Data and AI

13,658 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.

302ai-api-integration

673

302ai/302AI-API-Integration-Skill

Skill Claude CodeCodex

ALWAYS use this skill when user needs ANY API functionality (AI models, image generation, video, audio, text processing, etc.). Automatically search 302.AI's 1400+ APIs and generate integration code. Use proactively whenever APIs or AI capabilities are mentioned.

not rated 11 4mo ago A 60 tokens original Apache-2.0

security-audit

674

RewritingTheCode/workshop

Command Claude Code

Full security pass - verify, validate and harden this repo against its real threat model.

not rated 11 +1 7d ago A 17 tokens original MIT

airllm-skill

675

velumkai/airllm-skill

Skill Claude CodeCodex

Run massive language models (70B+) on consumer GPUs with only 4-8GB VRAM. No quantization, no model degradation.

not rated 11 +1 6mo ago A 0 tokens

video-to-h3-prompt

676

LoveRain1997/video-to-h3-prompt

Skill Claude CodeCodex

Reverse-engineer a video into a complete MiniMax H3 prompt (T2VA / I2VA / FL2VA / L2VA / Ref2VA) ready to paste into H3. Use when the user provides a video file and a reference image and asks to feed H3, swap the character, recreate the same motion path, or generate a reusable script for a known choreography.…

not rated 11 +1 28d ago A 159 tokens original MIT

vercel-ai-sdk-expert

677

JayZeeDesign/claude-code-vault

Agent Claude Code

Use for Vercel AI SDK v5 implementation work: chat interfaces, tool calling, streaming, agentic loop control, type-safe custom messages, or migrating from v4. Covers useChat, streamText, generateText, tools, and the React/Vue/Svelte/Angular integrations.

not rated 11 +1 3mo ago A 0 tokens

datacoolie-build

678

datacoolie/datacoolie

Skill Codex

Build, modify, materialize, run, and verify DataCoolie projects. Use for workspace bootstrap, metadata authoring, environment overlays, capability checks, runners, notebooks, custom functions, narrow unsupported adapters, local tests, immutable builds, and project-owned build/CI automation. This is the sole…

not rated 11 +1 changed 6d ago A 92 tokens AGPL-3.0

vllm-ascend-developer

679

LookAround0301/vllm-ascend-developer

Skill Claude CodeCodex

A development and debugging guide for vLLM and vLLM-Ascend, tools for running machine-learning models to generate responses. It covers inference accuracy checks, service management, automated tests, and code fixes for single-machine or split deployments.

not rated 11 +1 26d ago A 47 tokens

datagovmy-mcp-server

680

manfye/data-dosm-mcp-nodejs

MCP server Claude CodeCodexCursor +2

A simple MCP server for crawling the data from datagovmy API. Runs locally from the datagovmy-mcp-server npm package.

not rated 11 1y ago A tokens not measured original ISC

zvec-mcp-server

681

zvec-ai/zvec-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server for Zvec vector database. Runs locally from the zvec-mcp-server Python package.

not rated 11 +2 4mo ago A tokens not measured original Apache-2.0

dbt-agent-readiness

682

GetCassis/dbt-agent-readiness

Plugin Claude Code

Bundles 1 skill · 126 tokens together

Audit a dbt project for what an AI agent will get wrong if you point it at the data today: wrong metric, wrong table, missed rows, broken joins. Produces one evidence-backed report with blockers, verification queries, and a safe starting perimeter.

not rated 11 9d ago A tokens not measured original MIT

token-compressor

683

base76-research-lab/token-compressor

MCP server Claude CodeCodexCursor +2

MCP server that compresses prompts 40-60% using local LLM + embedding validation. Runs locally from the token-compressor-mcp Python package.

not rated 10 6mo ago A tokens not measured original MIT

prompt

684

gpaiva00/pt-prompt

Skill Claude CodeCodex

Use when translating Brazilian Portuguese messages into English prompts for Claude Code — preserves intent, clarifies ambiguity, and surfaces urgency signals that colloquial Portuguese would lose.

not rated 10 3mo ago B 33 tokens

pytorch-train

685

Axect/pytorch_template

Skill Claude Code

Guide for training PyTorch models using this template's config-driven pipeline. Use this skill whenever the user wants to: train a model, create experiment configs (run.yaml / opt.yaml / best.yaml), run hyperparameter optimization (HPO) with Optuna, extract best parameters from an HPO study, set up a new experiment…

not rated 10 4mo ago A 127 tokens original MIT

crystallize

686

axiomantic/spellbook

Command Claude Code

Transform verbose SOPs into high-performance agentic prompts via principled compression. Use when user says "/crystallize", "compress this prompt", "make this more agentic".

not rated 10 today A 36 tokens original MIT

notebookmd

687

minhlucvan/notebookmd

Skill Claude CodeCodex

Skill "notebookmd" from minhlucvan/notebookmd, covering notebookmd — ai agent data analysis skill, quick start, installation, when to use this skill and core concepts.

not rated 10 4mo ago A 0 tokens original MIT

benjaminshafii/digital-empire

Agent Claude Code

Use this agent when you need to research and document current best practices for local LLM implementation, structured outputs, prompt engineering, or performance optimization. Examples:\n\n \nContext: The team is implementing a new feature that requires multiple LLM calls and wants to optimize the approach.\nuser…

not rated 10 7mo ago A 0 tokens

far

689

mr-kelly/far

Skill Claude Code

File-Augmented Retrieval — generate persistent .meta sidecar files for PDFs, images, spreadsheets, videos and more, making every binary file readable to AI coding agents.

not rated 10 6mo ago A 35 tokens

upstage-ai

690

UpstageAI/upstage-extensions-hub

Plugin Claude Code

Bundles 9 skills · 1,011 tokens together

Official Upstage AI bundle for Claude Code — Solar models, document processing (OCR, parse, classify, extract), schema generation, Studio agent workflows, multi-API builder for webapps, and the BotMadang community client. One install activates all 9 skills with auto-trigger by description.

not rated 10 4mo ago A tokens not measured original MIT

ShayIsso/trajectory-auditor

Skill Claude CodeCodex

Safeguard LLM calls using adaptive/extended thinking against token truncation. Use this skill when configuring API parameters for reasoning models (like Claude 3.7 Sonnet), when structured JSON outputs are returned unparseable or incomplete, or when designing cost-sensitive pipelines that utilize LLM reasoning.

not rated 10 10d ago A 68 tokens

jupyter

692

jrgleason/embeddings-demystified

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

MCP server "jupyter" as configured in jrgleason/embeddings-demystified. Runs in Docker (datalayer/jupyter-mcp-server:latest). Needs 2 environment variables to run.

not rated 10 3mo ago A tokens not measured

polygres

693

Evokoa/polygres-skills

Plugin Claude Code

Bundles 5 skills, 1 MCP server · 317 tokens together

Use Polygres MCP, sync PostgreSQL sources, set up data pipelines, build retrieval, and troubleshoot through supported dashboard, CLI, SDK, and Runtime API workflows.

not rated 10 changed 4d ago A tokens not measured original Apache-2.0

data-liberation

694

CUPIDS-Lab/data-liberation-skill

Skill Claude CodeCodex

Build Python data pipelines that liberate structured data from unstructured and semi-structured sources — government PDFs, FOIA releases, scanned reports, scraped HTML, panel-format spreadsheets — into tidy, documented, reproducible civic datasets. Works at six escalating levels, from a one-shot "just give me the CSV"…

not rated 10 2mo ago A 263 tokens original MIT

NVIDIA/digital-health-skills

Skill Claude CodeCodex ✓ vendor

Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).

not rated 10 2mo ago A 72 tokens

tidymodels-skills

696

tidymodels/skills

Plugin Claude Code

Bundles 6 skills, 1 hook · 310 tokens together

Claude Code skills for the Tidymodels ecosystem — developer tools for building extensions and user guides for data analysis and modeling.

not rated 10 13d ago A tokens not measured

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: