cloud No risky patterns found
Match 1.8
Skill durable-agent-workflows milad-ahmd/agent-skills

…of re-running and re-paying for steps 1 to 36. Wraps each model call, tool call and side effect in a journaled step (ctx.step, ctx.llm), moves time, randomness and network reads behind ctx so replays match, puts…

Development No risky patterns found
Match 1.8