发现 content media llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Use when implementing AI features in TypeScript/Next.js with Vercel AI SDK v6 (generateText/streamText, tools, structured output, streaming route handlers). Enforces v6 APIs and best practices; prevents halluci...
Send prompts to OpenAI Codex CLI and process the output. Use /codex to invoke Codex, then Claude analyzes, reviews, or integrates the results.
Guide for using LLM utilities in speedy_utils, including memoized OpenAI clients and chat format transformations.
Guide for creating new Agent Skills with proper structure, frontmatter, bundled assets, and validation. Includes templates, best practices, and examples for building reusable skill resources.
Senior Architect for @google/genai v1.35.0+. Specialist in Structured Intelligence, Context Caching, and Agentic Orchestration in 2026.
Senior Progress Analyst & Conductor Strategist. Expert in Predictive Project Tracking and Agentic Milestone Management for 2026.
Master Architect in Stagehand V3. Expert in Direct CDP Automation, Decision Caching, and Agentic Web Orchestration for 2026.
Senior AI Security Architect. Expert in Prompt Injection Defense, Zero-Trust Agentic Security, and Secure Server Actions for 2026.
Senior Orchestrator for Autonomous Missions. Expert in Manus API v2, Multi-Step Task Logic, and Secure Connectors (RSA-SHA256).
Master of Semantic Code Intelligence and Token Optimization, specialized in Context Engineering and Automated Context Packing (ACP).
This skill should be used when the user asks to "create a skill", "add a new skill", "write a skill", "make a skill", "skill template", "scaffold a skill", "skill directory structure", "SKILL.md format", "skill...
Setup and configure React Grab to let you click elements in your running app and send them directly to Claude Code for editing. Use when setting up React Grab, when the user wants to click UI elements to modify...
Google Cloud Vector Search 2.0 introduction and implementation guide
Agent Development Kit from Google
Write SKILL.md for the user using all available wisdom and documented guidance about how Agent Skills are made. New skills are written carefully to be orthogonal to the existing skills in the same repo.
Use when generating synthetic training data for multi-turn conversation fine-tuning. Triggers - have design artifacts ready, need to generate conversations, ready to assess quality. Requires finetune-design fir...
Use when training a fine-tuned model and evaluating improvement over base model. Triggers - have filtered training data, ready to submit training job, need to convert to GGUF. Requires finetune-generate first.
Use when preparing to fine-tune an LLM for multi-turn conversations, before generating any training data. Triggers - starting a fine-tuning project, need to define evaluation criteria, designing conversation da...
Coordinate Holo output formatting and telemetry so 0102, Qwen, and Gemma receive exactly what they need.
Generate YouTube Live stream content, consciousness responses, and engagement prompts. Use when creating stream announcements, chat responses, moderation messages, community engagement prompts, or emergency pro...
Qwen Cleanup Strategist (Prototype)
Qwen Roadmap Auditor (Prototype)
Moderate YouTube live chat by detecting spam, toxic content, and enforcing rate limits. PROTOTYPE for testing pattern fidelity before deploying to native Qwen/Gemma.
Qwen Training Data Miner (Prototype)
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。