Living directory signal
Agent skills directorySecurity-first catalogUpdated from tracked datasets

Discover agent skills through a catalog that actually shows its freshness.

3,548+ tracked skills, MCP servers, and workflow building blocks across the ecosystem, including 555 curated directory entries and 2,993 OpenClaw inventory rows. Agent Skills Hub should feel like a living product surface, so the homepage leads with sync visibility, category coverage, and repeat-visit hooks instead of hiding freshness in the background.

Explore trending See recent scansJoin weekly digest

Catalog pulse

Last dataset scan: Mar 14, 2026

warming

The site should make freshness impossible to miss. This block turns scan timing into a trust signal instead of a hidden backend detail.

3,548+

Tracked items

47

Official

100%

High safety

Why this matters

Users should know whether the directory is actively maintained before they click a single skill. Freshness, category breadth, and recent additions are now homepage-level trust signals.

Latest dataset scan

Mar 14, 2026

Confirmed 460 skills 1 day ago

Directory coverage

4 core groups

555+ indexed skills

Sync health

warming

Source: awesome-mcp-servers

Weekly digest

Coming next

Use email to pull users back into the catalog

Coverage snapshot

Development549
Marketing2
Finance2
Workflows1

Top platforms

mcp 路 555langchain 路 1

Weekly digest, not social clutter

You decided not to expose a personal X account, which is the right call for now. The stronger retention move is a branded weekly digest that packages new skills, rising MCP servers, and workflow picks into one repeatable return path.

Recommended first email

  • Top 5 new or newly reviewed skills
  • One rising workflow worth copying
  • One category movement snapshot
  • One editor pick with a short operational note
Plan digest launchSubmit a skill

OpenClaw // Featured

OpenClaw Skills Leaderboard

Ranked by heat score (community adoption + security audit score) from 2,993 cleaned OpenClaw skills.

Explore OpenClaw Hub

Top OpenClaw Skills

Top 100
1

self-improvement

B

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

鈽?137Installs 17,058Heat 179
2

capability-evolver

B

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

鈽?33Installs 36,013Heat 171
3

byterover

B

Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (store knowledge). Invoke when user requests information lookup, pattern discovery, or knowledge persistence. Developed by ByteRover Inc. (https://byterover.dev/)

鈽?36Installs 16,214Heat 168
4

Agent Browser

B

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

鈽?46Installs 12,909Heat 168
5

proactive-agent

B

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

鈽?58Installs 8,699Heat 167
6

clawddocs

B

Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features

鈽?47Installs 5,476Heat 163
7

bird

B

X/Twitter CLI for reading, searching, and posting via cookies or Sweetistics.

鈽?27Installs 8,551Heat 161
8

auto-updater

B

Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.

鈽?35Installs 7,034Heat 160

What is OpenClaw?

OpenClaw is an open skill ecosystem for agent workflows. AgentSkillsHub tracks its most useful skills with structured metadata and security-first scoring.

Learn OpenClaw

Security Reviewed (A/B)

2,555 skills (85%) passed high-safety grade in the latest audit.

self-improvementBcapability-evolverBbyteroverBAgent BrowserB

OpenClaw Tutorials

Browse OpenClaw SkillsSecurity Audit Guide
🏆

Top Agent Skills Leaderboard

Ranked by community stars and security grade

View All →
1
EverythingB

Reference / test server with prompts, resources, and tools

Developmentmcp
76,481
2
FetchB

Web content fetching and conversion for efficient LLM usage

Developmentmcp
76,481
3
FilesystemB

Secure file operations with configurable access controls

Developmentmcp
76,481
4
GitB

Tools to read, search, and manipulate Git repositories

Developmentmcp
76,481
5
MemoryB

Knowledge graph-based persistent memory system

Developmentmcp
76,481
6
Sequential ThinkingB

Dynamic and reflective problem-solving through thought sequences

Developmentmcp
76,481
7
TimeB

Time and timezone conversion capabilities

Developmentmcp
76,481
8
TimeB

MCP server which provides utilities to work with time and dates, with natural language, multiple formats and timezone convertion capabilities.

Developmentmcp
76,481

Wide-screen layout note

Do not waste the right third of the screen

On large displays, one long leaderboard column feels cheap because the rest of the viewport stays empty. This side rail keeps ecosystem context visible and makes the homepage feel denser, more premium, and more like the competitor.

Above-the-fold density

8 leaderboard rows

Enough to feel substantial without swallowing the whole first viewport.

Parallel context

4 maintainer signals

Faces and reputation cues sit beside the main list instead of hiding far below.

Maintainer spotlight

modelcontextprotocol avatar

modelcontextprotocol

Everything

3,594,607awslabs avatar

awslabs

AWS Bedrock KB Retrieval

284,184examples avatar

examples

Notion Workspace Sync

7,460

Trending Picks This Week

Editor-curated top verified skills

View All →
Grade A - Verified
3,400

Notion Workspace Sync

Deep integration with Notion databases. Create pages, read specs, and update project statuses via natural language.

Workflowsmcp
Grade A - Verified
2,100

HubSpot CRM Link

Bidirectional sync for HubSpot CRM. Auto-log meetings from transcripts and draft follow-up emails based on deal stage.

Marketingmcp
Grade A - Verified
1,240

Stripe Connect Agent

Natural language interface for Stripe. Process refunds, check payouts, and analyze subscription churn directly from your agent window.

Financemcplangchain

Top Agent Skills Collections

Curated skill bundles for common workflows

🛒

E-commerce Automation

0

Shopify, Stripe, inventory management skills

鈿欙笍

Developer Toolkit

0

GitHub, CI/CD, code review, deployment skills

📈

Marketing & SEO Suite

0

Content, analytics, social media, SEO skills

💰

Finance & Operations

0

Invoicing, expense tracking, payment processing

🔄

Workflow Automation

0

Zapier-style orchestration, data transforms

🛡️

All Verified (Grade A)

4

Every skill with top security certification

Featured maintainers

Show the people behind strong skills, not just the repo rows

This is one place where the competitor feels premium. Author faces and reputational signals make the directory feel alive, curated, and closer to a real ecosystem.

modelcontextprotocol avatar

modelcontextprotocol

47 tracked skills

Strongest skill

Everything

Reference / test server with prompts, resources, and tools

3,594,607 total starsmaintainer
awslabs avatar

awslabs

36 tracked skills

Strongest skill

AWS Bedrock KB Retrieval

Query Amazon Bedrock Knowledge Bases using natural language to retrieve relevant information from your data sources.

284,184 total starsmaintainer
examples avatar

examples

5 tracked skills

Strongest skill

Notion Workspace Sync

Deep integration with Notion databases. Create pages, read specs, and update project statuses via natural language.

7,460 total starsmaintainer
apify avatar

apify

6 tracked skills

Strongest skill

Apify

[Actors MCP Server](https://apify.com/apify/actors-mcp-server): Use 3,000+ pre-built cloud tools to extract data from websites, e-commerce, social media, search engines, maps, and more

4,206 total starsmaintainer

A registry built for safety first

Agent Skills Hub helps teams discover reusable skills without guessing what is safe. Every entry is scanned, tagged, and scored so you can pick tools that match your risk tolerance and production needs.

Use the registry to compare repo signals, validate security posture, and track updates over time. The goal is simple: ship faster while keeping your workflow trustworthy.

What we flag

  • Hardcoded secrets and token leaks
  • Unsafe filesystem access and path traversal
  • Unpinned dependencies and suspicious install scripts
  • Network calls to unknown endpoints

Participation layer

Submit, feature, and grow the catalog with clearer inbound paths

Good competitors do not just list skills. They create a loop where builders can submit repos, request coverage, and come back for editorial updates. This section makes that loop explicit.

Submit a skill

Send a GitHub repo and get it into the review queue for the public directory.

Open submission

Request featured review

Ask for stronger editorial coverage when a skill deserves front-page attention.

Fast-track request

Sponsor intake

Use the sponsor lane if you want premium placement, enterprise-facing copy, or launch support.

Sponsor options

Showcase // 01

Featured Solution Blueprints

Explore All Scenarios →
🛒
ID: WF-001

E-commerce Automation

Automatically discover trending items, generate SEO descriptions, and upload to Shopify in minutes.

DiscoveryActive
💰
ID: WF-002

Smart Expense Audit

Extract invoice data via OCR, verify against policy, and auto-sync to QuickBooks or Google Sheets.

Finance SDKVerified
📈
ID: WF-003

AI Content Engine

Crawl keywords, analyze competitor Gaps, and publish viral threads to X based on trending topics.

Viral HooksOptimized

Showcase // 02

Official Integrations

View All Official →

Everything

by modelcontextprotocol

Reference / test server with prompts, resources, and tools

★76,481
GRADE B
View Details →

Fetch

by modelcontextprotocol

Web content fetching and conversion for efficient LLM usage

★76,481
GRADE B
View Details →

Filesystem

by modelcontextprotocol

Secure file operations with configurable access controls

★76,481
GRADE B
View Details →

Showcase // 03

Community Favorites

View Top Rated →

AWS Bedrock KB Retrieval

by awslabs

Query Amazon Bedrock Knowledge Bases using natural language to retrieve relevant information from your data sources.

★7,894
GRADE B
View Details →

AWS CDK

by awslabs

Get prescriptive CDK advice, explain CDK Nag rules, check suppressions, generate Bedrock Agent schemas, and discover AWS Solutions Constructs patterns.

★7,894
GRADE B
View Details →

AWS Core

by awslabs

Core AWS MCP server providing prompt understanding and server management capabilities.

★7,894
GRADE B
View Details →

Showcase // 04

Skills Leaderboard

View Full Rankings
#1Everything
76,481
GRADE B
modelcontextprotocolDevelopment
#2Fetch
76,481
GRADE B
modelcontextprotocolDevelopment
#3Filesystem
76,481
GRADE B
modelcontextprotocolDevelopment
#4Git
76,481
GRADE B
modelcontextprotocolDevelopment
#5Memory
76,481
GRADE B
modelcontextprotocolDevelopment
#6Sequential Thinking
76,481
GRADE B
modelcontextprotocolDevelopment
#7Time
76,481
GRADE B
modelcontextprotocolDevelopment
#8Time
76,481
GRADE B
modelcontextprotocolDevelopment
#9Everything
76,481
GRADE B
modelcontextprotocolDevelopment
#10Fetch
76,481
GRADE B
modelcontextprotocolDevelopment
Rankings based on GitHub stars
Top 10 of 555

Industry Segments

E-commerceFinance & OpsMarketing & SEODev ToolsWorkflows
AD

Sponsorship & Partners

Reach 10,000+ AI developers and technical decision makers.

Apply for Placement

Email: sponsor@agentskillshub.dev

Threat Intelligence

Why Security Scoring Matters?

We found critical vulnerabilities in 0% of public skills. Our scanner checks for 45+ specific attack vectors across every repository.

[VULN-01]

Arbitrary code execution

Skills using eval() or exec() can run malicious Python code on your local machine instantly.

Case Study // 0xCC →
[VULN-02]

API Key leakage

Hardcoded credentials or improper environment handling can silently exfiltrate your OpenAI/Claude API keys to third-party endpoints.

Detection Logic →
[VULN-03]

Unbounded file access

Unbounded fs.read allows skills to steal SSH keys, .env secrets, or browse history without prompting.

Sandbox Rules →

Intelligence // 01

AI Skill Recommender

Try:

Type a use case to discover matching skills

What Are AI Agent Skills?

AI Agent Skills are modular, reusable capabilities that extend the functionality of AI agents like Claude, ChatGPT, and other LLM-powered assistants. Think of them as plugins or extensions that give your AI agent superpowers — from accessing external APIs to executing complex workflows.

With the rise of Model Context Protocol (MCP) and similar standards, developers can now build and share skills that work across multiple AI platforms. This creates an ecosystem where one skill can be used by thousands of developers, dramatically accelerating AI agent development.

Why Security Matters for Agent Skills

Unlike traditional software libraries, agent skills often have broad system access — they can read files, make network requests, and execute code. A malicious or poorly-written skill could expose sensitive data, leak API keys, or compromise your entire development environment.

That's why Agent Skills Hub exists. We scan every skill's source code for 45+ vulnerability patterns including arbitrary code execution, credential leakage, and unbounded file access. Our security grades (A through F) give you instant visibility into risk levels before you install.

Popular Use Cases

  • Development Tools: GitHub integration, code review automation, deployment pipelines
  • Finance & Ops: Stripe payment processing, invoice generation, expense tracking
  • E-commerce: Shopify store management, inventory updates, product SEO
  • Marketing: Social media scheduling, SEO analysis, content generation
  • Workflows: Zapier-style automation, data transformation, API orchestration

Getting Started

Browse our registry of 555+ verified skills, each with detailed security analysis and usage documentation. Use the search bar above to find skills by name, category, or platform compatibility. All skills are free to use — we only charge for premium security audits and verification badges.

Answer-first FAQ

Short answers for teams evaluating the directory itself

This block gives AI crawlers and human evaluators one clean place to understand what Agent Skills Hub is, who it is for, and how to use it safely before expanding a rollout.

What is Agent Skills Hub?

Agent Skills Hub is a security-first directory for AI agent skills, MCP servers, and workflow tools. It helps teams find, compare, and evaluate agent-ready tools with fresher dataset signals than a generic static directory.

Who should use Agent Skills Hub?

It is most useful for agent builders, platform operators, workflow designers, and technical teams that need a faster way to shortlist skills before rollout or internal adoption.

How is it different from a generic skills directory?

The homepage and key skill pages focus on freshness, security posture, rollout fit, and category context instead of only listing repositories in one long feed.

How should a team evaluate a skill before rollout?

Start with one real workflow, check the security grade, review install friction, confirm maintenance freshness, and decide whether the skill solves a live operator problem before scaling it across the team.

What is the safest way to roll out a skill internally?

Pilot one skill in a narrow workflow, document rollback steps, keep the first rollout owner-visible, and only expand after the team sees stable results in production-like use.

Mission-Critical
Agent Skills

Get the "VERIFIED SECURE" internal node badge.
Boost user trust and get priority routing in our directory.

Includes manual static analysis & security certificate