Data and AI skills

10,147 tagged Data and AI, measured the same way as everything else here.

Browse within: LLM 284agents 135agent 131agentic-ai 110skills 87cli 77machine-learning 60anthropic-claude 59coding-agents 59chatgpt 57javascript 56ai-scientist 55openai 52bioinformatics 44

raganything-mcp

769

yyisahandsomeboy/rag_anything_mcp_sever

Skill Claude CodeCodex

A skill for operating the RAG-Anything MCP service, which lets an agent index and search information in files such as PDFs, documents, spreadsheets, web pages, and code.

not rated 0 2mo ago A 100 tokens

mcp-ml-toolkit-zx

770

wzx11223344/mcp-ml-toolkit

Skill Claude CodeCodex

A machine-learning toolkit covering common methods for classification, prediction, grouping, dimensionality reduction, data preparation, and model evaluation. Classification predicts categories, regression predicts numbers, and clustering groups similar records.

not rated 0 1mo ago A 8 tokens original MIT

recognize-image

771

LY20050921/qwen-vision-mcp

Skill Claude CodeCodex

An image-understanding skill that sends an image to a Qwen vision model when the current model cannot view its contents directly. It returns a text description for the agent to use.

not rated 0 1mo ago A 56 tokens original MIT

minimax-h3-prompting

772

jonpojonpo/comfy-h3-mcp

Skill Claude CodeCodex

Write effective prompts for MiniMax-H3 video+audio generation, and assemble the resulting clips into a cut. Covers prompt structure, camera vocabulary, native audio prompting, reference-mode tagging, the model's hard constraints, and a frame-exact ffmpeg assembly recipe. Use this skill when generating video with…

not rated 0 1mo ago A 151 tokens

baic-datalayer

773

prepmonk/baic-dl-mcp

Skill Claude CodeCodex

Use for all BAIC Data Layer work through the baic-dl MCP tools - connectors and sources, data ingestion into knowledge bases, golden SQL and instructions, knowledge clusters, and the Data Discovery / Data Engineering / Data Analyst agents including building pipelines and asking questions of data. Enforces passing user…

not rated 0 1mo ago A 137 tokens

luma-vision-mcp

774

harryopo/luma-vision-mcp

Skill Claude CodeCodex

A visual-understanding service for text-only language models that describes uploaded images, extracts text, and compares pictures.

not rated 0 1mo ago A 82 tokens

etreby/intel-npu-tools

Skill Codex

Index and semantically search private local text, source code, documentation, and logs with the intel-npu-tools MCP server. Use when an agent needs meaning-based retrieval from a local project or document directory, needs to refresh an existing NPU index, or needs source-backed local context without uploading files.

not rated 0 29d ago A 67 tokens original MIT

good-skill

776

0xNagato/skill-lint

Skill Claude CodeCodex

Converts CSV exports to Parquet and validates them against a declared schema, reporting type mismatches per column. Use when the user asks to convert, compact, or validate tabular data files before loading them into a warehouse.

not rated 0 14d ago A 49 tokens original MIT

data-transformer

777

tetracoralla/BatchTicket

Skill Codex

Use for deterministic inspection, reshaping, conversion, validation, or comparison of JSON, JSONL, CSV, TSV, YAML, and Parquet; for adapting one tool's structured output to another tool's input; or when a large payload should be summarized and transformed without model-generated data rewriting.

not rated 0 7d ago A 63 tokens original Apache-2.0

dataset-discovery

778

Ben11304/OC-mcp

Skill Claude CodeCodex

Find construction datasets for a specific AI or research task using OpenConstruction catalog metadata. Use when the user needs ranked dataset candidates, source links, license/access checks, or comparison-ready dataset options.

not rated 0 19d ago A 42 tokens original Apache-2.0

using-vlm-mcp

779

YC-CLT/VLM-mcp

Skill Claude CodeCodex

Use when user provides images requiring VLM-based processing via VLM-mcp.

not rated 0 changed 7d ago A 21 tokens original MIT

grok-prompting

780

bigu1/grok-plugin-codex

Skill Claude Code

Internal guidance for composing clear Grok task prompts from Codex rescue handoffs.

not rated 0 18d ago A 21 tokens original Apache-2.0

gpt-img-2/image3-prompt-mcp

Skill Claude CodeCodex

Research real GPT Image 2 prompt examples and turn rough image ideas into structured prompt packs, reference-image edit instructions, product visuals, layouts, and debugging loops. Use for prompt search, prompt rewriting, ecommerce images, readable text, posters, social creatives, character sheets, storyboards, or…

not rated 0 17d ago A 84 tokens original MIT

gpt-img-2/opensora2-prompt-mcp

Skill Claude CodeCodex

Turn rough video ideas into structured OpenSora prompt packs, reference-aware motion instructions, shot plans, and focused debugging loops. Use for text-to-video, image-to-video, video-to-video, product clips, cinematic scenes, transitions, or multi-shot sequences; do not use for unrelated models, account support, or…

not rated 0 17d ago A 79 tokens original MIT

gpt-img-2/chinavideoai-prompt-mcp

Skill Claude CodeCodex

Turn rough China AI video ideas into structured English or Chinese prompt packs, reference-aware motion instructions, shot plans, and focused debugging loops. Use for text-to-video, image-to-video, reference-to-video, video-to-video, product clips, cinematic scenes, transitions, or multi-shot sequences; do not use for…

not rated 0 16d ago A 83 tokens original MIT

gpt-img-2/see-dance-2-prompt-mcp

Skill Claude CodeCodex

Turn rough video ideas into structured English or Chinese Seedance-oriented prompt packs, exact reference bindings, shot sequences, and focused debugging loops. Use for text-to-video, image-to-video, multimodal reference, product clips, cinematic scenes, transitions, or loops; do not use for account support, live…

not rated 0 16d ago A 81 tokens original MIT

modelmix

785

StarShipI/modelmix

Skill Claude Code

Multi-model LLM comparison tool. Compare how different AI models handle the same task, get quality scores, and identify the best model. Use when comparing model outputs for translation, coding, writing, or analysis tasks. Use when the user asks to "compare models", "which model is better for X", or "test different…

not rated 0 1mo ago A 74 tokens

extract-text-to-json

786

coastmancoastman/diem-agent-workers

Skill Codex

Convert bounded, user-supplied text into caller-defined, schema-valid JSON through the DIEM Agent Workers x402 endpoint. Use for entity extraction, record normalization, classification, or text-to-JSON jobs when the caller needs deterministic keys and machine validation and has an x402-capable HTTP client.

not rated 0 today A 65 tokens original MIT

runtime-copilot

787

kroq86/data-engineering-runtime-lab

Skill Codex

Use when the user wants to operate, diagnose, or validate the Mini Data Engine MCP runtime from Codex; prefer the MCP surface over raw shell commands, start with projecttoolcatalog and projectgetdefaults, then use healthcheck, projectrunregression, explainrun, projectcomparebaseline, and related runtime tools.

not rated 0 3mo ago A 69 tokens original MIT

zenlee123/routerbase-agent-skills

Skill Codex

Integrate applications with RouterBase, the OpenAI-compatible model gateway at https://routerbase.com/v1. Use when migrating OpenAI SDK calls to RouterBase, configuring RouterBase API keys, implementing chat completions, streaming, tool calling, JSON mode, vision inputs, request validation, error handling, or…

not rated 0 2mo ago A 104 tokens

ingest-knowledge

789

hyh0620/mcp-knowledge-service

Skill Claude CodeCodex needs its repo

Ingest a source path into a specified collection and report file, chunk, vector, and BM25 counts.

not rated 0 1mo ago A 27 tokens original MIT

tillpad

790

number1101/tillpad-mcp

Skill Claude CodeCodex

Connect to Tillpad MCP for bounded KVP, RAG search, receive-only email inboxes (webhooks, blocklist, raw MIME), and run-key wipe receipts. Use when onboarding to Tillpad, minting API keys, creating agent inboxes, or running the zero-human bootstrap loop.

not rated 0 9d ago A 64 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: