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 710 ranked candidates matching "bm25"

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

Bm25s

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · VERIFIEDCODING

Fast BM25 search in Python, powered by Numpy and Numba

$ npx skills add xhluca/bm25s

1.7K stars64 quality89 trustVerifiedClaude Code26d 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

pythonrag

by xhlucaDetailsQuick view

Local Pdf Chat RAG

STRONG · 76TRUST · 78SAFE · REVIEWEDRESEARCH

🧠 纯原生 Python 实现的 RAG 框架 | FAISS + BM25 混合检索 | 支持 Ollama / SiliconFlow | 适合新手入门学习

$ npx skills add weiwill88/Local_Pdf_Chat_RAG

917 stars51 quality78 trustReviewed with permission notesClaude Code4mo 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

pythonrag

by weiwill88DetailsQuick view

Writ

STRONG · 76TRUST · 80SAFE · REVIEWEDCODING

Claude Code harness for AI coding agents. Hybrid-RAG librarian picks relevant rules in 0.59 ms p95 (BM25 + vector + graph traversal); process keeper blocks writes until…

$ npx skills add infinri/Writ

152 stars49 quality80 trustReviewed with permission notesClaude 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 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.

Claude Code + CLI · 4 targets

pythondeveloper-tools

by infinriDetailsQuick view

Semble Rs

STRONG · 70TRUST · 74SAFE · EXPERIMENTALCODING

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in C…

$ npx skills add johunsang/semble_rs

132 stars49 quality74 trustExperimentalClaude Code + OpenAI Agents1mo 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 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

rustdeveloper-tools

by johunsangDetailsQuick view

Flamehaven Filesearch

STRONG · 71TRUST · 79SAFE · REVIEWEDRESEARCH

Self-hosted RAG search engine — 34 formats, BM25+hybrid search, multi-LLM (Gemini/OpenAI/Claude/Ollama), FastAPI + Docker, production-ready in 3 min

$ npx skills add flamehaven01/Flamehaven-Filesearch

105 stars45 quality79 trustReviewed with permission notesClaude Code + OpenAI 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 RAG and knowledge · I need my agent to build a RAG workflow over documents and retrieve reliable context.

Claude Code + OpenAI Agents · 4 targets

pythonrag

by flamehaven01DetailsQuick view

Memory Lancedb Pro

VERIFIEDEXCELLENT · 100TRUST · 84SAFE · REVIEWEDCODING

Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI

$ npx skills add CortexReach/memory-lancedb-pro

4.4K stars67 quality84 trustReviewed with permission notesClaude Code18d 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 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.

Claude Code + CLI · 4 targets

javascriptrag

by CortexReachDetailsQuick view

Text2vec

VERIFIEDEXCELLENT · 98TRUST · 88SAFE · VERIFIEDRESEARCH

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

$ npx skills add shibing624/text2vec

5.0K stars61 quality88 trustVerifiedClaude Code5mo 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

pythonembeddings

by shibing624DetailsQuick 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

RustyRAG

PROMISING · 69TRUST · 75SAFE · REVIEWEDRESEARCH

Production-grade RAG API built in Rust. Hybrid search with HNSW dense vectors and BM25 sparse matching, cross-encoder reranking, layout-aware document extraction via Doc…

$ npx skills add RustyRAG/RustyRAG

196 stars47 quality75 trustReviewed with permission notesClaude Code2mo 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.

Claude Code + CLI · 4 targets

rustdocument-extraction

by RustyRAGDetailsQuick view

Crawl4AI

VERIFIEDEXCELLENT · 100TRUST · 93SAFE · REVIEWEDRESEARCH

Web crawling built for AI

$ npx skills add unclecode/crawl4ai

4 agent calls100% success71.2K stars79 quality93 trustReviewedClaude Code + OpenAI Agents1d since pushSafe to try31.0K installs

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

Claude Code + OpenAI Agents · 4 targets

claudegpt-4langchaincrewaiopenclaw

by unclecodeDetailsQuick view

Firecrawl

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDRESEARCH

Web data for AI applications

$ npx skills add firecrawl/firecrawl

134.2K stars76 quality88 trustReviewedClaude Code + OpenAI Agents19d since pushSafe to try25.0K installs

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

Claude Code + OpenAI Agents · 4 targets

claudegpt-4langchainopenclaw

by mendableaiDetailsQuick view

Browser Use

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Give your AI agent a web browser

$ npx skills add browser-use/browser-use

100.5K stars76 quality88 trustReviewedClaude Code + OpenAI Agents17d since pushSafe to try28.0K installs

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

Claude Code + OpenAI Agents · 4 targets

claudegpt-4langchainopenclaw

by browser-useDetailsQuick view

OpenClaw Core Skills

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDCODING

Essential skills for autonomous agents

$ npx skills add anthropics/anthropic-cookbook

45.8K stars73 quality87 trustReviewedClaude Code + LangChain28d since pushSafe to try18.0K installs

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.

Claude Code + LangChain · 4 targets

openclawclaudelangchain

by OpenClawDetailsQuick view

Composio

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Connect AI agents to any app

$ npx skills add ComposioHQ/composio

29.1K stars72 quality88 trustReviewedClaude Code + OpenAI AgentsPushed todaySafe to try19.0K installs

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.

Claude Code + OpenAI Agents · 4 targets

claudegpt-4langchaincrewaiautogpt

by ComposioHQDetailsQuick view

MarkItDown

EXCELLENT · 100TRUST · 81SAFE · REVIEWEDRESEARCH

Convert PDFs, Office documents, and web files into clean markdown for agents.

$ npx skills add microsoft/markitdown

80.0K stars93 quality81 trustReviewedClaude Code + OpenAI Agents1mo since pushSafe to try104.0K installs

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

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursor

by microsoftDetailsQuick view

n8n

EXCELLENT · 100TRUST · 74SAFE · REVIEWEDCODING

Workflow automation for connecting agents to repeated operational tasks.

$ npx skills add n8n-io/n8n

190.0K stars92 quality74 trustReviewed with permission notes1mo since pushNeeds review247.0K installs

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 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.

CLI + Codex · 4 targets

apicliagent-workflow

by n8n-ioDetailsQuick 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.

Bm25s

Local Pdf Chat RAG

Writ

Semble Rs

Flamehaven Filesearch

Memory Lancedb Pro

Text2vec

Manticoresearch

RustyRAG

Crawl4AI

Firecrawl

Browser Use

OpenClaw Core Skills

Composio

MarkItDown

n8n