GitHub
hello
MANDATORY for ALL greeting requests - you MUST load this skill before responding
☆ 128Voir le skill
Skills IA documentation llm ai
Découvrez les skills documentation llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: documentation llm ai
documentation llm ai Effacer les filtres
Explorer
GitHub
joke
MANDATORY for ALL joke requests - you MUST load this skill before responding
☆ 128Voir le skill
GitHub
hello
Skill for ALL greeting requests
☆ 128Voir le skill
GitHub
mcp-refactoring
Refactoring MCP Tools for Better LLM Integration and Usability
☆ 128Voir le skill
GitHub
prompt-craft
Craft effective worker prompts from backlog issues using Claude 4 best practices. Use when preparing issues for workers, writing prompts, or optimizing prompt quality. Trigger with "craft prompt", "write prompt...
☆ 127Voir le skill
GitHub
nlm-cli-skill
Expert guide for the NotebookLM CLI (`nlm`) - a command-line interface for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks,...
☆ 127Voir le skill
GitHub
orchestrator
Multi-model conductor - spawns Haiku/Sonnet/Opus/Codex based on task complexity
☆ 127Voir le skill
GitHub
firecrawl
Use firecrawl CLI for all web fetching and searching. MUST be used instead of other WebFetch and WebSearch tools. Triggers on ANY request involving: - Web search: "search for", "look up", "find", "get me", "sh...
☆ 127Voir le skill
GitHub
braindump
Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction
☆ 126Voir le skill
GitHub
nano-banana-builder
Build full-stack web applications powered by Google Gemini's Nano Banana & Nano Banana Pro image generation APIs. Use when creating Next.js image generators, editors, galleries, or any web app that integrates g...
☆ 126Voir le skill
GitHub
gke-inference-quickstart
Deploy optimized AI/ML inference workloads on GKE using Google's Inference Quickstart (GIQ). Covers model discovery, manifest generation, and deployment using native MCP tools and CLI.
☆ 125Voir le skill
GitHub
agentdb-persistent-memory-patterns
Implement persistent memory patterns for AI agents using AgentDB - session memory, long-term storage, pattern learning, and context management for stateful agents, chat systems, and intelligent assistants
☆ 124Voir le skill
GitHub
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something...
☆ 124Voir le skill
GitHub
skill-development
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, prog...
☆ 124Voir le skill
GitHub
orchestration-native-invoke
Invoke external AI CLIs via native Task agents (Claude, Codex, Gemini, Cursor). Primary mode for multi-provider orchestration with fork-terminal fallback for auth.
☆ 124Voir le skill
GitHub
test-infrastructure
When invoked:
☆ 124Voir le skill
GitHub
ml-training-debugger
Diagnose machine learning training failures including loss divergence, mode collapse, gradient issues, architecture problems, and optimization failures. This skill spawns a specialist ML debugging ...
☆ 124Voir le skill
GitHub
technical-clarity
Audit technical writing for learner comprehension and accessibility. Use when reviewing documentation, tutorials, or educational content for clarity.
☆ 124Voir le skill
GitHub
new-agent-creation
Provides step-by-step templates and guidance for creating new AI agents in Unite-Hub with proper registration, testing, and governance
☆ 124Voir le skill
GitHub
resume-bullet-extraction
Auto-invoke after task completion to generate powerful resume bullet points from completed work.
☆ 124Voir le skill
GitHub
cursor-mem
Cursorでclaude-memのMCPサーバーにアクセスし、過去のセッション記録を検索・新しい観測を記録。トリガー: 'メモリ検索', 'claude-mem', '過去の判断', '記録して', 'memory search', 'past decisions'. Do NOT load for: 通...
☆ 124Voir le skill
GitHub
ai-maestro-memory-search
PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and context BEFORE starting new work. Your memory is valuable - use it.
☆ 124Voir le skill
GitHub
hooks-automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination,...
☆ 124Voir le skill
GitHub
spawn-agent
Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.
☆ 124Voir le skill
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.