GitHub
context-elicitation
For complex problems where user context is insufficient, systematically elicit information through adaptive prompt patterns. Combines five complementary patterns (Flipped Interaction, Cognitive Verifier, Questi...
Skills IA research llm ai
Découvrez les skills research llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: research llm ai
research llm ai Effacer les filtres
Explorer
GitHub
context-management
Manages personal knowledge about the user through Basic Memory. Use this skill when: (1) User requests to search/retrieve past information, (2) User requests to record/save information, or (3) Important insight...
GitHub
create-command
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command w...
GitHub
create-skill
Guide for creating effective skills. Use when users want to create a new skill, update an existing skill, or need help with SKILL.md files, frontmatter fields, skill structure, naming conventions, or skill deve...
GitHub
create-mcp
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
GitHub
prompt-engineering
Use this skill when you are writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt...
GitHub
task-to-knowledge
Extract learnings from completed tasks and create knowledge notes. Use when user says "make this knowledge", "extract learnings", "save what I learned", or wants to convert task insights to permanent notes.
GitHub
ralph-autonomous
Autonomous coding patterns for unattended feature implementation using Ralph loop runner. Use when running Ralph autonomous loop, implementing features without supervision, handling long-running agent sessions,...
GitHub
skill-creator
Guide for creating effective Agent Skills during Spec Kit planning. Use when users want to create a new skill, update an existing skill, or when running /speckit.specify to create tech-stack-specific skills. Ex...
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...
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。
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.