GitHub
telegram-integration
Set up, check status, or use the Telegram integration for Claude Code. Use this skill when the user mentions Telegram, wants to send messages to Telegram, check Telegram status, or troubleshoot Telegram connect...
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
dart-flutter-expert
Expert Flutter/Dart guidance. Use when working with Flutter projects, implementing BLoC/Riverpod patterns, writing Dart code, optimizing performance, or following Clean Architecture. Provides architecture patte...
GitHub
besm-design-npc
BESM 4e NPC/enemy generator. Mirrors the repo's `.claude/commands/design-npc.md`.
GitHub
restify-conversion
Orchestrate the conversion of Node.js Restify API services to Rust Dropshot API traits. Use this skill when migrating Node.js services to Rust. This orchestrator spawns separate sub-agents for each phase to man...
GitHub
chatgpt-oracle
Send prompts to ChatGPT Pro via Playwriter browser automation. Use for cross-validation, second opinions, or leveraging GPT-5.2 Pro's research-grade intelligence.
GitHub
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx file...
GitHub
ralph-loop
Ralph Loop autonomous iteration plugin - enables self-referential development loops with multi-ralph support. Forked from ralph-loop@claude-plugins-official for persistence.
GitHub
skill-manager
Manages the dynamic skill learning system. Use when you want to list skills, scan transcripts for patterns, learn preferences, approve/reject candidates, rollback versions, view skill history, or check usage st...
GitHub
claude-sdk
Use the Anthropic Claude SDK for programmatic API access. Enables spawning sub-agents, parallel processing, batch operations, and custom Claude interactions via Python. Use when tasks need multiple Claude insta...
GitHub
ralph-invoke
Allows Claude to directly start Ralph-Wiggum autonomous loops without user commands. Use when user asks to "start a ralph loop", "run ralph", wants autonomous iteration, says "keep working until done", or when...
GitHub
nanobanana
Use when "nanobanana", "generate image", "create image", "edit image", "AI drawing", "Gemini image", "image generation"
GitHub
vector-databases
Use when "vector database", "embedding storage", "similarity search", "semantic search", "Chroma", "ChromaDB", "FAISS", "Qdrant", "RAG retrieval", "k-NN search", "vector index", "HNSW", "IVF"
GitHub
langchain-agents
Use when "LangChain", "LLM chains", "ReAct agents", "tool calling", or asking about "RAG pipelines", "conversation memory", "document QA", "agent tools", "LangSmith"
GitHub
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx file...
GitHub
llm-inference
Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU i...
GitHub
git-workflows
This skill should be used when the user asks to "create a commit", "write commit message", "create a pull request", "generate changelog", "manage branches", "git workflow", "merge strategy", "PR description", o...
GitHub
context-optimization
Use when optimizing agent context, reducing token costs, implementing KV-cache optimization, or asking about "context optimization", "token reduction", "context limits", "observation masking", "context budgetin...
GitHub
using-ltk
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
GitHub
memory-systems
Use when implementing agent memory, persisting state across sessions, building knowledge graphs, tracking entities, or asking about "agent memory", "knowledge graph", "entity memory", "vector stores", "temporal...
GitHub
agent-evaluation
Use when evaluating agent performance, building test frameworks, measuring quality, or asking about "agent evaluation", "LLM-as-judge", "agent testing", "quality metrics", "evaluation rubrics", "agent benchmark...
GitHub
dspy-prompting
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "few-shot le...
GitHub
context-degradation
Use when diagnosing agent failures, debugging lost-in-middle issues, understanding context poisoning, or asking about "context degradation", "lost in middle", "context poisoning", "attention patterns", "context...
GitHub
branding
This skill should be used when the user asks about "branding", "brand identity", "logo design", "color palette", "brand guidelines", "visual identity", "brand voice", "style guide", or mentions brand-related de...
GitHub
huggingface-tokenizers
Use when "tokenizers", "HuggingFace tokenizer", "BPE", "WordPiece", or asking about "train tokenizer", "custom vocabulary", "tokenization", "subword", "fast tokenizer", "encode text"
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.