majiayu000/claude-skill-registry - Página 20

gemini-specialist

Use Gemini CLI for massive context tasks (1M-2M tokens). Orchestrator evaluates safety and directs usage patterns intelligently.

Idioma do texto original: inglês

gemini-text

Generate text content using Google Gemini models via scripts/. Use for text generation, multimodal prompts with images, thinking mode for complex reasoning, JSON-formatted outputs, and Google Search grounding for real-time information. Triggers on "generate…

Idioma do texto original: inglês

gemini-tools

Execute and manage Gemini CLI built-in tools including file operations, web search, shell commands, and memory. Use for automated workflows, tool orchestration, and safe execution patterns.

Idioma do texto original: inglês

gemini-video

Invoke Google Gemini for video understanding and analysis using the Python google-genai SDK. Supports gemini-3-pro-preview and gemini-2.5-flash for video analysis, transcription, and content extraction.

Idioma do texto original: inglês

gemini

Run Google Gemini CLI as a subagent for second opinions, code reviews, and questions. Use when you want a different AI model's perspective.

Idioma do texto original: inglês

genai-image

Generate images using Google GenAI Nano Banana Pro model via CLI. Use when the user asks to create images, generate pictures, make AI art, do image-to-image transformations, place people in scenes, or create character variations.

Idioma do texto original: inglês

genai-text

Generate text using Google GenAI Gemini models via CLI. Use when the user asks to generate text, get AI responses, create content, write with AI, or use Gemini for text completion.

Idioma do texto original: inglês

genai-video

Generate videos using Google GenAI Veo 3.1 model via CLI. Use when the user asks to create videos, generate animations, make AI video content, do image-to-video transformations, interpolate between frames, or create cinematic shots with camera movement.

Idioma do texto original: inglês

ggg

Smart context filter - reduce tokens 50-90% before sending to Claude. Use when reading large files (>1000 lines), analyzing complex codebases, or when user types 'ggg'. Saves ~69% cost per task.

Idioma do texto original: inglês

google-gemini-api

Google Gemini API with @google/genai SDK. Use for multimodal AI, thinking mode, function calling, or encountering SDK deprecation warnings, context errors, multimodal format errors.

Idioma do texto original: inglês

google-gemini-embeddings

Google Gemini embeddings API (gemini-embedding-001) for RAG and semantic search. Use for vector search, Vectorize integration, or encountering dimension mismatches, rate limits, text truncation.

Idioma do texto original: inglês

google-search

Integration patterns for web search grounding, including query operator usage, API-based search orchestration, and citation metadata mapping. Triggers: google-search, grounding, search-api, citations, search-operators, web-search.

Idioma do texto original: inglês

gorilla

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls) api-router, python, api, api-documentation, chatgpt, claude-api, gpt-4-api. Use when you need api-router capabilities. Triggers on: api-router.

Idioma do texto original: inglês

confidence-scorer

Truth-verification engine for Epsilon Prime. Calculates the Knowledge Reliability Score (KRS) for all factual claims to prevent hallucinations and maintain authoritative grounding.

Idioma do texto original: inglês

gpt-image-skill

Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Triggers: "gpt image", "openai image", "generate image with openai", "draw image", "create image", "image generation", "AI drawing", "图片生成", "AI绘图", "生成图片", "画图". Use this…

Idioma do texto original: inglês

grok-oracle

Deep reasoning oracle leveraging Grok's 2M context window. Dump massive context, get deep synthesis. Collision: context-engineering x pattern-synthesis x perspective-aggregation.

Idioma do texto original: inglês

grok-search

Enhanced web search and real-time content retrieval via Grok API with forced tool routing. Use when: (1) Web search / information retrieval / fact-checking, (2) Webpage content extraction / URL parsing, (3) Breaking knowledge cutoff limits for current…

Idioma do texto original: inglês

groq-inference

Fast LLM inference with Groq API - chat, vision, audio STT/TTS, tool use. Use when: groq, fast inference, low latency, whisper, PlayAI TTS, Llama, vision API, tool calling, voice agents, real-time AI.

Idioma do texto original: inglês

hybrid-search-implementation

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Idioma do texto original: inglês

hyde-retrieval

HyDE (Hypothetical Document Embeddings) for improved semantic retrieval. Use when queries don't match document vocabulary, retrieval quality is poor, or implementing advanced RAG patterns.

Idioma do texto original: inglês

image

Generate and edit images using AI models via OpenRouter. Supports Nano Banana Pro (Gemini 3 Pro Image), FLUX, and other image generation models.

Idioma do texto original: inglês

image-gen

图片生成, 架构图, 流程图, 时序图, 泳道图, diagram, architecture, flowchart, sequence, swimlane, image generation, nano banana, 生图, 画图, 画一个, 生成图片, generate image, draw diagram

Idioma do texto original: chinês

image-gen

图片生成, 架构图, 流程图, 时序图, 泳道图, diagram, architecture, flowchart, sequence, swimlane, image generation, nano banana, 生图, 画图, 画一个, 生成图片, generate image, draw diagram

Idioma do texto original: chinês

image-gen

AI 图片生成。通过 ModelScope API 生成图片，支持文生图、异步任务轮询、LoRA 风格叠加、自定义尺寸。当用户要求生成图片、画图、创建插画、制作海报配图时使用。

Idioma do texto original: chinês

image-generation

Generate images from text prompts using Ollama.

Idioma do texto original: inglês

image-generation

Generates professional AI images using Google Gemini. ALWAYS invoke this skill when building websites, landing pages, slide decks, presentations, or any task needing visual content. Invoke IMMEDIATELY when you detect image needs - don't wait for the user to…

Idioma do texto original: inglês

image-generation

Generate or edit images with Gemini Pro. Use when user says "generate an image", "create a picture", "make me a logo", "edit this image", "remove the background", "change the style", "combine these images", "add text to image", "style transfer", "make a…

Idioma do texto original: inglês

image-generation

AI-powered image generation and editing using Gemini. Use when Claude needs to: (1) Generate images from text descriptions, (2) Edit existing images with instructions, (3) Create infographics or charts, (4) Generate visual assets for reports/presentations,…

Idioma do texto original: inglês

image-generation

Generate AI image prompts for website assets using Imagen (infographics, diagrams, icons, maps).

Idioma do texto original: inglês

image-generator

Generate professional visuals using Gemini via browser automation with 6-gate quality control. Use when creating chapter illustrations, diagrams, or teaching visuals. NOT for stock photos or decorative images.

Idioma do texto original: inglês

image-mining

I mine pixels for atoms. Reality is just compressed resources.

Idioma do texto original: inglês

image-nano-banana

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

Idioma do texto original: inglês

image-openai

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Idioma do texto original: inglês

improve-conversation

Analyze conversations to identify improvements for prompts, instructions, skills, or workflows. Use when something went wrong, behavior didn't match expectations, you want to improve AI interactions, or when the user says "improve", "improve chat", or…

Idioma do texto original: inglês

instruction-engineering

Use when crafting, improving, or reviewing prompts, system prompts, skill instructions, or any text that instructs an LLM. Triggers: 'write a prompt', 'prompt engineering', 'improve this prompt', 'design a system prompt', 'write skill instructions', 'craft…

Idioma do texto original: inglês

instruction-engineering

Use when: (1) constructing prompts for subagents, (2) invoking the Task tool, or (3) writing/improving skill instructions or any LLM prompts

Idioma do texto original: inglês

instruction-improver

Search memex for user feedback patterns (frustration, corrections, praise, successful outcomes) to identify recurring mistakes and wins, then generate CLAUDE.md or AGENTS.md improvements.

Idioma do texto original: inglês

instruction-optimizer

Use when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability. Triggers: "optimize instructions", "reduce tokens", "compress skill", "make this shorter", "too verbose".

Idioma do texto original: inglês

instructor

Structured outputs with Instructor. Extract typed data from LLMs using Pydantic models and validation. Use for data extraction, structured generation, and type-safe LLM responses.

Idioma do texto original: inglês

invoking-gemini

Invokes Google Gemini models for structured outputs, multi-modal tasks, and Google-specific features. Use when users request Gemini, structured JSON output, Google API integration, or cost-effective parallel processing.

Idioma do texto original: inglês