nowfound

AI · alternatives · 2026

24 alternatives to vett

Hey HN. I built a security registry for AI agent skills. There are 64k skills on Vercel's skills.sh. Cursor, Claude Code, Windsurf, and dozens more agents pull them from GitHub at HEAD — no versioning, signing, or scanning. The OpenClaw agents themselves flagged this: "The supply chain attack nobody is talking about: skill.md is an unsigned binary."[0] I took an official skill that packages other skills, added a few lines of Python to exfiltrate env vars, shell history, and git config, and installed it into Claude Code and Codex. Claude Code ran the script without flagging the outbound…

Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.

  1. 1

    Curated agent-skills: 1,000+ practical skills selected from 63,000+ GitHub skills. Filter by newest/hot/installs. Works with Claude Code, Codex, ChatGPT, and Cursor.

    Mar 2026 · agentskill.sh · its alternatives →

  2. 2
    Skillkit▲252

    It's an open-source project that lets you create, translate, and work with multiple agents at the same time, and more.

    Feb 2026 · agenstskills.com · its alternatives →

  3. 3
    Agent 37▲401

    Hey HN, I noticed there are 1,000+ MCP skills on GitHub with zero way for creators to charge for them. So I built Agent37. Selling Claude skills today means asking customers to download your skill, set up Claude Code on their laptops, configure MCP servers, and pray it works. No trial, no updates, often you're just handing over the source. Agent37 lets creators upload a skill, share a link, and anyone can try it instantly (no Claude account needed). Built-in Stripe, creators keep 80%. Looking for feedback on the approach. Would you use something like this?

    Mar 2026 · agent37.com · its alternatives →

  4. 4
    Tessl▲260

    I'm Guy, the founder behind Snyk — now building Tessl, a package manager for agent skills. We’ve recently witnessed that most teams still treat skills as static artifacts: markdown files, created or copied from repo to repo. This approach offers a strong initial boost, but quickly creates debt: - Skills are duplicated, and updates never roll out. - Poor quality skills go unseen, misguiding agents instead of helping. - Skill knowledge grows stale, and don’t keep up with the systems and practices they describe. Without a way to evaluate skills, teams have no clear way to understand how good a…

    Feb 2026 · tessl.io · its alternatives →

  5. 5

    Security scanner for OpenClaw AI agent skills

    Feb 2026 · sclawhub.com · its alternatives →

  6. 6

    13,000+ MCP servers, skills & plugins for AI coding agents

    Jul 2026 · codexmarketplaces.com · its alternatives →

  7. 7

    hi guys. been working on something i think is fundamentally missing in today's workflow with ai agents. vcs. i find myself struggling with questions that agents can't answer like "why did you do it?", "when did u delete this folder? why?", etc. or trying to /rewind (after a /compact...) or basically `bisect` to find when and why something was done by the agent in the current / previous session. just like git did for code, i think we are the same core capabilities with ai agents so... i developed an open source solution for that (currently supporting claude code) would love to…

    May 2026 · github.com · its alternatives →

  8. 8

    Security-scored directory for AI skills and agent tools

    Feb 2026 · skillshield.io · its alternatives →

  9. 9

    Discover 172K+ AI agent skills for Claude, Codex & Copilot

    Feb 2026 · skills.palebluedot.live · its alternatives →

  10. 10

    Audit your AI agent skills to avoid malware

    Apr 2026 · labs.snyk.io · its alternatives →

  11. 11

    We built an open-source library of 125 GTM (go-to-market) skills that plug into AI coding agents like Claude Code, Codex, and Cursor. With these skills an AI agent can automatically: - Find ICP leads from conference speakers, LinkedIn activity, or job boards - Generate personalized cold email sequences - Monitor competitor blogs, pricing pages, and hiring signals - Generate programmatic SEO pages from keyword lists - Track where your brand appears in ChatGPT, Perplexity, and Claude answers --- How skills work Each skill is a structured markdown file containing instructions, scripts, and tool…

    Mar 2026 · github.com · its alternatives →

  12. 12

    Excited to launch Awesome AI Agent Skills! An open-source collection of 70+ production-ready skills to make your AI agents smarter and faster. Stop reinventing the wheel. From code generation to security audits, it's all here. Contributions welcome! Let's build together.

    Feb 2026 · github.com · its alternatives →

  13. 13

    3,000+ AI skills for Claude, Cursor & ChatGPT

    May 2026 · getskillsai.org · its alternatives →

  14. 14

    Give your AI agent expert skills before it builds

    May 2026 · npmjs.com · its alternatives →

  15. 15

    Stop AI skills from silently breaking across platforms

    Apr 2026 · github.com · its alternatives →

  16. 16

    789 skills & 10 autonomous agents for Claude Code

    Mar 2026 · clskillshub.com · its alternatives →

  17. 17

    Scans AI agent skills for malicious code

    Aug 2026 · github.com · its alternatives →

  18. 18

    Every Agent Skill, One Registry

    Feb 2026 · askill.sh · its alternatives →

  19. 19

    Discover, save, and install thousands of skills for agents

    Aug 2026 · skillmd.com · its alternatives →

  20. 20

    Detect Security Threats in Agent Skills

    Jan 2026 · skillgaurd.up.railway.app · its alternatives →

  21. 21

    I built a skill library for OpenClaw (always-on AI agent runtime, not session-based) where the agent can teach itself new behaviors during normal conversation. The idea: you tell your agent "every time I ask for a code review, always check for security issues first." It invokes a create-skill skill, writes a new SKILL.md, and that behavior is live immediately — no restart, no config change, no developer required. What I think is actually useful (the safety cluster): • loop-circuit-breaker: OpenClaw retries ALL errors identically. This halts on the 2nd identical failure before it burns your…

    Mar 2026 · github.com · its alternatives →

  22. 22

    Hi Hacker News! I’m Ritam, working with the small but mighty team at Nori. We’ve been obsessed in recent months with how to take tools like Claude Code from “I’ll experiment around with this” to “This is the most useful and necessary thing I use every day”. When I first sat down with our team to check out what they’d built, I found my skepticism about agentic coding melting away—they’d built useful, high quality, handwritten skills, instructions that functioned as “skillsets” to tie skills together for consistent and replicable results, and tooling to manage loading the right context for the…

    Jan 2026 · noriskillsets.dev · its alternatives →

  23. 23

    10 evidence-first workflows for AI coding agents

    Jul 2026 · ai-agent-skills-pack.vercel.app · its alternatives →

  24. 24

    Discover and download agent skills for Claude, featuring capabilities from Anthropic, Notion, Composio, and the community. Fast, powerful, and smart AI agent skills.

    Jan 2026 · openskills.space · its alternatives →

Also compare

Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →