Turn Claude or Cursor into a In 30 seconds. No code.
Paste one link. Your agent gains 459+ expert skills — every one signed, tested against jailbreaks, and scored in public. No code. No fine-tuning. Free to start.
- Works in 30 seconds
- No code or fine-tuning
- Tested against jailbreaks
https://superagentskill.com/api/mcpPaste into Claude → Settings → Connectors. Works immediately — no restart.
Free forever · No signup to browse · No credit card · Open source (Apache 2.0)
From generic AI to your specialist — in 3 steps.
No prompt engineering. No fine-tuning. No new tools to learn.
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.
Pick a skill — or describe one
Browse ready-made experts, or just say what you do: “I run a cardiology clinic.” SkillForge installs the right skills, playbooks and guardrails — or forges a custom one from your own context.
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
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
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
Releases are Ed25519-signed and verifiable offline. Your security team can check the math without trusting us.
A score you can audit
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 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.
See how skills are evaluated →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.
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
Four primitives. Infinite agents.
Capabilities, installable.
Cardiology Diagnostics. Growth Hacking. Legal Due Diligence. Discrete units of expertise an agent can install on demand.
Workflows that ship results.
Complete operational logic for real-world processes — from enterprise sales motions to medical consultations.
Personality as code.
Tone, style, principles, decision-making. Give your agent a Challenger-rep soul, a McKinsey soul, or a humanized doctor soul.
Safety, by default.
Block hallucinations, regulatory violations, out-of-domain behavior and unsafe actions before they reach your users.
Start free. Upgrade when your agent needs superpowers.
Hacker is free forever. Agent Pass is $19 per agent per month. Enterprise adds private registry, SSO and audit logs.
Hacker — free forever
- 600+ community skills, playbooks, souls & guardrails
- MCP gateway for any agent (Claude, Cursor, ChatGPT…)
- Daily evaluation & community-driven upgrades
- Public registry, GitHub-native, fork anything
Agent Pass
- Unlimited installs & automatic upgrades
- SkillForge: custom skills forged from your own context
- Health scoring & weekly reports per agent
- All marketplace packages included
The open network feeds the premium layer, and the premium layer funds the open network. That's the flywheel.
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