New: Credits are here. One balance for web and MCP. See pricing
Give your AI agent superpowers. Built by experts. Scanned for safety. Yours in 30 seconds.
or describe what you need
Works with every major AI coding agent
No sales calls. No demos. No config. Buy, download, install, done.
Search live skills by task, agent, or category.
Pay once and own it, or grab free skills instantly.
One-time purchase.
Drop the unzipped folder into your agent's skills directory.
$ unzip skill.zip -d ~/.claude/skills/
✓ Skill installed. Ready on next session.
Or skip the manual steps - connect your agent via MCP and it handles everything.
{ "mcpServers": { "agensi": { "url": "https://mcp.agensi.io/mcp" } } }Fresh skills from our creator community
An adversarial gate that audits cloud and infrastructure-as-code config — Terraform, Kubernetes, IAM, security groups, buckets — for the misconfigurations that cause real breaches, and returns a structured PASS/REVISE/BLOCK verdict with severities and exact fixes before anything reaches your environment.
An expert architect for building scalable, high-performance React applications with TypeScript and modern best practices.
An adversarial gate that audits a research brief or AI-generated answer for unsupported claims, weak or outdated sources, missing citations, and one-sided framing — returning a structured TRUST/VERIFY/REJECT verdict with the exact passage quoted and what to verify for each.
An adversarial pre-publish gate that audits any article or web page draft for on-page SEO — title and meta, heading structure, keyword use without stuffing, internal links, readability, and search intent — returning a structured PASS/REVISE/FAIL verdict with a fix for each issue.
An adversarial pre-send gate that reviews any email or chat message and returns a structured SEND/REVISE/HOLD verdict — flagging unclear asks, unintended tone, buried action items, and missing context, with the exact text quoted and a fix for each.
An adversarial editing gate that scans any AI-assisted draft and flags the exact tells that make it sound machine-written — filler phrases, formulaic structure, robotic cadence, punctuation tics — returning a structured PASS/REVISE/FAIL verdict with specific fixes.
The builders behind the most popular skills on Agensi.
Not a GitHub scraper with 800,000 unvetted repos. A curated marketplace with standards.
Every skill uses the open SKILL.md standard. Universal skills work across Claude Code, OpenClaw, Codex CLI, Cursor, Gemini CLI, and 20+ agents. Not locked to one tool. One purchase, used everywhere.
Connect your agent to Agensi via MCP and it can search the full catalog mid-conversation. When your agent hits a task a skill could handle, it finds and suggests the right one. No browsing, no downloads. One MCP connection, instant access.
One-time purchases only. No subscriptions, no license keys, no runtime calls. When the creator ships an update, you download it free. The skill runs on your machine. Agensi is never in the loop after purchase.
Every skill is submitted by a creator, scanned by an automated security system, and reviewed by admins before going live. We check for dangerous command patterns, hardcoded secrets, obfuscated code, prompt injection, and suspicious network access. Zip structure validated, SKILL.md checked, content moderated. You are installing something that has been inspected, not a random repo with 2 stars.
Everything you need to turn your agent expertise into recurring revenue, with protection built in.
Every download is buyer-fingerprinted with a unique identifier in the SKILL.md frontmatter. If your skill leaks, upload the file to your piracy reporting dashboard. We match the fingerprint to the exact buyer. From there, you can issue a warning email, suspend their account, or generate a pre-filled DMCA takedown notice to send to the hosting platform. Full enforcement, not just detection.
Agensi publishes a machine-readable catalog API that AI agents query mid-conversation. When a user's agent needs a capability your skill provides, it surfaces your listing at the exact moment of need. Impulse purchases at peak intent.
The Skill Request Board shows what buyers actually want, with upvotes and suggestions. Post a request, and every creator who has a matching skill gets the chance to suggest it. No guessing. No launching into silence.
Set your price. Earn up to 80% on every sale. Direct purchases: 80%. Credit installs: 70%. Paid via Stripe Connect.
Agensi takes 20-30% per sale depending on purchase method. Direct purchases: 20% + $0.50. Credit installs: 30% of net revenue. No hidden fees.
Find skills organized by what they help you do.
Guides, tutorials, and deep-dives on AI agent skills.
Everything you need to know before getting started.
Have questions about Agensi? Drop us an email and we'll get back to you.
Founder & CEO of Agensi
Email UsBook a Callinfo@agensi.io
We typically respond within a few hours during business hours.