High-intent entry points

Start from the task, not a keyword list.

These shortcuts use the same trust, supply, and relevance signals as the registry API, so humans and agents land on a useful shortlist faster.

Agent-readable index

FinanceStock analysis QuantTrading research SlidesPPT generation DocsPDF parsing ExtractWeb scraping CreativeDesign workflow SportsFootball analytics

Decision filters

Choose by scenario, quality, and trust signals.

Use casePlatform fitQuality tierTrust profileSafety gateGitHub adoption

Showing 1-16 of 873 ranked candidates matching "qa"

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

OpenQA

STRONG · 74TRUST · 77SAFE · REVIEWEDCODING

openQA web-frontend, scheduler and tools.

$ npx skills add os-autoinst/openQA

367 stars52 quality77 trustReviewed with permission notes1mo since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Testing and QA · I need my agent to test a web app, reproduce bugs, and verify fixes.

CLI + Codex · 4 targets

perltesting

by os-autoinstDetailsQuick view

KoalaQA

PROMISING · 67TRUST · 77SAFE · REVIEWEDRESEARCH

KoalaQA 是一款 AI 大模型驱动的开源售后服务社区，提供 AI 回答、AI 搜索、AI 运营等能力，帮助你快速落地售后客服、社区问答、自助服务等场景，帮助团队显著降低人工运营成本、提升客户满意度与响应效率，助力实现 ZCR（Zero Contact Resolution）目标。

$ npx skills add chaitin/KoalaQA

512 stars50 quality77 trustReviewed with permission notes2mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario RAG and knowledge · I need my agent to build a RAG workflow over documents and retrieve reliable context.

CLI + Codex · 4 targets

typescriptrag

by chaitinDetailsQuick view

NISQA

NEEDS REVIEW · 50TRUST · 73SAFE · EXPERIMENTALDESIGN

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

$ npx skills add gabrielmittag/NISQA

954 stars40 quality73 trustExperimental2y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustGood trust signals with a few areas worth checking before rollout.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

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

CLI + Codex · 4 targets

pythonvoice

by gabrielmittagDetailsQuick view

AISquare Studio QA

STRONG · 73TRUST · 76SAFE · REVIEWEDCODING

Setting up QA testing agents using playwright and crewAI

$ npx skills add AISquare-Studio/AISquare-Studio-QA

167 stars49 quality76 trustReviewed with permission notesOpenAI Agents + Browser agents28d since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

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

OpenAI Agents + Browser agents · 4 targets

pythontesting

by AISquare-StudioDetailsQuick view

Qqqa

PROMISING · 61TRUST · 72SAFE · EXPERIMENTALCODING

Fast, stateless LLM for your shell: qq answers; qa runs commands

$ npx skills add iagooar/qqqa

619 stars42 quality72 trustExperimentalClaude Code + OpenAI Agents8mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

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

Claude Code + OpenAI Agents · 4 targets

rustproductivity

by iagooarDetailsQuick view

FinQA

NEEDS REVIEW · 46TRUST · 71SAFE · EXPERIMENTALCODING

Data and code for EMNLP 2021 paper "FinQA: A Dataset of Numerical Reasoning over Financial Data"

$ npx skills add czyssrs/FinQA

376 stars37 quality71 trustExperimental4y since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

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

CLI + Codex · 4 targets

pythonfinancial-data

by czyssrsDetailsQuick view

LLM KG4QA

PROMISING · 55TRUST · 73SAFE · REVIEWEDRESEARCH

LLM-KG4QA: Large Language Models and Knowledge Graphs for Question Answering

$ npx skills add machuangtao/LLM-KG4QA

160 stars38 quality73 trustReviewed with permission notes8mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario RAG and knowledge · I need my agent to build a RAG workflow over documents and retrieve reliable context.

CLI + Codex · 4 targets

javascriptrag

by machuangtaoDetailsQuick view

SlideVQA

NEEDS REVIEW · 35TRUST · 68SAFE · BLOCKEDRESEARCH

SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (AAAI2023)

$ npx skills add nttmdlab-nlp/SlideVQA

106 stars33 quality68 trustBlocked for auto-install1y since pushRisky

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: License is unclear

Safety gateThis skill should not be selected by an agent without explicit human security review.

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

CLI + Codex · 4 targets

pythonocr

by nttmdlab-nlpDetailsQuick view

ManipVQA

NEEDS REVIEW · 35TRUST · 69SAFE · BLOCKEDCODING

[IROS24 Oral]ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models

$ npx skills add SiyuanHuang95/ManipVQA

102 stars33 quality69 trustBlocked for auto-install2y since pushRisky

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: License is unclear

Safety gateThis skill should not be selected by an agent without explicit human security review.

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

CLI + Codex · 4 targets

pythonrobotics

by SiyuanHuang95DetailsQuick view

Paper Qa

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDCODING

High accuracy RAG for answering questions from scientific documents with citations

$ npx skills add Future-House/paper-qa

8.7K stars69 quality89 trustReviewed1mo 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/…Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

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

CLI + Codex · 4 targets

pythonrag

by Future-HouseDetailsQuick view

Phpqa

VERIFIEDEXCELLENT · 94TRUST · 84SAFE · REVIEWEDCODING

Docker image that provides static analysis tools for PHP

$ npx skills add jakzal/phpqa

1.3K stars64 quality84 trustReviewed1mo since pushSafe to try

QualityHigh-confidence pick with strong adoption and healthy maintenance signals.

TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin

Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

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

CLI + Codex · 4 targets

dockerfilestatic-analysis

by jakzalDetailsQuick view

DeepQA

VERIFIEDPROMISING · 69TRUST · 80SAFE · REVIEWEDCODING

My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot

$ npx skills add Conchylicultor/DeepQA

2.9K stars51 quality80 trustReviewed with permission notes4y since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.Check: Repository looks stale

TrustGood trust signals with a few areas worth checking before rollout.Review: Repository looks stale

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

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

CLI + Codex · 4 targets

pythonchatbot

by ConchylicultorDetailsQuick view

Primeqa

PROMISING · 62TRUST · 77SAFE · REVIEWEDRESEARCH

The prime repository for state-of-the-art Multilingual Question Answering research and development.

$ npx skills add primeqa/primeqa

740 stars43 quality77 trustReviewed with permission notes10mo since pushNeeds review

QualityUseful candidate, but compare it with alternatives before adopting.

TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review

Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario RAG and knowledge · I need my agent to build a RAG workflow over documents and retrieve reliable context.

CLI + Codex · 4 targets

pythonsemantic-search

by primeqaDetailsQuick view

ArXivQA

NEEDS REVIEW · 54TRUST · 72SAFE · EXPERIMENTALRESEARCH

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

$ npx skills add taesiri/ArXivQA

380 stars41 quality72 trustExperimentalClaude Code11mo since pushNeeds review

QualityInspect the repository carefully before adding it to an agent workflow.

TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear

Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

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

Claude Code + CLI · 4 targets

pythonresearch

by taesiriDetailsQuick view

Neural Vqa

NEEDS REVIEW · 42TRUST · 65SAFE · BLOCKEDCODING

:grey_question: Visual Question Answering in Torch

$ npx skills add abhshkdz/neural-vqa

485 stars38 quality65 trustBlocked for auto-install10y since pushRisky

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: License is unclear

Safety gateThis skill should not be selected by an agent without explicit human security review.

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

CLI + Codex · 4 targets

luacomputer-vision

by abhshkdzDetailsQuick view

TableQA

NEEDS REVIEW · 45TRUST · 66SAFE · BLOCKEDDATA

AI Tool for querying natural language on tabular data.

$ npx skills add abhijithneilabraham/tableQA

320 stars36 quality66 trustBlocked for auto-install3y since pushRisky

QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale

TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale

Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario Database and SQL · I need my agent to inspect database schemas, write SQL, and explain query results.

CLI + Codex · 4 targets

pythonmachine-learning

by abhijithneilabrahamDetailsQuick 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

AI Agent Skills Directory

Real skills, grouped by the work your agent needs to finish.

Build the registry by domain, not just by count.

Coding and developer agents

Research and knowledge work

Presentation and deck workflows

Finance and quant workflows

Marketing and growth automation

Design and creative production

Data, BI, and analytics

Legal, policy, and compliance

Education and tutoring

Football and World Cup analytics

Start from the task, not a keyword list.

Choose by scenario, quality, and trust signals.

OpenQA

KoalaQA

NISQA

AISquare Studio QA

Qqqa

FinQA

LLM KG4QA

SlideVQA

ManipVQA

Paper Qa

Phpqa

DeepQA

Primeqa

ArXivQA

Neural Vqa

TableQA