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 878 ranked candidates matching "research"

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

Deep Research

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · VERIFIEDRESEARCH

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of th…

$ npx skills add dzhng/deep-research

19.1K stars70 quality92 trustVerifiedClaude Code + OpenAI Agents3mo 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/…

Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

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

Claude Code + OpenAI Agents · 4 targets

typescriptresearch-agent

by dzhngDetailsQuick view

Open Deep Research

VERIFIEDSTRONG · 73TRUST · 82SAFE · REVIEWEDRESEARCH

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

$ npx skills add nickscamara/open-deep-research

6.3K stars53 quality82 trustReviewed with permission notesClaude Code1y since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.Check: Repository looks stale

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.

Claude Code + CLI · 4 targets

typescriptresearch-agent

by nickscamaraDetailsQuick view

Google Research

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · REVIEWEDRESEARCH

Google Research

$ npx skills add google-research/google-research

38.1K stars75 quality92 trustReviewedClaude Code21d 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 RAG and knowledge · I need my agent to build a RAG workflow over documents and retrieve reliable context.

Claude Code + CLI · 4 targets

jupyter-notebookmachine-learning

by google-researchDetailsQuick view

Autoresearch

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · VERIFIEDCODING

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

$ npx skills add uditgoenka/autoresearch

5.1K stars68 quality91 trustVerifiedClaude Code1mo 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/…

Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

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

Claude Code + CLI · 4 targets

javascriptclaude-code

by uditgoenkaDetailsQuick view

Awesome Autoresearch

VERIFIEDEXCELLENT · 97TRUST · 87SAFE · REVIEWEDCODING

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

$ npx skills add alvinreal/awesome-autoresearch

2.2K stars65 quality87 trustReviewedClaude Code1mo 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: License is unclear

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.

Claude Code + CLI · 4 targets

ai-agents

by alvinrealDetailsQuick view

Awesome Agent Skills For Empirical Research

VERIFIEDEXCELLENT · 99TRUST · 88SAFE · REVIEWEDCODING

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇…

$ npx skills add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research

1.8K stars65 quality88 trustReviewedClaude 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/…Review: License is unclear

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.

Claude Code + CLI · 4 targets

stataai-agents

by brycewang-stanfordDetailsQuick view

NanoResearch

VERIFIEDEXCELLENT · 97TRUST · 87SAFE · VERIFIEDRESEARCH

🦞+🔬 NanoResearch: The Autonomous AI Research Assistant

$ npx skills add OpenRaiser/NanoResearch

1.5K stars61 quality87 trustVerifiedClaude Code1mo 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/…

Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

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

Claude Code + CLI · 4 targets

pythonai-agents

by OpenRaiserDetailsQuick view

Local Deep Research

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · VERIFIEDRESEARCH

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private docum…

$ npx skills add LearningCircuit/local-deep-research

8.5K stars69 quality92 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/…

Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

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

Claude Code + CLI · 4 targets

pythonresearch

by LearningCircuitDetailsQuick view

Auto Deep Research

VERIFIEDSTRONG · 80TRUST · 81SAFE · REVIEWEDRESEARCH

"Your Fully-Automated Personal AI Assistant"

$ npx skills add HKUDS/Auto-Deep-Research

1.6K stars53 quality81 trustReviewed with permission notesClaude Code9mo 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: 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.

Claude Code + CLI · 4 targets

pythonresearch-agent

by HKUDSDetailsQuick view

Awesome Deep Research

STRONG · 80TRUST · 81SAFE · REVIEWEDRESEARCH

[ACL 2026 KnowFM] Awesome Agentic Deep Research Resources

$ npx skills add DavidZWZ/Awesome-Deep-Research

765 stars51 quality81 trustReviewedClaude Code2mo since pushSafe to try

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

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

Claude Code + CLI · 4 targets

rag

by DavidZWZDetailsQuick view

QuantResearch

VERIFIEDSTRONG · 75TRUST · 80SAFE · EXPERIMENTALCODING

Quantitative analysis, strategies and backtests

$ npx skills add letianzj/QuantResearch

3.0K stars51 quality80 trustExperimentalClaude Code3y since pushNeeds review

QualitySolid option that is likely worth shortlisting for production workflows.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 Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

Claude Code + CLI · 4 targets

jupyter-notebookfinance

by letianzjDetailsQuick view

Codex Autoresearch

EXCELLENT · 86TRUST · 84SAFE · REVIEWEDRESEARCH

A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build spe…

$ npx skills add TheGreenCedar/codex-autoresearch

669 stars53 quality84 trustReviewedClaude Code + OpenAI Agents24d 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: Quality score needs review

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

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

Claude Code + OpenAI Agents · 4 targets

typescriptai-agents

by TheGreenCedarDetailsQuick view

Manticoresearch

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

Easy to use open source fast database for search | Good alternative to Elasticsearch | Drop-in replacement for E in the ELK stack

$ npx skills add manticoresoftware/manticoresearch

11.8K stars72 quality90 trustReviewedClaude Code21d 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: Permission surface needs review: filesystem or document access, network or brow…

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

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

Claude Code + CLI · 4 targets

c++search

by manticoresoftwareDetailsQuick view

Presidio Research

STRONG · 79TRUST · 80SAFE · REVIEWEDRESEARCH

This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluati…

$ npx skills add microsoft/presidio-research

290 stars51 quality80 trustReviewedClaude Code1mo since pushSafe to try

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

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

Claude Code + CLI · 4 targets

jupyter-notebookmachine-learning

by microsoftDetailsQuick view

Academic Research Skills

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

Academic Research Skills for Claude Code: research → write → review → revise → finalize

$ npx skills add Imbad0202/academic-research-skills

36.6K stars75 quality90 trustReviewedClaude 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/…Review: License is unclear

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

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

Claude Code + CLI · 4 targets

pythonresearch

by Imbad0202DetailsQuick view

GPT Researcher

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDRESEARCH

Run autonomous deep research over web and local sources

$ npx skills add assafelovic/gpt-researcher

28.0K stars75 quality86 trustReviewed with permission notesClaude Code9d since pushNeeds review

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

TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: License is unclear

Safety gateUsable candidate, but the agent should surface permission and audit notes before 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-agentllm

by assafelovicDetailsQuick 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.

Deep Research

Open Deep Research

Google Research

Autoresearch

Awesome Autoresearch

Awesome Agent Skills For Empirical Research

NanoResearch

Local Deep Research

Auto Deep Research

Awesome Deep Research

QuantResearch

Codex Autoresearch

Manticoresearch

Presidio Research

Academic Research Skills

GPT Researcher