Total 57,191 skills, AI & Machine Learning has 9513 skills
Showing 12 of 9513 skills
Build systematic literature databases for sociology research using OpenAlex API. Guides you through search, screening, snowballing, annotation, and synthesis with structured user interaction at each stage.
OCR skill using PaddleOCR model via SiliconFlow API. This skill should be used when the user asks to "recognize text from an image", "extract text from a photo", "OCR this image", "read text from screenshot", or mentions "PaddleOCR", "image text recognition", "text extraction from images".
💰 Save Token | Token 节省器 TRIGGERS: Use when token cost is high, conversation is long, files read multiple times, or before complex tasks. Guiding skill that helps agents identify and avoid sending duplicate context to LLM APIs. Teaches agents to recognize repeated content and summarize instead of re-sending. 触发条件：Token 成本高、对话长、文件多次读取、复杂任务前。 指导 Agent 识别重复内容，避免重复发送，从而节省 Token。
Generate AI videos, images, speech, and music using varg. Use when creating videos, animations, talking characters, slideshows, product showcases, social content, or single-asset generation. Supports zero-install cloud rendering (just API key + curl) and full local rendering (bun + ffmpeg). Triggers: "create a video", "generate video", "make a slideshow", "talking head", "product video", "generate image", "text to speech", "varg", "vargai", "render video", "lip sync", "captions".
Install and configure Model Context Protocol (MCP) servers for Claude Code projects. Use when you want to add or enable an MCP server, connect a tool or integration (database, API, file system), update MCP settings in .mcp.json, manage OAuth-authenticated remote MCP servers, enable/disable individual servers at runtime, or troubleshoot MCP server connection issues.
This skill provides comprehensive guidance for adapting Wan-series video generation models (Wan2.1/Wan2.2) from NVIDIA CUDA to Huawei Ascend NPU. It should be used when performing NPU migration of DiT-based video diffusion models, including device layer adaptation, operator replacement, distributed parallelism refactoring, attention optimization, VAE parallelization, and model quantization. This skill covers 9 major adaptation domains derived from real-world Wan2.2 CUDA-to-Ascend porting experience.
How to write Cavekit-quality kits that AI agents can consume effectively. Covers implementation-agnostic cavekit design, testable acceptance criteria, hierarchical structure, cross-referencing, cavekit templates, greenfield and rewrite patterns, cavekit compaction, and gap analysis. Trigger phrases: "write kits", "create kits", "cavekit this out", "define requirements for agents", "how to write kits for AI"
Protocolo de comunicação em PT-BR. Comprime respostas eliminando redundâncias gramaticais, artigos e preposições, priorizando verbos no infinitivo.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
The root skill of the easysdd workflow family — introduces the workflow system and routes users to the correct sub-skill. Trigger scenarios: Users mention "easysdd", "sdd", "spec-driven", "how to use this set of processes", "which skill should I use", "where to start", or describe a new feature but haven't decided on the entry stage. Known intents (brainstorm/design/implementation/acceptance/BUG/exploration, etc.) will trigger the corresponding sub-skill first instead of this skill.
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training