459+ signed skills · Free to start

Turn Claude, Cursor or ChatGPT into an expert in your field — in 30 seconds.

Paste one link and your agent gains 459+ expert skills — every one signed, tested against jailbreaks and scored in public. No code. No fine-tuning.

Free forever: unlimited public skills via the MCP gateway · No credit card · No signup to browse · Open source (Apache 2.0)

GitHub starsJoin the DiscordEvery skill adversarially tested before publish

Already use MCP? Paste this URL into your client — it works instantly, no restart.

https://superagentskill.com/api/mcp
install.mcp
30 seconds
1
2
3
Paste URL into client
Your MCP endpoint
That's it. One URL — no SDK, no keys, no DevOps.
Works with Claude Cursor Codex Lovable Windsurf
Expert skills
0+
Playbooks
0+
Souls (expert personas)
0+
Setup time
0s
Universal compatibility

Works with every agent you already use.

One MCP endpoint. No SDK. No config files. Paste the URL and your agent is upgraded.

Missing your favorite? Request it →

How it works

From generic AI to your specialist — in 3 steps.

No prompt engineering. No fine-tuning. No new tools to learn.

01

Connect your AI

Paste one link into Claude, ChatGPT, Cursor or any MCP-compatible tool. Done in 30 seconds. No code, no setup, no IT ticket.

02

Pick a skill — or describe one

Browse ready-made experts, or just say what you do: “I run a cardiology clinic.” The right skills and guardrails get installed — or a custom one is built from your own context.

03

It improves on its own

Every skill is re-tested daily against new attacks. Patched versions arrive automatically; underperformers get re-scored, not buried.

One endpoint · Claude Code · Cursor · ChatGPT · Continue · Cline · Any MCP client

Plain-English commands

If you can write a sentence, you can ship a specialist.

Super Agent Skill does two things at once: it installs the best existing packages for your industry, and it forges new ones — skills, playbooks and souls custom-built from your data — on demand.

Industry

Clinical-grade specialists with citation-required guardrails.

›_

Make my agent a cardiologist trained on the latest ESC guidelines.

Cites the guideline behind every recommendation and refuses to dose without patient weight.

  • skillcardiology-diagnostics
  • guardrailmedical-guardrails
›_

Build a triage flow for chest-pain intake at our ER.

Routes STEMI vs non-STEMI vs musculoskeletal and escalates ambiguous cases to the on-call cardiologist.

  • playbookchest-pain-triage
  • guardrailcite-required
›_

Summarize a discharge summary for the primary care physician, citing every claim.

Extracts diagnosis, meds, follow-ups and red flags — citations link back to the source chart.

  • skillclinical-summarizer
›_

Block any answer that gives a dose without patient weight.

Hard refusal plus a structured request for the missing fields. Every attempt is logged for audit.

  • guardraildose-safety-shield
Why it's different

Anyone can publish a prompt. We publish proof.

The hard part isn't writing a skill — it's convincing your security team it won't leak PII, accept a jailbreak, or hallucinate compliance text. That's what we build.

Attacked before it ships

Adversarial harness

Every skill runs an adversarial gauntlet — prompt injection, jailbreaks, data exfiltration, policy bypass — before it can publish. Pass rate is public, per attack class.

Signed, not just published

Ed25519 · offline-verifiable

Releases are Ed25519-signed and verifiable offline. Your security team can check the math without trusting us.

A score you can audit

Public formula

Trust Score is a public, weighted formula — adversarial robustness, real-world success, signed releases, age. Embed the live badge in your README.

Gets better while you sleep

SkillForge

SkillForge re-tests every skill daily and ships patched versions automatically — no retraining, no downtime, every install reversible and audited.

The flywheel: every production execution feeds the Trust Score. Skills that survive real workloads bubble up; ones that drift get re-scored and patched automatically.

The Stack

Four building blocks. Infinite agents.

SKILLSWhat your agent can do

Capabilities, installable.

Cardiology Diagnostics. Growth Hacking. Legal Due Diligence. Discrete units of expertise an agent can install on demand.

cardiology-diagnosticsgrowth-hacking-prolegal-due-diligence
PLAYBOOKSHow it runs a process end-to-end

Workflows that ship results.

Complete operational logic for real-world processes — from enterprise sales motions to medical consultations.

enterprise-sales-flowmedical-consultation-v2startup-validation
SOULSHow it sounds and decides

Personality as code.

Tone, style, principles, decision-making. Give your agent a Challenger-rep soul, a McKinsey soul, or a humanized doctor soul.

challenger-rep-soulmckinsey-consultanthumanized-doctor
GUARDRAILSWhat it must never do

Safety, by default.

Block hallucinations, regulatory violations, out-of-domain behavior and unsafe actions before they reach your users.

medical-guardrailsfinance-complianceno-hallucination
Pricing

Start free. Upgrade when your agent needs superpowers.

Hacker is free forever — every public skill, via one MCP URL, no account. Agent Pass is $19 per agent per month: your agent's skills stay current and jailbreak-hardened automatically. Enterprise adds private registry, SSO and audit logs.

Open registry

Hacker — free forever

Apache 2.0 · CC BY-SA
  • 600+ public skills, playbooks, souls (drop-in expert personas) & guardrails — unlimited via the MCP gateway, no account needed
  • MCP gateway for any agent (Claude, Cursor, ChatGPT…)
  • Free account adds per-package installs, library sync & reviews
  • Public registry, GitHub-native, fork anything
Browse the open registry →
Most chosen
$19 / agent / month

Agent Pass

+ Enterprise
  • SkillForge auto-patching — skills stay current automatically
  • Continuous jailbreak re-testing on every installed skill
  • Health scoring & weekly reports per agent
  • Priority skills & all marketplace packages included
See all plans →

The open network feeds the premium layer, and the premium layer funds the open network. That's the flywheel.

FAQ

Plain answers to the obvious questions.

How the MCP connection works, what Super Agent Skill actually creates, and how you start with a single sentence.

  • MCP (Model Context Protocol) is a standard way for an AI agent to talk to external tools. You point your agent at Super Agent Skill once — it shows up as a connected tool. From then on, every command you send (in plain English) flows through that connection: Super Agent Skill installs, generates and hot-swaps packages without you touching code or restarting the agent. If your agent already speaks MCP (Claude, Cursor, OpenAI agents, custom), you're 60 seconds away.

One MCP URL.
One sentence. Done.

Install the best packages of your industry, generate what doesn't exist yet, and let SkillForge ship better versions for you — week after week.

$https://superagentskill.com/api/mcp