New: Credits are here. One balance for web and MCP. See pricing

    The Marketplace for AI Agent Skills

    Give your AI agent superpowers. Built by experts. Scanned for safety. Yours in 30 seconds.

    Browse
    Install in 30 seconds Every skill security-scanned Works with 20+ AI agents Agent-native MCP

    or describe what you need

    Works with every major AI coding agent

    CCCGGV🦞WMACQTRATKBZGZHCCCGGV🦞WMACQTRATKBZGZH
    How It Works

    Three steps to your first skill

    No sales calls. No demos. No config. Buy, download, install, done.

    01

    Browse

    Search live skills by task, agent, or category.

    Search skills…/
    designing-hybrid-context-layers$10
    ai-automation-qa-pack$5
    02

    Buy or download

    Pay once and own it, or grab free skills instantly.

    designing-hybrid-context-layers$10.00
    Purchase

    One-time purchase.

    03

    Install

    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" } } }
    Set up MCP →

    Recently Listed Skills

    Fresh skills from our creator community

    View all

    Open Source README Generator

    by Arnstein Larsen

    $7.99

    A repo visitor decides in about ten seconds whether your project solves their problem — and most READMEs spend those ten seconds on installation instructions instead of answering 'what does this actually do'

    1
    open-sourcedocumentationgithub+3

    prompt-injection-auditor

    by Timoranjes

    Free

    The security auditor for AI agents. Detect prompt injection, secret leaks, and unsafe tool access in SKILL.md files.

    1
    prompt-injectionsecurityagent-safety+3

    Developer Documentation Writer

    by Arnstein Larsen

    $8.99

    Developers don't read documentation — they arrive with a task, scan for the answer, and leave. Docs that aren't structured for that pattern don't get read, they get abandoned

    1
    documentationtechnical-writingapi-docs+2

    LLM Eval Framework Builder

    by Arnstein Larsen

    $12.99

    You changed the prompt, tried four inputs, it looked better, you shipped — and three days later support tickets say outputs are worse for an entire class of inputs you didn't test

    1
    llm-evalprompt-engineeringtesting+3

    Prompt Engineering Specialist

    by Arnstein Larsen

    $9.99

    Production prompts grow by accretion — every failure gets another appended rule until the prompt is two thousand words of contradictions that the model navigates unpredictably

    1
    prompt-engineeringllm-opssystem-design+2

    RAG System Designer

    by Arnstein Larsen

    $12.99

    Every RAG tutorial shows the same pipeline; almost none of it survives contact with your actual corpus

    1
    For Skill Users

    Skills you can actually trust

    Not a GitHub scraper with 800,000 unvetted repos. A curated marketplace with standards.

    Works with your entire stack

    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.

    Your agent finds skills for you

    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 purchase

    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.

    Reviewed, not scraped

    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.

    For Skill Creators

    Build skills. Get paid. Keep your IP.

    Everything you need to turn your agent expertise into recurring revenue, with protection built in.

    Your IP is protected

    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.

    Your agent sells for you

    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.

    Build to real demand

    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.

    Simple, transparent earnings

    Set your price. Earn up to 80% on every sale. Direct purchases: 80%. Credit installs: 70%. Paid via Stripe Connect.

    Start Selling

    Agensi takes 20-30% per sale depending on purchase method. Direct purchases: 20% + $0.50. Credit installs: 30% of net revenue. No hidden fees.

    FAQ

    Got questions?

    Everything you need to know before getting started.

    Get in touch

    Have questions about Agensi? Drop us an email and we'll get back to you.

    SR

    Samuel Rose

    Founder & CEO of Agensi

    Email UsBook a Call

    info@agensi.io

    We typically respond within a few hours during business hours.