Data and AI skills

10,079 tagged Data and AI, measured the same way as everything else here.

Browse within: LLM 282agent 133agents 126agentic-ai 115cli 79skills 71anthropic-claude 59machine-learning 59chatgpt 57javascript 56ai-scientist 55openai 53coding-agents 52bioinformatics 44

nkg-ai-flow-skill

265

wqaetly/nkg-ai-flow

Skill Claude CodeCodex

A set of rules for building runnable AI workflow apps in this repository. It covers TypeScript FlowBuilder graphs, custom nodes, shared context, supervision flows, and app configuration.

not rated 49 28d ago A SkillSpector: warn 80 tokens original MIT

agnes-ai-models

266

AgnesAI-Labs/skills

Skill Codex

Agnes AI model integration skill for OpenAI-compatible text, image, video, and agent workflows. Use when Codex needs to configure Agnes AI API access, select or document Agnes models including agnes-2.5-flash, agnes-image-2.1-flash, and agnes-video-v2.0, write Python/Node/curl examples, debug common API errors, poll…

not rated 49 +1 1mo ago A 123 tokens

deepseek-harness

267

HenryZ838978/deepseek-harness

Skill Claude Code needs its repo

Use this skill whenever the user wants to call DeepSeek V4-Pro / V4-Flash (or its legacy aliases deepseek-chat / deepseek-reasoner), or you see code that imports from openai import OpenAI with baseurl="https://api.deepseek.com". This skill teaches you the 10 protocol contract rules required to avoid the 16 documented…

not rated 49 +1 2d ago A SkillSpector: warn 144 tokens original MIT

databricks-solutions/solution-builder

Skill Claude Code

Configure, run, and adapt the {{demo-name}} demo in the user's Databricks workspace. Use when the user is working in (or has imported) the {{demo-slug}} project AND says any of "run in my workspace", "set this up", "configure for my workspace/catalog/schema", "deploy this demo", "make this work in my workspace"; OR…

not rated 48 +2 20d ago A 0 tokens

nai5-prompting

272

Miint-Sunny/nai5-prompting

Skill Claude CodeCodex

A guide for writing prompts for NovelAI Diffusion V5, an image-generation system. It covers describing scenes, arranging multiple characters, making comic panels, and troubleshooting results.

not rated 48 +10 7d ago A 116 tokens GPL-3.0

ChamberTeller/b02-skills-main-datascience

Skill Claude CodeCodex

🤖 Data Science Engineering Skills — TDD and planning skills for ML pipelines, data APIs and analytical tooling. Derived from skills-main (mattpocock/skills). Data pipelines, model training, evaluation, MLOps.

not rated 47 4mo ago A 56 tokens

jatevo

274

lucacadalora/jatevo-openclaw

Skill Claude CodeCodex

Free inference-as-a-service via Jatevo.id — access Qwen 3.5 Plus, Kimi K2.5, and GLM 4.7 at zero cost. Use when you want free, high-quality LLM models for OpenClaw.

not rated 47 5mo ago A 57 tokens original MIT

code-review

277

gridctl/gridctl

Skill Claude CodeCodex

Structured code review prompt with language and focus area.

not rated 45 today A SkillSpector: pass 12 tokens original Apache-2.0

amrouter

278

akillness/jeo-skills

Skill Claude CodeCodex

Self-hosted AI gateway with one OpenAI-compatible endpoint for multi-provider LLM, embedding, image, and audio routing, automatic fallback, load balancing, and cost optimization.

not rated 45 +1 7d ago A 38 tokens

vision-multimodal

281

Yts1919/dsh-vision-complete

Skill Claude CodeCodex

A skill that adds image, video, audio, document, and screenshot understanding to a text-only model. It includes tasks such as reading text from images, locating objects, transcribing speech, and analyzing media.

not rated 43 24d ago A SkillSpector: pass 112 tokens original MIT

vaquarkhan/data-engineering-agent-skills

Skill Claude CodeCodex

Forces replay-safe rollout plans, reconciliation gates, and rollback paths before executing any data backfill or historical reprocessing. Use when running /backfill, rerunning pipelines, repairing publish windows, or any work that risks double-counting or downstream corruption.

not rated 43 +3 2mo ago A 61 tokens original MIT

prompt-polish

283

mfarzanansari/prompt-polish

Skill Claude CodeCodex

Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for…

not rated 42 1mo ago A 146 tokens original MIT

setup-vision-helper

284

50kg/zcode-deepseek-eye

Skill Claude CodeCodex

A setup guide for connecting a text-only main model to a separate vision assistant when images need to be interpreted.

not rated 42 +1 28d ago A SkillSpector: pass 106 tokens original MIT

metabase/agent-skills

Skill Claude CodeCodex

A Metabase AI-readiness coach, covering the data groundwork that makes AI answers trustworthy: modeling with Transforms, table and field metadata, the Glossary, saved Metrics, and marking canonical content. Use this skill whenever the user wants to check if their data is ready for AI, prep the underlying data for…

not rated 42 +1 14d ago A SkillSpector: warn 213 tokens original MIT

antigravity-api-skill

286

luoluoluo22/antigravity-api-skill

Skill Claude CodeCodex

A usage guide for APIs made available through an Antigravity reverse proxy, including Gemini models, image generation, and video analysis.

not rated 41 6mo ago A 46 tokens

mastra

287

Array-Ventures/coworker

Skill Claude CodeCodex

Comprehensive Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents and workflows. Covers documentation lookup strategies (embedded docs, remote docs), core concepts (agents vs workflows, tools, memory, RAG), TypeScript requirements, and common patterns. Use this…

not rated 41 6mo ago A 83 tokens original Apache-2.0

eval-engineer

288

Galileo-Agent-Labs/eval-engineer

Skill Codex

Use when a user is unsure which Eval Engineer command to run for AI agents/RAG apps, needs onboarding/status for a .galileo workspace, or asks where to start.

not rated 41 28d ago A SkillSpector: pass 39 tokens original MIT

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: