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 starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWri...
Generate AI content (images, videos, audio, avatars) and analyze videos with detailed timelines using YAML pipelines with 51 models across 8 categories. Includes video analysis with Gemini 3 Pro.
Manage AI notes in ~/Compost/AI-Notes - read existing notes, list recent documents, and write new implementation plans (仕様書, 計画書, 設計書). Auto-triggers when reading from or writing to notes, specificatio...
Comprehensive guide to implementing RAG systems including vector database selection, chunking strategies, embedding models, and retrieval optimization. Use when building RAG systems, implementing semantic searc...
LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systema...
Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs, implementing NLP ta...
Document solved problems for knowledge persistence
Resume context from previous session
REST API specialist for Rails applications. Use when building API endpoints, implementing serialization, API versioning, JWT authentication, or creating API documentation. Focuses on RESTful design, performance...
FAQ identification from support tickets, step-by-step tutorial creation, screenshot/video script guidance, search optimization, and self-service deflection tracking.
Maintain project state across MULTIPLE conversations over days/weeks. Track tasks, decisions, blockers, resources. Auto-update when project mentioned. Generate status reports and proactive reminders.
Convert webinar recordings into blog posts, social snippets, email series. Extract key quotes, statistics, and soundbites.
Mine ALL past Claude conversations to build a living 'User Manual About You'. Extract writing style, business context, goals, preferences, and patterns. Make all other skills smarter with context.
CHAIN multiple existing skills into custom multi-step workflows. Programmable skill combinations with automatic handoffs. Create composite skills from building blocks with conditional logic.
Optimize job applications by tailoring resumes to job postings, generating customized cover letters, and preparing role-specific interview questions. Analyzes job descriptions to highlight relevant skills and e...
Analyze pipeline health, identify stalled deals, predict close probability, and suggest actions to move deals forward. Improves forecast accuracy and prevents revenue leakage. Use when deals get stuck or foreca...
Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.
Transform text-heavy slides into visual storytelling. Suggest layout improvements, icon usage, and data visualization.
Analyze meeting transcripts to extract decisions, action items, blockers, sentiment, and generate follow-up emails. Use when user provides meeting notes, transcripts, or recordings and needs structured summarie...
Score deal velocity based on email response times, meeting frequency, and stakeholder engagement. Predict which deals will close vs stall.
Master user interviews, usability testing, surveys, and research synthesis. Use when planning research, gathering user insights, or validating assumptions.
Search and retrieve data from local Weaviate using semantic search, filters, RAG, and hybrid queries
Create clever, non-offensive trash talk. Rivalry-specific references, historical callbacks, memes. Fun, not mean.
Generate realistic coach/player interview responses for wins, losses, controversies, injuries. Authentic coachspeak and player personalities.
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。