Total 50,313 skills, AI & Machine Learning has 8452 skills
Showing 12 of 8452 skills
Context layer for data and analytics AI agents with semantic layer, skills, and memory via MCP
Fully offline speech-to-text via the Vosk library — streaming recognition, 16 kHz PCM, no network required after model download.
Build production-ready GenAI agents with stateful workflows, vector memory, deployment, and orchestration using LangGraph and LangChain
Router skill for LLMQuant macro workflows. Use when the user needs macro dashboards, Fed or central-bank previews, inflation and growth context, liquidity, or macro-to-portfolio impact analysis.
Router skill for LLMQuant options workflows. Use when the user needs IV rank, option scoring, strategy construction, Greeks, P&L simulation, volatility surface, unusual activity, earnings IV crush, backtests, or hedges.
Guidelines for creating well-structured AI agent skills. Use when building a new skill, reviewing skill quality, or unsure how to organize a skill.
Design and build multi-agent harness architectures for long-running AI application development. GAN-inspired Generator-Evaluator pattern, Sprint Contract negotiation, context management, quality criteria calibration. Based on Anthropic Engineering patterns. Use when: "build a harness", "multi-agent architecture", "agent orchestration", "generator-evaluator", "long-running app", "harness design", "agent pipeline", "quality evaluation loop", "sprint contract", "build app with agents", "Claude Agent SDK architecture", or when building complex full-stack apps that need planning → generation → evaluation cycles. Also use when discussing context degradation, self-evaluation bias, or assumption testing in AI workflows.
Build strong Codex Goals from rough user objectives. Use when the user asks to create, write, generate, improve, expand, or refine a Codex `/goal`; mentions Codex Goals, goal mode, persistent objectives, "持续执行", "扩充目标", "生成 goal", "keep working until", or wants Codex to ask clarifying questions before starting a long-running objective. Helps draft evidence-based goal text and may start a goal only after explicit user approval.
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.
Compact context, cache-aware execution, scoped evidence reads, and role-specific skill attachment discipline.
Source-first, self-loop resistant guardrails for Capy GitHub dialogue responders before any write-capable PR, issue, or review action.
Query papers using RAG (PaperQA2 or LEANN). Use when user needs synthesized answers from papers, asks "what does paper X say about Y", or needs cited responses.