Loading...
Loading...
Found 1,669 Skills
Command-line interface for Ollama - Local LLM inference and model management via Ollama REST API. Designed for AI agents and power users who need to manage models, generate text, chat, and create embeddings without a GUI.
Design patterns for the Langroid multi-agent LLM framework. Covers agent configuration, tools, task control, and integrations.
Lossless DFlash speculative decoding for MLX on Apple Silicon — 1.7–4x faster LLM inference using block diffusion drafting with target model verification.
Use Neo4j GenAI Plugin ai.text.* functions and procedures for in-Cypher embedding generation, text completion, structured output, chat, tokenization, and batch ingestion. Covers ai.text.embed(), ai.text.embedBatch(), ai.text.completion(), ai.text.structuredCompletion(), ai.text.aggregateCompletion(), ai.text.chat(), ai.text.tokenCount(), ai.text.chunkByTokenLimit(), and provider configuration for OpenAI, Azure OpenAI, VertexAI, and Amazon Bedrock. Requires CYPHER 25. Replaces deprecated genai.vector.encode(). Use when writing pure-Cypher GraphRAG, embedding nodes in-graph, generating structured maps from prompts, or calling LLMs inside Cypher queries. Does NOT handle neo4j-graphrag Python library pipelines — use neo4j-graphrag-skill. Does NOT handle vector index creation/search — use neo4j-vector-index-skill.
DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; add tracing or @observe; send results to Confident AI; monitor production; run online evals; inspect traces; or iterate on prompts, tools, retrieval, or agent behavior from eval failures. AI agents are the primary use case. Covers Python SDK, pytest eval suites, CLI generation, tracing, Confident AI reporting, and agent-driven improvement loops. DO NOT TRIGGER for unrelated generic pytest, non-AI test setup, or non-DeepEval observability work unless the user asks to compare or migrate to DeepEval.
Build typed LLM applications with PydanticAI: schema-constrained outputs, tool integration, validation, retries, and deterministic downstream handoffs. Use when users need reliable structured outputs instead of free-form text generation.
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.
HertzFlow on-chain trade-decision intelligence. Currently covers Binance Alpha forensic across all surf-SQL EVM chains (BSC / Ethereum / Arbitrum / Base / Polygon / Optimism) — insider distribution, 真实派发 confirmed sell-out, 筹码三分法 (operator / CEX pool / verifiable retail), anomaly waves, monitoring exports. Solana runs in HOLDER_SNAPSHOT mode. Auto-trigger whenever the user pastes a raw 0x-prefixed 40-hex EVM CA, a Solana base58 CA, mentions a Binance Alpha token by ticker, or asks about 链上 forensic / 内幕出货 / 派发 / chip structure / quiet insider / Alpha distribution / on-chain dump — even if they don't say "hertzflow" explicitly. Pipeline runs deterministically (~2-10 min per CA depending on activity + surf cache state); LLM only fills narrative slots, never picks the verdict or writes SQL. Perp metrics, bridge audits, and HertzFlow core contract analysis sub-domains are coming — when those ship, this skill will dispatch to them based on input pattern (perp symbol, bridge protocol name, etc.) using the router table below. REQUIRES a Surf account + SURF_API_KEY. New users get 2000 free credits (~6-8 reports) via the HertzFlow private invite. Full forensic costs ~$1.5-3 USD per CA in Surf credits after the free tier runs out.
Expert skill for prompt engineering and task routing/orchestration. Covers secure prompt construction, injection prevention, multi-step task orchestration, and LLM output validation for JARVIS AI assistant.
Instrument LLM applications with Langfuse tracing. Use when setting up Langfuse, adding observability to LLM calls, or auditing existing instrumentation.
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.
Expert skill for AI model quantization and optimization. Covers 4-bit/8-bit quantization, GGUF conversion, memory optimization, and quality-performance tradeoffs for deploying LLMs in resource-constrained JARVIS environments.