GitHub
terminal
Execute shell commands in persistent, stateful VT100 terminal sessions. WHEN: User needs to "run a command", "execute shell", "build project", "run tests", "deploy", system administration. WHEN NOT: Simple file...
Skills IA Données et IA
Découvrez les skills Données et IA, comparez leurs dépôts et consultez leurs instructions.
Catégories: Données et IA
Données et IA Effacer les filtres
Explorer
GitHub
memory
Memory system with three MCP tools: mcp__plugin_kg_kodegen__memory_list_libraries (discover namespaces), mcp__plugin_kg_kodegen__memory_memorize (store with embeddings), mcp__plugin_kg_kodegen__memory_recall (s...
GitHub
reasoner
Advanced reasoning with search strategies (beam search, MCTS). WHEN: Complex problem-solving requiring exploration of multiple solution paths, optimization problems, decision trees, when you need scored/ranked...
GitHub
web-search
Perform DuckDuckGo web searches and return structured results. WHEN: User wants to "search the web", "find information online", "look up", "research topic". WHEN NOT: Know exact URL (use browser_navigate), craw...
GitHub
sequential-thinking
Step-by-step reasoning tool with revision and branching support. WHEN: Complex problem-solving requiring structured thinking, multi-step analysis, planning with room for revision, exploring alternatives. WHEN N...
GitHub
xstate
Expert guidance for XState state machines, actor model patterns, React integration, and statecharts. Use when implementing state machines, managing complex application state, using the actor model for concurren...
GitHub
hn-filter
Filter and analyze Hacker News top stories based on user interests. Use when the user wants to browse, filter, or get personalized Hacker News content, find interesting tech articles, or get a curated digest of...
GitHub
qdrant-pdf-reloader
Surgically reloads a single PDF to Qdrant by deleting old chunks and re-uploading with fixes. Use when user wants to reload, refresh, fix, or update a specific PDF without reloading the entire collection.
GitHub
qdrant-doc-deleter
Deletes specific PDF documents from Qdrant vector database collection. Use when user wants to remove, delete, or clean up PDF documents from the vector database, Qdrant collection, or needs to manage document v...
GitHub
qdrant-chunk-retriever
Retrieves and inspects chunks from specific PDF documents in Qdrant vector database. Use when user wants to view, inspect, debug, or examine chunks from a particular file, check chunk content, or investigate ch...
GitHub
qdrant-file-exporter
Extracts all chunks with three-tier contextual embeddings from a specific PDF file in Qdrant vector database and saves to plain text. Use when user wants to extract, export, dump, or view all chunks from a PDF...
GitHub
root-calculator
Performs mathematical root calculations including square root, cube root, and nth roots. Use when user asks to calculate square root, cube root, nth root, or uses keywords like 'sqrt', 'root of', 'calculate roo...
GitHub
pytorch-cuda
PyTorch CUDA environment and performance guidance, with emphasis on CUDA 13 toolkit/driver requirements, PyTorch wheel compatibility, and runtime checks. Use when configuring PyTorch on NVIDIA GPUs, debugging C...
GitHub
docker-compose
Multi-service orchestration with Docker Compose, focusing on network isolation, environment-specific profiles, and service discovery. Triggers: docker-compose, container-networking, docker-profiles, service-dis...
GitHub
llamaindex-wolfram-alpha
LlamaIndex Wolfram Alpha tool for computational knowledge queries, math solving, scientific calculations, and agent integration. Triggers: wolfram alpha, computational query, math solver, scientific calculation...
GitHub
numpy-datetime
Date and time handling with datetime64 and timedelta64, including business day offsets and naive time parsing. Triggers: datetime64, timedelta64, busday, time series, naive time.
GitHub
torchtext
Natural Language Processing utilities for PyTorch (Legacy). Includes tokenizers, vocabulary building, and DataPipe-based dataset handling for text processing pipelines. (torchtext, tokenizer, vocab, datapipe, r...
GitHub
numpy-polynomial
Modern polynomial API for fitting, root finding, and working with orthogonal series like Chebyshev and Legendre. Triggers: polynomial, polyfit, Chebyshev, Legendre, root finding.
GitHub
torchaudio
Audio signal processing library for PyTorch. Covers feature extraction (spectrograms, mel-scale), waveform manipulation, and GPU-accelerated data augmentation techniques. (torchaudio, melscale, spectrogram, pit...
GitHub
torchserve
Model serving engine for PyTorch. Focuses on MAR packaging, custom handlers for preprocessing/inference, and management of multi-GPU worker scaling. (torchserve, mar-file, handler, basehandler, model-archiver,...
GitHub
numpy-masked
Masked arrays for robust handling of missing or invalid data, ensuring they are excluded from statistical and mathematical computations. Triggers: masked array, numpy.ma, missing data, invalid values, hard mask...
GitHub
adk-rag-agent
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval t...
GitHub
unsloth-qlora
Advanced 4-bit quantization techniques using Unsloth and BitsAndBytes for extreme VRAM efficiency (triggers: QLoRA, 4-bit, load_in_4bit, bnb-4bit, VRAM optimization, dynamic quantization).
GitHub
numpy-set-ops
Set-theoretic operations for finding unique elements, membership testing, and array intersections. Triggers: unique, isin, intersect1d, setdiff1d, union1d.
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.