Total 56,945 skills, AI & Machine Learning has 9468 skills
Showing 12 of 9468 skills
Plans.mdのタスクを実装。スコープを聞いて自動判断、1タスクから全タスクまで。Use when user mentions '/work', execute plan, implement tasks, build features, work on tasks, 'do everything', 'implement', '実装して', '全部やって', 'ここだけ'. Do NOT load for: planning, reviews, setup, deployment, or breezing (team execution).
Guide VibeCoder (non-technical users) in natural language development. Use this when users ask what to do next, how to use the system, need help, or are stuck. Do NOT load this for: technical user work, direct implementation requests, or reviews.
Use when an existing agent already works without Prefactor and you need to add tracing for runs, llm calls, tool calls, and failures with minimal behavior changes.
One-click comprehensive analysis of cryptocurrencies. Collect data from five dimensions - price, news sentiment, sector comparison, market environment, and project fundamentals - through parallel sub-agents, and output an HTML report (including 24-hour market trends and 7-day trends) after cross-analysis. Trigger phrases: Analyze BTC, analyze ETH, How is Bitcoin?, Is SOL worth buying?
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when: building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
Build RAG systems and semantic search with Gemini embeddings (gemini-embedding-001). 768-3072 dimension vectors, 8 task types, Cloudflare Vectorize integration. Prevents 13 documented errors. Use when: vector search, RAG systems, semantic search, document clustering. Troubleshoot: dimension mismatch, normalization required, batch ordering bug, memory limits, wrong task type, rate limits (100 RPM).
Development skill from everything-claude-code
Comprehensive guide for BFL FLUX image generation models. Covers prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing, and model-specific best practices for FLUX.2 and FLUX.1 families.
BFL FLUX API integration guide covering endpoints, async polling patterns, rate limiting, error handling, webhooks, and regional endpoints with Python and TypeScript code examples.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.