GitHub
minion-sweep
PROACTIVELY USE when user asks to add docstrings/types across multiple files or a directory. Delegates bulk grunt work to local LLMs — saves cloud tokens. Two phases: discover, then apply. Use instead of manual...
Skills IA content media llm ai
Découvrez les skills content media llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: content media llm ai
content media llm ai Effacer les filtres
Explorer
GitHub
minion-setup
Verify Ollama is running and models are configured. Run to diagnose minion issues.
GitHub
minion-models
Manage Ollama models for minions. Pull new models, list available ones, switch presets, check disk usage. Use when setting up or changing models.
GitHub
web-browser-skill
AI-driven frontend development with live browser preview and visual verification. Use when building web UIs (dashboards, landing pages, web apps), when previewing/testing frontend code, when researching web des...
GitHub
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
GitHub
ios-speech-recognition
iOS Speech Framework integration for voice-to-text transcription. When to use: when implementing speech recognition, building dictation features, adding voice commands, converting audio to text, or working with...
GitHub
google-genai
Comprehensive toolkit for working with Google's Gemini API using the Google GenAI SDK. Use when Claude needs to: (1) Generate, summarize, or analyze text using Gemini models, (2) Process images, audio, or video...
GitHub
technical-writer
This skill should be used when the user asks to "write documentation", "create README", "document API", "add comments", "explain code", "generate docs", or requests documentation creation and maintenance. Use f...
GitHub
task-manager
This skill should be used when the user asks to "list tasks", "show all tasks", "compare versions", "switch to task X", "task status", "version history", "what tasks do I have", or needs to manage multiple trai...
GitHub
llm-knowledge
This skill should be used when the user asks "what is LoRA", "compare models", "which model is best for Chinese", "SFT vs DPO", "how to handle overfitting", "class imbalance solution", "model architecture", "tr...
GitHub
writing-plans
This skill should be used when the user asks to "write a plan", "create training plan", "plan my fine-tuning", "make a plan for model training", or when starting a new training task that requires multiple steps...
GitHub
llm-coach
This skill should be used when the user asks to "train a model", "fine-tune", "build NLP model", "create training task", "optimize model performance", "improve accuracy", "what model should I use", or expresses...
GitHub
data-pipeline
This skill should be used when the user asks to "configure data source", "data from database", "fetch data from API", "scrape web data", "generate training data with LLM", "regenerate data", "data pipeline", "w...
GitHub
finetune-llm
LLM fine-tuning 教練式引導工作流程 v2。 核心功能：主動探索使用者痛點、引導明確目標、多任務管理、資料來源追蹤、完整版本 lineage。 支援：LoRA/QLoRA/DoRA 微調、SFT/ORPO/DPO 對齊、資料準備、Benchmark 評估、HuggingF...
GitHub
self-review
タスク完了前のセルフレビュー。Gemini CLI + Claude subagent によるマルチ視点検証。
GitHub
token-efficiency
Token optimization best practices for cost-effective Claude Code usage. Automatically applies efficient file reading, command execution, and output handling strategies. Includes model selection guidance (Opus f...
GitHub
claude-skill-management
Expert guide for managing Claude Code global skills and commands. Use when creating new skills, symlinking to projects, updating existing skills, or organizing the centralized skill repository.
GitHub
daily-learning
Daily random learning assistant. Randomly picks topics from robot/coding/engineering/business/history/math, teaches with progressive depth, and quizzes on learned material using local cache.
GitHub
pattern-observer
Observes development patterns and suggests automations. Use when reviewing learnings, analyzing patterns, creating automations, or when asked about repeated tasks, workflow optimization, pending suggestions, or...
GitHub
agent-creator
Creates new specialist subagents based on detected tech stack or observed patterns. Use proactively during /claudenv to create agents for detected technologies, or when usage patterns suggest a new specialist i...
GitHub
orchestrator
Orchestrates complex tasks by automatically spawning specialist subagents in parallel. Use proactively when detecting complex multi-domain tasks, large refactors, comprehensive reviews, or when task complexity...
GitHub
deep-learning-study
Evidence-based learning and study skill for deep, durable understanding. Triggers when users want to learn or understand a topic, ask to be quizzed or tested, use phrases like "I'm studying [topic]", "help me l...
GitHub
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
GitHub
project-bootstrap
프로젝트용 AI 에이전트 팀 구조(.claude/agents/)를 자동 생성하고, 선택적으로 실제 프로젝트 환경까지 셋업. "에이전트 팀 만들어줘", "에이전트 팀 구성", "에이전트 팀 생성" 등 반드시 "에이전트 팀"이라는 키워드가 포...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.