Star0

Skill Registry

Find the right skill for the job your agent is doing.

Search by task, platform, trust profile, or GitHub adoption. OpenAgentSkill keeps the interface human-readable and the API ready for agents.

29
Shown
0
Tracks
92
Targets

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

142

Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.

142 quality142 maintained

Research

Research and knowledge work

41

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

41 quality41 maintained

Finance

Finance and quant workflows

6

Market data, SEC filings, portfolio analysis, quant research, backtesting, and risk workflows.

6 quality6 maintained

Marketing

Marketing and growth automation

4

SEO, content operations, lead generation, CRM, email automation, analytics, and growth workflows.

4 quality4 maintained

Design

Design and creative production

11

Design assets, images, video, audio, multimodal media, presentation, and creative production skills.

11 quality11 maintained

Data

Data, BI, and analytics

21

CSV, SQL, notebooks, dashboards, data pipelines, BI, ETL, and spreadsheet analysis.

21 quality21 maintained

Legal

Legal, policy, and compliance

5

Contract analysis, privacy, policy review, compliance checks, governance, and document risk review.

5 quality5 maintained

Education

Education and tutoring

1

Tutoring, course generation, quizzes, learning analytics, classrooms, and teaching workflows.

1 quality1 maintained

World Cup

Football and World Cup analytics

0

Football data, World Cup dashboards, xG, match prediction, scouting, and sports analytics.

0 quality0 maintained

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-29 of 29 ranked candidates matching "deep"

Best blend of quality, stars, freshness, and agent usage

1

Tensorflow

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

An Open Source Machine Learning Framework for Everyone

$ npx skills add tensorflow/tensorflow
195.7K stars78 quality95 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

c++machine-learning
by tensorflowDetailsQuick view
2

Transformers

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDDESIGN

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

$ npx skills add huggingface/transformers
161.6K stars78 quality98 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmachine-learning
by huggingfaceDetailsQuick view
3

Langchain

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · REVIEWEDCODING

The agent engineering platform.

$ npx skills add langchain-ai/langchain
139.3K stars78 quality95 trustReviewedClaude Code + OpenAI Agents1d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

1d since push

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

pythonai-agents
by langchain-aiDetailsQuick view
4

Pytorch

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Tensors and Dynamic neural networks in Python with strong GPU acceleration

$ npx skills add pytorch/pytorch
100.8K stars78 quality91 trustReviewedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

License is unclear

Gate

review

Reviewed

pythonmachine-learning
by pytorchDetailsQuick view
5

LLMs From Scratch

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

$ npx skills add rasbt/LLMs-from-scratch
97.3K stars78 quality91 trustReviewedClaude Code + OpenAI Agents14d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

14d since push

Risk

Safe to try

License is unclear

Gate

review

Reviewed

jupyter-notebookmachine-learning
by rasbtDetailsQuick view
6

Deer Flow

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

$ npx skills add bytedance/deer-flow
71.1K stars77 quality98 trustVerifiedClaude Code2d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

2d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmulti-agent
by bytedanceDetailsQuick view
7

Gpt4free

VERIFIEDEXCELLENT · 100TRUST · 97SAFE · VERIFIEDCODING

The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

$ npx skills add xtekky/gpt4free
66.3K stars77 quality97 trustVerifiedClaude Code + OpenAI Agents1d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

1d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonchatbot
by xtekkyDetailsQuick view
8

Keras

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · REVIEWEDCODING

Deep Learning for humans

$ npx skills add keras-team/keras
64.1K stars77 quality95 trustReviewedClaude Code3d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

3d since push

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

pythonmachine-learning
by keras-teamDetailsQuick view
9

Openinterpreter

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

$ npx skills add openinterpreter/openinterpreter
64.0K stars77 quality95 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

rustcoding-agent
by openinterpreterDetailsQuick view
10

Ultralytics

VERIFIEDEXCELLENT · 100TRUST · 93SAFE · REVIEWEDDESIGN

Ultralytics YOLO 🚀

$ npx skills add ultralytics/ultralytics
58.5K stars77 quality93 trustReviewed with permission notesClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.Action: Require human approval before installing into a real workspace.

Scenario

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed with permission notes

pythonmachine-learning
by ultralyticsDetailsQuick view
11

Yolov5

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

$ npx skills add ultralytics/yolov5
57.5K stars77 quality95 trustVerifiedClaude Code3d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

3d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmachine-learning
by ultralyticsDetailsQuick view
12

Faceswap

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · REVIEWEDCODING

Deepfakes Software For All

$ npx skills add deepfakes/faceswap
55.3K stars76 quality95 trustReviewedClaude Code18d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

18d since push

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

pythonmachine-learning
by deepfakesDetailsQuick view
13

Last30days Skill

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDRESEARCH

Agent-led recent-trends research across social, prediction markets, video, code, and the web.

$ npx skills add mvanhorn/last30days-skill -g
43.0K stars76 quality98 trustVerifiedClaude Code + OpenAI Agents6d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Research agents

I need my agent to research a topic, compare sources, and produce a concise report.

Agents

Claude Code + OpenAI Agents + Cursor

4 install targets

Maintenance

fresh

6d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonclaude-codecodexcursoragent-skills
by mvanhornDetailsQuick view
14

AI For Beginners

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

12 Weeks, 24 Lessons, AI for All!

$ npx skills add microsoft/AI-For-Beginners
48.2K stars76 quality95 trustVerifiedClaude Code5d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

5d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

jupyter-notebookmachine-learning
by microsoftDetailsQuick view
15

Cherry Studio

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

$ npx skills add CherryHQ/cherry-studio
47.3K stars76 quality98 trustVerifiedClaude Code + OpenAI Agents2d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

2d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

typescriptai-agents
by CherryHQDetailsQuick view
16

Streamlit

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDDATA

Streamlit — A faster way to build and share data apps.

$ npx skills add streamlit/streamlit
45.0K stars76 quality95 trustVerifiedClaude Code2d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Data analysis

I need my agent to analyze CSV data, produce insights, and explain trends.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

2d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythondata-analysis
by streamlitDetailsQuick view
17

Supervision

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDDESIGN

We write your reusable computer vision tools. 💜

$ npx skills add roboflow/supervision
44.4K stars76 quality95 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmachine-learning
by roboflowDetailsQuick view
18

Gradio

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDDATA

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

$ npx skills add gradio-app/gradio
42.9K stars76 quality98 trustVerifiedClaude Code1d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Data analysis

I need my agent to analyze CSV data, produce insights, and explain trends.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

1d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythondata-analysis
by gradio-appDetailsQuick view
19

Ray

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

$ npx skills add ray-project/ray
42.9K stars76 quality98 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmachine-learning
by ray-projectDetailsQuick view
20

DeepSpeed

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

$ npx skills add deepspeedai/DeepSpeed
42.5K stars76 quality98 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmachine-learning
by deepspeedaiDetailsQuick view
21

BettaFish

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDDATA

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

$ npx skills add 666ghj/BettaFish
41.4K stars76 quality95 trustVerifiedClaude Code23d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Data analysis

I need my agent to analyze CSV data, produce insights, and explain trends.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

23d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythondata-analysis
by 666ghjDetailsQuick view
22

Chatbox

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · REVIEWEDCODING

Powerful AI Client

$ npx skills add chatboxai/chatbox
40.5K stars75 quality95 trustReviewedClaude Code + OpenAI Agents4d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

4d since push

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

typescriptchatbot
by chatboxaiDetailsQuick view
23

Tesseract.Js

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · REVIEWEDRESEARCH

Pure Javascript OCR for more than 100 Languages 📖🎉🖥

$ npx skills add naptha/tesseract.js
38.1K stars75 quality95 trustReviewedClaude Code30d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Document processing

I need my agent to read PDFs, extract tables, and turn documents into structured data.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

30d since push

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

javascriptocr
by napthaDetailsQuick view
24

Mediapipe

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDDESIGN

Cross-platform, customizable ML solutions for live and streaming media.

$ npx skills add google-ai-edge/mediapipe
35.7K stars75 quality95 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

c++machine-learning
by google-ai-edgeDetailsQuick view
25

Langgraph

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · REVIEWEDCODING

Build resilient agents.

$ npx skills add langchain-ai/langgraph
34.9K stars75 quality92 trustReviewedClaude Code + OpenAI AgentsPushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: Documentation summary is thin · README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + OpenAI Agents + LangChain

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

pythonai-agents
by langchain-aiDetailsQuick view
26

Diffusers

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDDESIGN

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

$ npx skills add huggingface/diffusers
33.9K stars75 quality98 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonimage-generation
by huggingfaceDetailsQuick view
27

SpaCy

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

💫 Industrial-strength Natural Language Processing (NLP) in Python

$ npx skills add explosion/spaCy
33.7K stars75 quality95 trustVerifiedClaude Code28d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

28d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmachine-learning
by explosionDetailsQuick view
28

Netron

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

Visualizer for neural network, deep learning and machine learning models

$ npx skills add lutzroeder/netron
33.1K stars75 quality95 trustVerifiedClaude Code2d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

2d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

javascriptmachine-learning
by lutzroederDetailsQuick view
29

Pytorch Lightning

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

$ npx skills add Lightning-AI/pytorch-lightning
31.2K stars75 quality98 trustVerifiedClaude Code6d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

6d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmachine-learning
by Lightning-AIDetailsQuick view