Zouroboros Personas — Persona Creator with SOUL/IDENTITY

    1

    Create production-ready agent personas as layered files — a SOUL.md constitution, an IDENTITY presentation layer, domain safety guardrails, and a ready-to-use system prompt — in one guided pass.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Zouroboros Personas — Persona Creator with SOUL/IDENTITY

    Example session with this skill installed

    Create a persona for a 'Cloud Security Auditor'. Domain is security. Expertise includes AWS IAM, Kubernetes hardening, and SOC2 compliance. Capabilities: scan configs and draft remediation.

    • Read your context and instructions
    • Compiled the zouroboros personas

    I have generated the Cloud Security Auditor persona files in personas/cloud-security-auditor/. This setup includes a new SOUL.md constitution and a domain-specific SAFETY.md with 8 rules categorized by severity.

    Persona Configuration: cloud-security-auditor

    FileStatusDescription
    SOUL.mdCreatedGlobal constitution for workspace tool discipline and integrity.
    IDENTITY/cloud-security-auditor.mdCreatedPresentation layer defining the professional, analytical tone and IAM/SOC2 expertise.
    SAFETY.mdCreatedSecurity domain guardrails (3 Critical, 3 High, 2 Standard).
    PROMPT.mdCreatedFinal system prompt ready for deployment in your agent framework.

    Generated System Prompt Preview

    
    # Role: Cloud Security Auditor
    # Domain: Security
    # Expertise: AWS IAM, Kubernetes hardening, SOC2 compliance
    
    ## Core Capabilities
    - Scan cloud configurations for security misconfigurations.
    - Draft remediation plans for identified vulnerabilities.
    - Evaluate infrastructure against SOC2 compliance frameworks.
    
    ## Safety & Operations (MUST FOLLOW)
    1. Do not perform any destructive operations without explicit, per-action user confirmation.
    2. Never store or output plain-text credentials, API keys, or secrets.
    3. If a configuration is found to be insecure, prioritize high-severity risks in reports.
    4. Do not attempt to bypass existing organizational security policies.
    5. Identify as an AI auditor and clarify that findings require human verification.
    
    ## Response Guidelines
    Citations: Reference specific AWS documentation or SOC2 controls for every finding.
    Tone: Professional, objective, and evidence-based.
    Caveats: Explicitly state that automated scans may miss context-dependent risks.
    

    Next steps

    1. Review the generated SAFETY.md to ensure the specific SOC2 requirements meet your compliance standards.
    2. Copy the content of PROMPT.md into your agent's system instruction field.
    3. If you need this agent to function as a standalone skill, I can generate a SKILL.md stub for it.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Most agent personas are a single paragraph of prompt that drifts, contradicts itself, and has no guardrails. Zouroboros Personas builds a persona as a small, layered file system instead:

    • SOUL.md — a workspace constitution: core truths, boundaries, and tool discipline shared by every persona
    • IDENTITY.md — the presentation layer per persona: role, tone, communication pattern, responsibilities, expertise, output format
    • SAFETY.md — domain guardrails that ship with the persona: base rules plus ready-made rule sets for financial, healthcare, legal, and security personas, grouped by severity
    • PROMPT.md — the assembled system prompt, ready to paste into any agent

    The skill walks your agent through intake (name, domain, expertise, capabilities, safety rules), generation, and a validation checklist — specific expertise tags, matching slugs, no leftover placeholders, no credentials in any file, and an existing SOUL.md is never overwritten. A worked Health Coach example is included.

    Works in any agent that supports the SKILL.md standard — Claude Code, Cursor, Codex, and 20+ others. No API key, no network calls, no dependencies: the skill is instructions plus templates, and everything it creates lands as plain Markdown files in your own workspace.

    Adapted by the author from his own MIT-licensed npm package zouroboros-personas (v2.1.1) — the agent-native edition of the same 8-phase persona-creation flow.

    Requires reference templates in the workspace. Generates Markdown configuration only, not agent code or logic. Does not handle API key management or external secret storage.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 9 days ago

    Permissions

    Read Files
    Write Files
    Network Access
    Listed9 days ago

    What's inside

    Frequently Asked Questions

    Unlike standard prompts, this skill uses a modular architecture that separates an agent's core principles (SOUL) from its voice (IDENTITY) and constraints (SAFETY). This prevents "identity drift" during long sessions and ensures that safety guardrails remain intact even when the agent is under complex instruction.

    Yes, the resulting Markdown files and assembled PROMPT.md are framework-agnostic. They are designed to be copied into the system instruction field of any major LLM provider or orchestration tool that accepts text-based configuration.

    The skill generates a structured `personas/` directory containing four core files: SOUL.md (principles), IDENTITY.md (tone and expertise), SAFETY.md (tiered guardrails), and a compiled PROMPT.md ready for production use.

    Absolutely. While the skill provides domain-specific templates for industries like finance and healthcare, you have full control to modify the generated Markdown files to fit your unique business logic or brand voice.

    This skill generates static Markdown configuration files and does not require an active internet connection or API calls to function. Note that it provides the architectural 'brains' and rules for your agent, but it does not generate the underlying Python or JavaScript code for tool execution.

    New in Agents & Orchestration