Data and AI

13,613 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.

tinker-inkling

481

gvkhosla/pi-tinker

Skill Claude CodeCodex

Sample, evaluate, and post-train Inkling and Inkling-Small from Pi. Use when the user mentions Inkling, tml-renderers, TMLv0, thinking effort, Inkling-Small, or Inkling audio/images. Load before writing Inkling training or eval code.

not rated 24 11d ago A SkillSpector: pass 66 tokens original Apache-2.0

KathanModh259/latent-gate

Skill Claude CodeCodex

Compress images, long prompts, conversations, and RAG documents locally via Ollama before consuming LLM tokens. Reduces token usage by 80% on images and 85% on text. Use proactively when: the user uploads images, processes long context, works with multiple RAG sources, or when approaching token limits.

not rated 24 1mo ago A 73 tokens

tinker-sft

483

collinear-ai/simlab

Skill Claude CodeCodex

Fine-tune a model on expert agent trajectories collected from SimLab using Tinker's supervised learning pipeline.

not rated 24 1mo ago A 0 tokens

dataset-mcp

484

boleyn/fastgpt-dataset-mcp

MCP server Claude CodeCodexCursor +2

MCP server "dataset-mcp" as configured in boleyn/fastgpt-dataset-mcp. Runs locally from the dataset-mcp Python package.

not rated 24 1y ago A tokens not measured

ai-agent-super-skill

485

get-zeked/ai-agent-super-skill

Skill Claude CodeCodex

Comprehensive AI agent building skill merging Perplexity Computer's skill creation, webserver, and automation capabilities with Claude Code's agent orchestration, MCP server building, RAG system construction, subagent coordination, parallel agent dispatching, prompt optimization, and execution planning. Covers…

not rated 24 +1 6mo ago A 119 tokens

obtainer

486

OpenDCAI/Dataflow-LoopAI

Skill Claude CodeCodex needs its repo

Use this skill when LoopAI needs dataset discovery, acquisition, web-page collection, DataMixer lakehouse operations, data processing, indexing, recipe planning, or production training-data export. In long-running Codex SDK loops, when Analyzer produces an analysis report, failure taxonomy, or user request that…

not rated 24 yesterday A SkillSpector: warn 190 tokens original Apache-2.0

prompt-warrior

487

timoncool/prompt-warrior

Skill Claude CodeCodex

Use when the user wants to analyze their communication style with AI from Claude Code logs — asks for a "prompt warrior" profile, an "AI profile", "wrapped", a psychological portrait of how they prompt, statistics of their sessions/messages, or personalized prompt-engineering recommendations based on their chat…

not rated 23 yesterday B 77 tokens original MIT

help

488

pinecone-io/gemini-cli-extension

Skill Claude CodeCodex

Overview of all available Pinecone skills and what a user needs to get started. Invoke when a user asks what skills are available, how to get started with Pinecone, or what they need to set up before using any Pinecone skill.

not rated 23 25d ago A SkillSpector: pass 50 tokens original MIT

prompt-optimizer

489

ckanner/agent-skills

Skill Claude CodeCodex

This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models…

not rated 23 9mo ago A 83 tokens original Apache-2.0

kling-3-prompting

490

aedev-tools/kling-3-prompting-skill

Skill Claude CodeCodex

Write better prompts for Kling 3.0 AI video generation. Use when the user wants to create, write, improve, or refine prompts — text-to-video, image-to-video, keyframes, multi-shot sequences, or dialogue scenes.

not rated 23 7mo ago A Socket: passSnyk: pass 56 tokens original MIT

Jeffisgod/Agri-CV-Research

Skill Claude CodeCodex

End-to-end crop disease detection skill supporting classification (which disease), detection (where is the disease), and segmentation (disease region) at three granularity levels, with multiple SOTA models and training strategies built in.

not rated 23 3mo ago A 0 tokens original MIT

alanalyzing/lenny-skills

Skill Claude CodeCodex

AI product development wisdom from 120+ Lenny's Podcast episodes. Covers AI product strategy, LLM applications, ML integration, AI agents, and building AI-native products. Use when building AI products, integrating LLMs, designing AI features, or developing AI strategy.

not rated 23 7mo ago A 63 tokens

skills

494

zhulei227/EasyMLOps

Skill Claude CodeCodex

A machine-learning framework built around pipelines, which are ordered steps for processing data, training models, and deploying them.

not rated 23 4mo ago A 0 tokens original Apache-2.0

openviking

495

swizardlv/openclaw_openviking_skill

Skill Claude CodeCodex

Semantic search, context management, and document indexing via OpenViking. Use when the user asks to: index/import documents or files into a knowledge base, perform semantic search across indexed content, browse or explore indexed resources, get summaries/overviews of indexed documents, manage an OpenViking instance…

not rated 23 6mo ago A 89 tokens original Apache-2.0

doggy8088/litellm-skills

Skill Claude CodeCodex

A set of instructions for controlling LiteLLM usage and spending. It covers virtual keys, which can identify users or applications, along with budgets, limits, and request labels.

not rated 23 1mo ago A 79 tokens

magic-etl-cli

497

stahura/domo-ai-vibe-rules

Skill Claude CodeCodex

Magic ETL dataflows via community-domo-cli — list, get-definition, create, update, run, execution status; JSON DAG actions, transforms, joins. Use when automating dataflows with the community Domo CLI end-to-end. For REST/Java-CLI–first flows or mixed API patterns, use magic-etl instead.

not rated 23 4mo ago A 74 tokens

Just-Agent/make-agents-cheaper

Skill Codex

Use when the user wants to make Claude Code cheaper by improving prompt-cache hit rate, especially for MiMo or other OpenAI-compatible routed models. Trigger for Claude Code cache-hit analysis, cache-friendly command construction, paired baseline vs candidate evaluation, token usage logging, or use of…

not rated 23 +1 3mo ago A 74 tokens original MIT

AlphaBitCore/nexus-gateway

Cursor rule Cursor

Canonical = OpenAI shape; each non-OpenAI adapter owns its bidirectional translation (8 binding rules from provider-adapter-architecture.md §3a).

not rated 23 7d ago A 0 tokens original Apache-2.0

sergekostenchuk/ui-ux-agent-skill-system

Skill Codex

Tactical LLM-friendly site optimization for making a website the best citable answer for AI assistants and RAG retrieval. Use for auditing and optimizing sites such as mlllm.io for llms.txt, AI citation readiness, pillar pages, direct-answer blocks, TL;DR sections, FAQ/schema, article/news schema, topic-to-URL…

not rated 23 +3 2mo ago A 120 tokens original Apache-2.0

mlops-automation

502

MLOps-Courses/mlops-coding-skills

Skill Claude CodeCodex

Automate an MLOps project with mise tasks, lefthook hooks, Docker images, GitHub Actions, and MLflow tracking on a SQL backend. Use when adding a task runner, git hooks, CI/CD, or experiment tracking to a working package.

not rated 22 29d ago A SkillSpector: warn 58 tokens original MIT

pw-danger-gemini-web

503

plugins-world/pw-skills

Skill Claude CodeCodex

A tool that uses the Gemini web service to generate text and images. It can accept reference images and keep context across multiple messages using a session.

not rated 22 7mo ago A 268 tokens

fable-prompt-pass

504

mvresh/fable-prompt-pass

Plugin Claude Code

Bundles 1 skill · 117 tokens together

Adapt any prompt to fit Claude Fable 5 (claude-fable-5) without losing its meaning: optimize structure per Fable's prompting guidance, clarify legitimate intent to avoid false-positive refusals, and flag mechanical API incompatibilities.

not rated 22 1mo ago A tokens not measured 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: