Open source · MIT
DeepSeek Harness
A plugin-first agent harness where models, tools, sessions, sandboxes, filesystems, loops, orchestration and UI are composable plugins.
208,385 GitHub starsSnapshot · source linked
Discover AI Skills With Clearer Context
Search source-backed Agent Skill packages with fixed release records, then use editorial capability guides to understand workflows, permissions, risks, and adoption guardrails.
Launch Radar
New agent platforms, tracked with evidence boundaries
Fast-moving launches deserve dedicated coverage—not premature security or compatibility claims.
Always-on agents
Grok Bot
A persistent agent platform with cloud-computer access, reusable routines, schedules and multi-bot collaboration.
Availability is plan-limitedSnapshot · source linked
SkillVet Charts · Current signal
Open the full leaderboard →What is leading—without hiding the evidence.
Transparent ClawHub popularity uses downloads, installs, and stars. Rank is not a quality or safety verdict.
- 01currentSoftware DevelopmentNo static findings
Github
by Peter Steinberger · fixed release 036fda
99.99chart score- Stars
- 664
- Downloads
- 196.3K
- Installs
- 7,629
- 02currentAgent Engineering, Security & GovernanceNo static findings
ontology
by oswalpalash · fixed release e4ce0e
99.98chart score- Stars
- 656
- Downloads
- 196.8K
- Installs
- 7,314
- 03currentAgent Engineering, Security & Governancemedium static signal
Proactive Agent
by halthelobster · fixed release 34d214
99.98chart score- Stars
- 829
- Downloads
- 173.8K
- Installs
- 7,186
Key Agent Capabilities
Agentic AI collection →MCP
MCP Connector Skill
Connect agents to tools and data with scopes, logs, and approval gates.
Computer UseBrowser Automation Agent
Let agents operate web workflows without giving up human control.
ResearchDeep Research Agent
Turn broad questions into cited, contradiction-aware research briefs.
GovernanceAgent Security Guardrails
Define permissions, monitoring, and incident response for action-taking agents.
Recently Updated Skill Packages
Canonical source and fixed release recorded; security and compatibility evidence remain separate.
Real package recordClawHubNo static findings
typecho-publisher
通过 typecho-cli 直接管理 Typecho 博客文章 — 创建、查询、更新、删除、查询分类。当用户要求发布文章到博客、保存内容到 Typecho、查询或修改博客文章时触发此技能。涉及"发博客""归档""知识库""Typecho""我的博客"等关键词时均应使用。
- Publisher
- CoolingRabbit
- Fixed release
- 4.1.1
OpenClaw · native official
Real package recordClawHubNo static findings
小红书转链工具
小红书笔记链接批量转链工具。当用户提到小红书、转链、链接转换、xhslink，或要求把小红书笔记链接（含短链）转换为携带xsec_token的且浏览器可以直接打开观看的新链接时使用本 skill。
- Publisher
- cuiyunhai
- Fixed release
- 1.1.0
OpenClaw · native official
Real package recordClawHubNo static findings
ojimport
从 OJ 平台搬运题目（含AtCoder/Codeforces等），生成标准化题目文件包；也可根据用户提供的题目仅生成测试数据。用户说"搬运""搬题""搬道题""导入题目"均适用
- Publisher
- fslong
- Fixed release
- 3.0.0
OpenClaw · native official
Real package recordClawHubNo static findings
sunday-ledger
Play in The Sunday Ledger — a free NFL prediction league for AI agents. Three HTTP calls a week. Reputation stakes only. A public, portable calibration record under your own name.
- Publisher
- Stanicky
- Fixed release
- 1.1.2
OpenClaw · native official
Real package recordClawHubNo static findings
OwlCoda RunKit
Run receipt-backed project execution with OwlCoda
- Publisher
- yeemio
- Fixed release
- 0.23.1
OpenClaw · native official
Real package recordClawHubNo static findings
Google Play Public Data API
Query Google Play app data through a read-only API.
- Publisher
- ReplyNodes
- Fixed release
- 1.0.1
OpenClaw · native official
Recently Updated Capability Guides
View all capability guides →Capability guideEditorial risk: Low
Agent Observability Control Plane
Agent Observability Control Plane: Monitor, log, and audit autonomous AI agent workflows to ensure they operate within safety and budgetary boundaries.
Agent Engineering, Security & GovernanceEditorial utility 5/5
Capability guideEditorial risk: Low
EU AI Act Compliance Checker
EU AI Act Compliance Checker: Automated auditing tool for multi-agent systems to ensure compliance with the latest 2026 EU regulatory requirements.
Enterprise FunctionsEditorial utility 4/5
Capability guideEditorial risk: Medium
Apple Intelligence Connector
Apple Intelligence Connector: Integrate local Apple Intelligence APIs with external autonomous agents for privacy-preserving, on-device data processing.
Agent Engineering, Security & GovernanceEditorial utility 5/5
Capability guideEditorial risk: High
ChatGPT Desktop Automation
ChatGPT Desktop Automation: Orchestrate native macOS applications by automating the official ChatGPT desktop client using accessibility APIs.
Browser Automation & RPAEditorial utility 4/5
Capability guideEditorial risk: High
Agent Security Guardrails
Agent Security Guardrails: Define permissions, policy checks, confirmations, monitoring, and incident response for AI agents that can use tools or take action.
Agent Engineering, Security & GovernanceEditorial utility 5/5
Capability guideEditorial risk: High
AI Coding Agent Skill
AI Coding Agent Skill: Plan, edit, test, and summarize code changes with repository context, terminal feedback, and human review checkpoints.
Software DevelopmentEditorial utility 5/5
Expert Guides
View all guides →Best ClawHub Alternatives (2026)
Best ClawHub Alternatives (2026): Looking for ClawHub alternatives? We compare the top AI skills directories and registries for developers, teams, and automation builders in 2026.
SkillVetAI vs ClawHub — Comparison
SkillVetAI vs ClawHub — Comparison: How a package registry and an editorial capability guide layer support different parts of AI skills discovery and evaluation.
Best skills for data work (CSV, Excel, PDFs)
Best skills for data work (CSV, Excel, PDFs): A hands-on collection of skills for cleaning data, extracting facts from PDFs, building spreadsheet logic, and turning raw inputs into reliable reports.
Curated Collections
Agentic AI Skill Collection
Agentic AI Skill Collection: Curated AI skills for 2026 agent workflows, including MCP connectors, browser agents, deep research, coding agents, RAG, voice agents, and security guardrails.
Content Creation Skill Collection
Content Creation Skill Collection: Curated AI skills for content workflows, including deep research agents, AI video generation, SEO keyword clustering, content briefs, image alt text, web research, and competitor analysis.
Customer Support Skill Collection
Customer Support Skill Collection: Curated AI skills for customer support workflows, including customer support agents, macros, refund handling, email triage, RAG knowledge retrieval, knowledge bases, and onboarding checklists.
Daily Productivity Skill Collection
Daily Productivity Skill Collection: Curated AI skills for productivity workflows, including email triage, calendar scheduling, meeting notes, PDF summarization, and form autofill.
Data Work Skill Collection
Data Work Skill Collection: Curated AI skills for data workflows, including RAG knowledge retrieval, deep research agents, data cleaning, spreadsheet formulas, PDF extraction, log analysis, and citations.
Developer Skill Collection
Developer Skill Collection: Curated AI skills for developer workflows, including AI coding agents, code review, issue triage, release notes, log analysis, security checks, API testing, and MCP connectors.
Security and Compliance Skill Collection
Security and Compliance Skill Collection: Curated AI skills for security and compliance workflows, including agent security guardrails, MCP risk review, checklists, dependency scanning, log analysis, API testing, and code review.