Loading...
Loading...
Found 1,564 Skills
Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from a voice prompt plus preview text before using the returned voice_id in TTS.
Eino component selection, configuration, and usage. Use when a user needs to choose or configure a ChatModel, Embedding, Retriever, Indexer, Tool, Document loader/parser/transformer, Prompt template, or Callback handler. Covers all component interfaces and their implementations in eino-ext including OpenAI, Claude, Gemini, Ollama, Milvus, Elasticsearch, Redis, MCP tools, and more.
Intelligent long text novel reader with smart content filtering and detailed asset extraction. Invoke when user wants to read or analyze long novels. Automatically skips irrelevant content and extracts detailed character/item/scene information.
当用户的 PinMe 项目（Worker TypeScript）需要集成发送邮件（send_email）或调用大模型 API（chat/completions）时使用此技能。指导 AI 生成正确的 Worker TS 代码。
Provides rules for handling multi-language documentation. Use this when configuring agent skill documents using starlight-skills on an i18n-enabled project. Do not use this for standard single-language sites or plugin configuration options.
Create, improve, or optimize prompts using best practices
[QwenCloud] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, when an execution skill needs model selection advice, or user explicitly invokes this skill by name (e.g. use qwencloud-model-selector). DO NOT TRIGGER when: non-Qwen model discussions (OpenAI, Gemini, etc.), general AI questions unrelated to Qwen.
Ultra-compressed communication mode. Talk like a caveman to reduce token usage by about 75%. Full technical accuracy is maintained. Intensity levels: 3 tiers - Polite, Normal (default), Extreme. Activate by saying "Caveman Mode", "Shorten", "Be Concise", "Save Tokens", or using /genshijin.
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Comprehensive multi-perspective review using specialized judges with debate and consensus building
GANG validator skill. You are a validator, performing rule-based verification to check if the worker's handoff meets the val standards and issuing a verdict.
Builds robust, tool-specific prompts from user intent using a structured extraction and routing engine. Use when the user asks for prompt creation, prompt repair, prompt decomposition, or adapting prompts across Claude, GPT, reasoning models, Gemini, coding IDEs, autonomous agents, and image tools.