GitHub
model-switcher
タスクの複雑さに応じて Claude のモデルを自動的に切り替える。複雑なタスク（アーキテクチャ設計、大規模リファクタリング、難解なバグ修正）では opus を、単純なタスク（小さな修正、フォーマット、簡単な質問）では sonne...
Skills IA testing security llm ai
Découvrez les skills testing security llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: testing security llm ai
testing security llm ai Effacer les filtres
Explorer
GitHub
subagent-creator
プラグインに新しいサブエージェントを作成する。「サブエージェント作成」「新しいエージェント」「エージェントを作って」「エージェント追加」「subagent 作成」「エージェントを追加したい」「新規エージェント」などで起...
GitHub
stacks-agent
AI-powered intelligence for building Stacks blockchain applications with 40 production code examples
GitHub
nanobanana
Generate and edit images using Google Gemini or OpenAI GPT Image models. Automatically used for requests like "generate an image", "create an illustration", "edit this image". Also supports sticker sheet genera...
GitHub
gemini
Use Google Gemini API for text generation, multimodal analysis, image generation (Nano Banana), function calling, and search grounding. Invoke when user wants to use Gemini, ask Gemini, generate images with Gem...
GitHub
multi-perspective-analysis
Analyze propositions from multiple expert perspectives. Dynamically generates 4-6 relevant expert roles, then performs validation, comprehensive analysis, or debate-style examination. Use when user wants to exa...
GitHub
gemini-embed
Generate text embeddings using Google Gemini API for RAG, semantic similarity, classification, and clustering tasks. Invoke when user wants to embed text, create embeddings, or convert text to vectors with Gemi...
GitHub
using-openai-platform
OpenAI SDK development with GPT-5 family, Chat Completions, Responses API, embeddings, and tool calling. Use for AI-powered applications, chatbots, agents, and semantic search.
GitHub
building-langgraph-agents
LangGraph development for stateful multi-agent applications, cyclic workflows, conditional routing, human-in-the-loop patterns, and persistent state management. Use for complex AI orchestration, agent coordinat...
GitHub
using-weaviate
Weaviate vector database for semantic search, hybrid queries, and AI-native applications. Use for embeddings storage, similarity search, RAG pipelines, and multi-modal retrieval.
GitHub
using-anthropic-platform
Claude SDK development with Messages API, Tool Use, Extended Thinking, streaming, and prompt caching
GitHub
using-perplexity-platform
Perplexity Sonar API development with search-augmented generation, real-time web search, citations, and OpenAI-compatible Chat Completions. Use for AI-powered applications requiring up-to-date information, rese...
GitHub
session-management
Git-native session lifecycle management for software development. Use when starting/resuming coding sessions, creating checkpoints, tracking objectives and blockers, generating handoffs between sessions, or nee...
GitHub
claude-context-manager
Enables autonomous context management for codebases through claude.md files. Use when creating, maintaining, or synchronizing AI agent context. Provides tools and workflows for monitoring context health, detect...
GitHub
memory-checkpoint
Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. Triggers: CP, checkpoint, save, 存檔, 記一下, 保存, sync memory, dump, 先記著, 等一下, 要離開, 暫停, pause,...
GitHub
mcp-client-builder
Build production-ready MCP clients in TypeScript or Python. Handles connection lifecycle, transport abstraction, tool orchestration, security, and error handling. Use for integrating LLM applications with MCP s...
GitHub
coding-workflow
Use when user asks to build a feature, implement something new, or make significant code changes. Recognizes requests like "build", "implement", "create a new feature", "add functionality", "develop", "I need t...
GitHub
chain-of-thought
INVOKE for debugging and step-by-step problem solving. Produces visible reasoning trace with each step shown. Use when tracing logic, explaining reasoning, or debugging issues. Triggers: debugging, tracing exec...
GitHub
implementation-planning
Create detailed implementation plans through interactive research. Use when in plan mode or when creating technical specifications.
GitHub
program-of-thoughts
INVOKE for calculations and data processing. Produces executable code instead of mental math. Use when precision matters or numbers are complex. Triggers: calculations, numerical analysis, data transformations,...
GitHub
self-consistency
INVOKE for verification and high-stakes decisions. Produces multiple independent reasoning paths with consensus check. Use before finalizing critical work. Triggers: verification, double-checking, validating ap...
GitHub
atomic-thought
INVOKE for research tasks and multi-source understanding. Produces visible dependency graphs and contracted answers. Use during research phase of workflow. Triggers: researching topics, gathering information be...
GitHub
tree-of-thoughts
INVOKE when multiple approaches exist and exploration is valuable. Produces visible branching with evaluation and recommendation. Use before implementation when comparing options. Triggers: comparing approaches...
GitHub
chat-etiquette
Message formatting conventions and channel routing for agent-chat coordination
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.