AI Agent Skill Repository

AI Agent Skills Directory

Browse reusable skills for Codex, Claude Code, Cursor, finance, research, web scraping, PPT, football analytics, data, marketing, design, and more.

Live registry search

Results for “accuracy-score

Exact name and slug matches are checked against the live registry before ranked alternatives.

Clear search

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 33 ranked candidates matching "accuracy-score"

Best blend of relevance, quality, freshness, and verified outcomes

1

Kube Score

VERIFIEDEXCELLENT · 90TRUST · 86SAFE · REVIEWEDCODING

Kubernetes object analysis with recommendations for improved reliability and security. kube-score actively prevents downtime and bugs in your Kubernetes YAML and Charts.…

$ npx skills add zegl/kube-score
3.1K stars59 quality86 trustReviewed3mo since pushSafe to try

Scenario Testing and QA

CLI + Codex · 4 targets

gosecurity
by zeglDetailsQuick view
2

Score

VERIFIEDEXCELLENT · 87TRUST · 82SAFE · REVIEWEDDESIGN

ossia score, an interactive sequencer for the intermedia arts

$ npx skills add ossia/score
2.0K stars62 quality82 trustReviewed with permission notes2mo since pushNeeds review

Scenario Design and creative

CLI + Codex · 4 targets

c++creative-coding
by ossiaDetailsQuick view
3

Bert Score

VERIFIEDPROMISING · 67TRUST · 77SAFE · EXPERIMENTALDESIGN

BERT score for text generation

$ npx skills add Tiiiger/bert_score
1.9K stars50 quality77 trustExperimental2y since pushNeeds review

Scenario Multimodal media

CLI + Codex · 4 targets

jupyter-notebookmachine-learning
by TiiigerDetailsQuick view
4

Blockads Android

VERIFIEDEXCELLENT · 90TRUST · 87SAFE · REVIEWEDLEGAL

Block ads system-wide on Android using local VPN-based DNS filtering. No root needed. No data collection.

$ npx skills add pass-with-high-score/blockads-android
1.1K stars60 quality87 trustReviewed2mo since pushSafe to try

Scenario Legal and compliance

CLI + Codex · 4 targets

kotlinprivacy
by pass-with-high-scoreDetailsQuick view
5

PyNomaly

PROMISING · 65TRUST · 75SAFE · REVIEWEDDESIGN

Anomaly detection using LoOP: Local Outlier Probabilities, a local density based outlier detection method providing an outlier score in the range of [0,1].

$ npx skills add vc1492a/PyNomaly
330 stars48 quality75 trustReviewed with permission notes2mo since pushNeeds review

Scenario Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by vc1492aDetailsQuick view
6

Paper Qa

VERIFIEDEXCELLENT · 99TRUST · 89SAFE · REVIEWEDCODING

High accuracy RAG for answering questions from scientific documents with citations

$ npx skills add Future-House/paper-qa
8.7K stars66 quality89 trustReviewed2mo since pushSafe to try

Scenario GitHub automation

CLI + Codex · 4 targets

pythonrag
by Future-HouseDetailsQuick view
7

DeepLearningExamples

VERIFIEDSTRONG · 73TRUST · 80SAFE · REVIEWEDDESIGN

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

$ npx skills add NVIDIA/DeepLearningExamples
14.8K stars57 quality80 trustReviewed with permission notes2y since pushNeeds review

Scenario Multimodal media

CLI + Codex · 4 targets

jupyter-notebookspeech
by NVIDIADetailsQuick view
8

Roast My Design System

PROMISING · 62TRUST · 74SAFE · REVIEWEDDESIGN

v3.11.0 · Try it: npx roast-my-design-system · Roasts your design system with real data: a health score, the receipts, the first fixes ranked by payoff, and with --rules…

$ npx skills add pencilrebel/roast-my-design-system
10 stars42 quality74 trustReviewed with permission notesClaude Code + OpenAI Agents10d since pushNeeds review

Scenario Design and creative

Claude Code + OpenAI Agents · 4 targets

javascript
by pencilrebelDetailsQuick view
9

Chronos

VERIFIEDEXCELLENT · 85TRUST · 81SAFE · REVIEWEDCODING

Kodezi Chronos is a debugging-first language model that achieves state-of-the-art results on SWE-bench Lite (80.33%) and 67% real-world fix accuracy, over six times bett…

$ npx skills add Kodezi/Chronos
4.9K stars57 quality81 trustReviewed with permission notesOpenAI Agents9mo since pushNeeds review

Scenario Coding agents

OpenAI Agents + CLI · 4 targets

javamachine-learning
by KodeziDetailsQuick view
10

arbor

EXCELLENT · 92TRUST · 82SAFE · REVIEWEDRESEARCH

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…

$ npx skills add K-Dense-AI/scientific-agent-skills --skill arbor
34.0K stars55 quality82 trustReviewed with permission notesClaude Code2d since pushSafe to try

Scenario Research agents

Claude Code + CLI · 4 targets

by K-Dense-AIDetailsQuick view
11

analytical-method-validation

EXCELLENT · 92TRUST · 75SAFE · REVIEWEDRESEARCH

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>,…

$ npx skills add K-Dense-AI/scientific-agent-skills --skill analytical-method-validation
34.0K stars55 quality75 trustReviewed with permission notesClaude Code2d since pushNeeds review

Scenario Research agents

Claude Code + CLI · 4 targets

by K-Dense-AIDetailsQuick view
12

OpenSCA Cli

VERIFIEDEXCELLENT · 86TRUST · 82SAFE · REVIEWEDCODING

OpenSCA is an open source software supply chain security solution that supports the detection of open source dependencies, vulnerabilities and license compliance with a…

$ npx skills add XmirrorSecurity/OpenSCA-cli
1.1K stars56 quality82 trustReviewed with permission notes3mo since pushSafe to try

Scenario Coding agents

CLI + Codex · 4 targets

gostatic-analysis
by XmirrorSecurityDetailsQuick view
13

Benchm Ml

VERIFIEDSTRONG · 73TRUST · 80SAFE · REVIEWEDCODING

A minimal benchmark for scalability, speed and accuracy of commonly used open source implementations (R packages, Python scikit-learn, H2O, xgboost, Spark MLlib etc.) of…

$ npx skills add szilard/benchm-ml
1.9K stars50 quality80 trustReviewed with permission notes4y since pushNeeds review

Scenario GitHub automation

CLI + Codex · 4 targets

rmachine-learning
by szilardDetailsQuick view
14

Antialiased Cnns

VERIFIEDPROMISING · 62TRUST · 74SAFE · EXPERIMENTALCODING

pip install antialiased-cnns to improve stability and accuracy

$ npx skills add adobe/antialiased-cnns
1.7K stars49 quality74 trustExperimental2y since pushNeeds review

Scenario GitHub automation

CLI + Codex · 4 targets

pythoncomputer-vision
by adobeDetailsQuick view
15

Herbie

STRONG · 70TRUST · 75SAFE · REVIEWEDCODING

Optimize floating-point expressions for accuracy

$ npx skills add herbie-fp/herbie
879 stars51 quality75 trustReviewed with permission notes2mo since pushNeeds review

Scenario Coding agents

CLI + Codex · 4 targets

htmldeveloper-tools
by herbie-fpDetailsQuick view
16

Units Of Measure Harmonization Intelligence Platform

STRONG · 74TRUST · 76SAFE · EXPERIMENTALCODING

Production-Grade ML System for Automated Unit of Measure Error Detection | 88-92% Accuracy | 94% Autonomy | KNIME Workflow

$ npx skills add JulietMirambo/Units_of_Measure_Harmonization-intelligence-platform
813 stars51 quality76 trustExperimental3mo since pushNeeds review

Scenario GitHub automation

CLI + Codex · 4 targets

powershellautomation
by JulietMiramboDetailsQuick view

Page 1

Showing the strongest 16 results to keep the registry fast for humans and agents. Refine by use case, platform, stars, or search query for a narrower shortlist.

Try the agent resolve API