Data and AI

14,252 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

kaggle

289

shepsci/kaggle-skill

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 100 tokens together

Independent, unofficial Kaggle.com plugin: research a competition, see where you stand, check and submit with a dry run first, read solution writeups and discussions, and work with datasets, models and notebooks. Not affiliated with, endorsed by, or sponsored by Kaggle or Google.

not rated 108 +2 changed 1mo ago A tokens not measured original MIT

nebius/nebius-physical-ai

Skill Claude CodeCodex

Use when authoring, running, submitting, or validating native NVIDIA PAIDF workflows on Nebius + SkyPilot — VDA, scoped DIG, IAA, EVG, and the NPA-specific Cosmos3 VDA variant — with real components, exact model provenance, artifact handoffs, and runtime access checks.

not rated 105 +6 changed 7d ago A SkillSpector: warn 70 tokens original Apache-2.0

academic-plotting

292

KalarisLabs/research-agent-skills

Skill Claude CodeCodex

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…

not rated 105 today A 68 tokens

infranodus

294

infranodus/mcp-server-infranodus

Plugin Cursor

Bundles 2 MCP servers

InfraNodus knowledge graphs and text network analysis: topics, content gaps, research questions, GraphRAG retrieval, SEO/GEO analysis, and structured memory for AI agents.

not rated 104 changed yesterday A tokens not measured original MIT

early-experience-data

295

OSU-NLP-Group/EarlyExperience

Skill Claude CodeCodex

Use this skill whenever the user asks to generate, collect, inspect, or prepare early-experience training data (Implicit World Modeling or Self-Reflection, in the sense of arXiv:2510.08558) for an agent environment. Trigger phrases include "rollout", "collect expert trajectories", "generate reflection", "smoke test…

not rated 103 +1 4mo ago A SkillSpector: pass 125 tokens original MIT

hybrid-memory

296

clawdbrunner/openclaw-graphiti-memory

Skill Claude CodeCodex

Hybrid memory strategy combining OpenClaw's built-in QMD vector memory with Graphiti temporal knowledge graph. Use for all memory recall requests.

not rated 103 3mo ago A SkillSpector: pass 32 tokens original MIT

mastra-skills

298

mastra-ai/skills

Plugin Claude Code

Bundles 2 skills · 211 tokens together

Mastra framework and Factory operations skills with progressive disclosure for development, API inspection, troubleshooting, and operations.

not rated 103 +3 changed 3d ago A tokens not measured

openrouter-multimodal

299

stabgan/openrouter-mcp-multimodal

MCP server Claude CodeCodexCursor +2

Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP. Runs locally from the @stabgan/openrouter-mcp-multimodal npm package. Needs 13 environment variables to run.

not rated 102 yesterday A tokens not measured original Apache-2.0

fdueblab/Micro-Agent

Skill Claude CodeCodex

Technical guidance for recognizing human actions in video without training a new machine-learning model or using an LLM. It describes a pipeline that samples video frames, estimates body poses, measures movement, and assigns labels with rules.

not rated 100 changed 1mo ago A SkillSpector: pass 0 tokens original MIT

tao-skills

301

NVIDIA-TAO/tao-skill-bank

Plugin Claude Code

Bundles 82 skills · 8,980 tokens together

Full TAO skill bank — every model, data, platform, and application skill in one bundle. Install this for the standard agentic-fine-tuning experience.

not rated 99 +1 changed 1mo ago A tokens not measured original Apache-2.0

rowan

302

dralkh/seerai

Skill Claude CodeCodex

Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related…

not rated 98 +4 1mo ago A 100 tokens original MIT

yolodex

303

qtzx06/yolodex

Skill Claude Code

Train a custom YOLO object detection model from any YouTube gameplay video. Provide a video URL and target classes, and this skill handles the entire pipeline autonomously — frame extraction, AI-powered labeling, data augmentation, training, and evaluation with iterative improvement.

not rated 96 7mo ago A 56 tokens

dat-skill

304

that-company/dat-skill

Skill Codex

Default path for any cloud training work in Dat. Use this skill whenever a task needs cloud training, GPU training, model fine-tuning, training evaluation, long-running training compute, or hosted training job orchestration. Also use it to submit prepared packages, handle approval/session handoff, track jobs, cancel…

not rated 93 3mo ago A 77 tokens

tensormux/kernel-skills

Skill Claude CodeCodex

Guide the agent through implementing a Triton kernel that writes newly computed K and V tensors into a pre-allocated KV cache during LLM inference. This covers two cache layouts (contiguous and paged / vLLM-style PagedAttention), unified prefill and decode handling via a slotmapping tensor, GQA/MQA where the cache…

not rated 89 +2 4mo ago A 0 tokens original MIT

nlp-text-analysis

307

leonardodalinky/SciDER

Skill Claude CodeCodex

Text data analysis for NLP research — dataset characterization, preprocessing decision guide, tokenization choices, embedding selection, and evaluation metrics (BLEU, ROUGE, BERTScore, perplexity). Use when analyzing or processing text datasets.

not rated 88 26d ago A 51 tokens original Apache-2.0

polars

308

polars-inc/skills

Plugin Claude Code

Bundles 1 skill · 166 tokens together

Official Polars skill: write fast, idiomatic lazy Polars in Python, answer data questions in one shot, run SQL on DataFrames, and translate pandas to Polars.

not rated 87 11d ago A tokens not measured original MIT

pdfmux

309

NameetP/pdfmux

MCP server Claude CodeCodexCursor +2

Self-healing PDF extraction for RAG — #2 of 8 engines on opendataloader-bench (0.903). Flags pages it can't read instead of dropping them, and certifies any extractor's output for silent drops. Verify signed manifests offline, free. Per-page confidence, 7-tool MCP server, LangChain/LlamaIndex loaders. LlamaParse…

not rated 86 6d ago A Socket: warn tokens not measured original MIT

ai-ready-data

310

Snowflake-Labs/ai-ready-data

Skill Claude CodeCodex

Assess and optimize data for AI workloads across platforms. Scan estates for prioritization, assess assets against profiles, and guide remediation.

not rated 86 5mo ago A 29 tokens original Apache-2.0

keboola

311

keboola/mcp-server

Plugin Cursor

Bundles 4 skills · 194 tokens together

Explore, query and build in your Keboola projects: inspect tables, run SELECT queries, create SQL transformations and flows, and debug failed jobs through the Keboola MCP server.

not rated 85 yesterday A tokens not measured original MIT

knowledge_sources

312

elizaOS/knowledge

Cursor rule Cursor

This repository aggregates knowledge from various sources for RAG systems. See the main README.md for a full overview.

not rated 84 +1 yesterday A 0 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: