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 450 ranked candidates matching "chm"

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

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

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 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

rmachine-learning

by szilardDetailsQuick view

Speech To Text Benchmark

STRONG · 74TRUST · 77SAFE · REVIEWEDDESIGN

speech to text benchmark framework

$ npx skills add Picovoice/speech-to-text-benchmark

693 stars51 quality77 trustReviewed with permission notes5mo 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 Multimodal media · I need my agent to process images, video, or audio and extract useful information.

CLI + Codex · 4 targets

pythonspeech

by PicovoiceDetailsQuick view

CatchMe

STRONG · 74TRUST · 77SAFE · REVIEWEDCODING

"CatchMe: Make Your AI Agents Truly Personal"

$ npx skills add HKUDS/CatchMe

416 stars52 quality77 trustReviewed with permission notes2mo 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 GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

pythonai-agents

by HKUDSDetailsQuick view

Browsers Benchmark

STRONG · 73TRUST · 77SAFE · REVIEWEDCODING

Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot…

$ npx skills add techinz/browsers-benchmark

335 stars51 quality77 trustReviewed with permission notesBrowser agents2mo 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.

Browser agents + CLI · 4 targets

pythonplaywright

by techinzDetailsQuick view

Chinese Llm Benchmark

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDCODING

非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat…

$ npx skills add jeinlee1991/chinese-llm-benchmark

6.2K stars68 quality85 trustReviewedClaude Code + OpenAI Agents2mo 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: 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 + OpenAI Agents · 4 targets

llm

by jeinlee1991DetailsQuick view

Torchmetrics

VERIFIEDEXCELLENT · 96TRUST · 86SAFE · REVIEWEDCODING

Machine learning metrics for distributed, scalable PyTorch applications.

$ npx skills add Lightning-AI/torchmetrics

2.4K stars65 quality86 trustReviewed2mo 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

pythonmachine-learning

by Lightning-AIDetailsQuick view

Deep Text Recognition Benchmark

VERIFIEDSTRONG · 70TRUST · 80SAFE · EXPERIMENTALRESEARCH

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

$ npx skills add clovaai/deep-text-recognition-benchmark

3.9K stars52 quality80 trustExperimental2y 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 Document processing · I need my agent to read PDFs, extract tables, and turn documents into structured data.

CLI + Codex · 4 targets

jupyter-notebookocr

by clovaaiDetailsQuick view

Thewatchman

STRONG · 73TRUST · 79SAFE · REVIEWEDCODING

Home Assistant custom integration to keep track of missing entities and actions in your config files

$ npx skills add dummylabs/thewatchman

660 stars50 quality79 trustReviewed with permission notes4mo 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 GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

pythonautomation

by dummylabsDetailsQuick view

Mteb

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · REVIEWEDRESEARCH

MTEB: Massive Text Embedding Benchmark

$ npx skills add embeddings-benchmark/mteb

3.3K stars66 quality86 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 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 embeddings-benchmarkDetailsQuick view

Action Tmate

VERIFIEDEXCELLENT · 98TRUST · 88SAFE · REVIEWEDCODING

Debug your GitHub Actions via SSH by using tmate to get access to the runner system itself.

$ npx skills add mxschmitt/action-tmate

3.5K stars67 quality88 trustReviewed2mo 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 Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

javascriptgithub

by mxschmittDetailsQuick view

Awesome Playwright

VERIFIEDEXCELLENT · 94TRUST · 84SAFE · REVIEWEDCODING

A curated list of awesome tools, utils and projects using Playwright

$ npx skills add mxschmitt/awesome-playwright

1.5K stars64 quality84 trustReviewedBrowser agents2mo 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 Testing and QA · I need my agent to test a web app, reproduce bugs, and verify fixes.

Browser agents + CLI · 4 targets

browser-automation

by mxschmittDetailsQuick view

CLUEDatasetSearch

VERIFIEDPROMISING · 66TRUST · 75SAFE · EXPERIMENTALRESEARCH

搜索所有中文NLP数据集，附常用英文NLP数据集

$ npx skills add CLUEbenchmark/CLUEDatasetSearch

4.5K stars52 quality75 trustExperimental4y 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: License is unclear

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

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

CLI + Codex · 4 targets

pythonknowledge-graph

by CLUEbenchmarkDetailsQuick view

Node Html Pdf

VERIFIEDSTRONG · 70TRUST · 77SAFE · EXPERIMENTALRESEARCH

This repo isn't maintained anymore as phantomjs got dreprecated a long time ago. Please migrate to headless chrome/puppeteer.

$ npx skills add marcbachmann/node-html-pdf

3.6K stars52 quality77 trustExperimentalBrowser agents2y 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 Document processing · I need my agent to read PDFs, extract tables, and turn documents into structured data.

Browser agents + CLI · 4 targets

javascriptpdf

by marcbachmannDetailsQuick view

Nbfc

VERIFIEDPROMISING · 64TRUST · 75SAFE · EXPERIMENTALDATA

NoteBook FanControl

$ npx skills add hirschmann/nbfc

3.2K stars51 quality75 trustExperimental2y 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: License is unclear

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

Scenario Data analysis · I need my agent to analyze CSV data, produce insights, and explain trends.

CLI + Codex · 4 targets

c#notebook

by hirschmannDetailsQuick view

Marinara

VERIFIEDPROMISING · 68TRUST · 76SAFE · EXPERIMENTALCODING

Pomodoro® time management assistant for Chrome

$ npx skills add schmich/marinara

2.5K stars50 quality76 trustExperimentalBrowser agents3y 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 gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

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

Browser agents + CLI · 4 targets

javascriptproductivity

by schmichDetailsQuick view

On Policy

VERIFIEDPROMISING · 67TRUST · 78SAFE · REVIEWEDCODING

This is the official implementation of Multi-Agent PPO (MAPPO).

$ npx skills add marlbenchmark/on-policy

2.0K stars50 quality78 trustReviewed with permission notes2y 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

pythonmulti-agent

by marlbenchmarkDetailsQuick 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

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 450 ranked candidates matching "chm"

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

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

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 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

rmachine-learning

by szilardDetailsQuick view

Speech To Text Benchmark

STRONG · 74TRUST · 77SAFE · REVIEWEDDESIGN

speech to text benchmark framework

$ npx skills add Picovoice/speech-to-text-benchmark

693 stars51 quality77 trustReviewed with permission notes5mo 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 Multimodal media · I need my agent to process images, video, or audio and extract useful information.

CLI + Codex · 4 targets

pythonspeech

by PicovoiceDetailsQuick view

CatchMe

STRONG · 74TRUST · 77SAFE · REVIEWEDCODING

"CatchMe: Make Your AI Agents Truly Personal"

$ npx skills add HKUDS/CatchMe

416 stars52 quality77 trustReviewed with permission notes2mo 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 GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

pythonai-agents

by HKUDSDetailsQuick view

Browsers Benchmark

STRONG · 73TRUST · 77SAFE · REVIEWEDCODING

Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot…

$ npx skills add techinz/browsers-benchmark

335 stars51 quality77 trustReviewed with permission notesBrowser agents2mo 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.

Browser agents + CLI · 4 targets

pythonplaywright

by techinzDetailsQuick view

Chinese Llm Benchmark

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDCODING

$ npx skills add jeinlee1991/chinese-llm-benchmark

6.2K stars68 quality85 trustReviewedClaude Code + OpenAI Agents2mo 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: 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 + OpenAI Agents · 4 targets

llm

by jeinlee1991DetailsQuick view

Torchmetrics

VERIFIEDEXCELLENT · 96TRUST · 86SAFE · REVIEWEDCODING

Machine learning metrics for distributed, scalable PyTorch applications.

$ npx skills add Lightning-AI/torchmetrics

2.4K stars65 quality86 trustReviewed2mo 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

pythonmachine-learning

by Lightning-AIDetailsQuick view

Deep Text Recognition Benchmark

VERIFIEDSTRONG · 70TRUST · 80SAFE · EXPERIMENTALRESEARCH

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

$ npx skills add clovaai/deep-text-recognition-benchmark

3.9K stars52 quality80 trustExperimental2y 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 Document processing · I need my agent to read PDFs, extract tables, and turn documents into structured data.

CLI + Codex · 4 targets

jupyter-notebookocr

by clovaaiDetailsQuick view

Thewatchman

STRONG · 73TRUST · 79SAFE · REVIEWEDCODING

Home Assistant custom integration to keep track of missing entities and actions in your config files

$ npx skills add dummylabs/thewatchman

660 stars50 quality79 trustReviewed with permission notes4mo 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 GitHub automation · I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

CLI + Codex · 4 targets

pythonautomation

by dummylabsDetailsQuick view

Mteb

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · REVIEWEDRESEARCH

MTEB: Massive Text Embedding Benchmark

$ npx skills add embeddings-benchmark/mteb

3.3K stars66 quality86 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 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 embeddings-benchmarkDetailsQuick view

Action Tmate

VERIFIEDEXCELLENT · 98TRUST · 88SAFE · REVIEWEDCODING

Debug your GitHub Actions via SSH by using tmate to get access to the runner system itself.

$ npx skills add mxschmitt/action-tmate

3.5K stars67 quality88 trustReviewed2mo 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 Coding agents · I need a coding agent that can understand a repository, edit code, and review pull requests.

CLI + Codex · 4 targets

javascriptgithub

by mxschmittDetailsQuick view

Awesome Playwright

VERIFIEDEXCELLENT · 94TRUST · 84SAFE · REVIEWEDCODING

A curated list of awesome tools, utils and projects using Playwright

$ npx skills add mxschmitt/awesome-playwright

1.5K stars64 quality84 trustReviewedBrowser agents2mo 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 Testing and QA · I need my agent to test a web app, reproduce bugs, and verify fixes.

Browser agents + CLI · 4 targets

browser-automation

by mxschmittDetailsQuick view

CLUEDatasetSearch

VERIFIEDPROMISING · 66TRUST · 75SAFE · EXPERIMENTALRESEARCH

搜索所有中文NLP数据集，附常用英文NLP数据集

$ npx skills add CLUEbenchmark/CLUEDatasetSearch

4.5K stars52 quality75 trustExperimental4y 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: License is unclear

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

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

CLI + Codex · 4 targets

pythonknowledge-graph

by CLUEbenchmarkDetailsQuick view

Node Html Pdf

VERIFIEDSTRONG · 70TRUST · 77SAFE · EXPERIMENTALRESEARCH

This repo isn't maintained anymore as phantomjs got dreprecated a long time ago. Please migrate to headless chrome/puppeteer.

$ npx skills add marcbachmann/node-html-pdf

3.6K stars52 quality77 trustExperimentalBrowser agents2y 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 Document processing · I need my agent to read PDFs, extract tables, and turn documents into structured data.

Browser agents + CLI · 4 targets

javascriptpdf

by marcbachmannDetailsQuick view

Nbfc

VERIFIEDPROMISING · 64TRUST · 75SAFE · EXPERIMENTALDATA

NoteBook FanControl

$ npx skills add hirschmann/nbfc

3.2K stars51 quality75 trustExperimental2y 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: License is unclear

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

Scenario Data analysis · I need my agent to analyze CSV data, produce insights, and explain trends.

CLI + Codex · 4 targets

c#notebook

by hirschmannDetailsQuick view

Marinara

VERIFIEDPROMISING · 68TRUST · 76SAFE · EXPERIMENTALCODING

Pomodoro® time management assistant for Chrome

$ npx skills add schmich/marinara

2.5K stars50 quality76 trustExperimentalBrowser agents3y 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 gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

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

Browser agents + CLI · 4 targets

javascriptproductivity

by schmichDetailsQuick view

On Policy

VERIFIEDPROMISING · 67TRUST · 78SAFE · REVIEWEDCODING

This is the official implementation of Multi-Agent PPO (MAPPO).

$ npx skills add marlbenchmark/on-policy

2.0K stars50 quality78 trustReviewed with permission notes2y 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

pythonmulti-agent

by marlbenchmarkDetailsQuick 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.

Benchm Ml

Speech To Text Benchmark

CatchMe

Browsers Benchmark

Chinese Llm Benchmark

Torchmetrics

Deep Text Recognition Benchmark

Thewatchman

Mteb

Action Tmate

Awesome Playwright

CLUEDatasetSearch

Node Html Pdf

Nbfc

Marinara

On Policy

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.

Benchm Ml

Speech To Text Benchmark

CatchMe

Browsers Benchmark

Chinese Llm Benchmark

Torchmetrics

Deep Text Recognition Benchmark

Thewatchman

Mteb

Action Tmate

Awesome Playwright

CLUEDatasetSearch

Node Html Pdf

Nbfc

Marinara

On Policy

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.

Benchm Ml

Speech To Text Benchmark

CatchMe