- Home
- Skills
- Prompt & Skill Engineering
- Agent Skill Architect
Agent Skill Architect
Turn real workflows, SOPs, and expert processes into reliable, testable, production-ready SKILL.md systems.
Free
Works with the AI Agents you already use
Agent Skill Architect
Example session with this skill installed
Turn my company's security incident response SOP into a hardened SKILL.md. I have the PDF manual and a log of the last five incidents. Focus on triage and containment steps.
- Read your context and instructions
- Compiled the agent architect
I have analyzed the Security Incident Response manual and the provided incident logs. I have extracted the triage workflow, identified containment as a fragile operation requiring explicit authorization, and mapped the escalation paths.
Incident Response Skill Architecture
| Layer | Implementation Detail |
|---|---|
| Trigger | Activated by "security-alert", "incident-triage", or "containment-request". |
| Expertise Kernel | NIST 800-61 Rev. 2 framework combined with your internal severity matrix. |
| Workflow Graph | Detection -> Triage (Fragile) -> Containment (Gated) -> Eradication -> Recovery. |
| Decision Map | Escalates to SOC Lead if severity > 3 or if PII is confirmed in logs. |
| Reliability | Deterministic hash checking for IOCs; regex validation for IP/domain artifacts. |
| Security Policy | Read-only access to logs; containment actions require EXPLICIT_APPROVAL token. |
# incident-responder
description: Manages the end-to-end security incident lifecycle from triage to recovery.
# Purpose
Standardize incident handling by enforcing the NIST-based internal SOP.
# Fragility Map
- Severity Scoring: Must use the internal matrix; do not estimate.
- Containment: Irreversible. Requires human gate.
Next steps
- Review the
incident-responder/SKILL.mdfor specific tool-call mappings. - Provide the API schema for your EDR tool to finalize the Containment tool policy.
- Run the generated test suite against the 5 historical incidents provided.
Connects securely to your tools. The creator never sees your data.
About this skill
Agent Skill Architect transforms rough AI Skill ideas, SOPs, business processes, and specialist workflows into production-ready SKILL.md systems. Instead of generating another generic prompt, it extracts the real job, identifies the expertise required, maps the workflow and decision rules, separates fragile steps from flexible ones, defines tool and research requirements, adds verification and quality gates, handles failure and uncertainty, and produces a reusable Skill architecture with evaluation and security controls. It is designed for creators, consultants, developers, automation builders, and teams who want Skills that behave like reliable expert operating systems rather than one-off instructions. Use it when you want to create, redesign, audit, harden, or productize an AI Skill for compatible agents and marketplaces such as Agensi.
Requires clear source evidence or SOPs to function effectively. Cannot guarantee marketplace sales or universal compatibility across all agent executors.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 2 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected