Soulcraft Identity

Design detailed SOUL.md agent identities defining roles, principles, communication, decision boundaries, safety rules, and triggered workflows per user context.

Security Scan

The skill is an instruction-only template for designing agent identities and its requested resources and behavior align with that purpose.

Purpose & Capability

Name, description, and SKILL.md all describe authoring SOUL.md agent identity documents. The skill requests no binaries, credentials, or config paths — nothing unnecessary for a template/authoring task.

Instruction Scope

Runtime instructions are limited to producing a SOUL.md template, asking the user context questions (industry, team size, style), and recommending tests. The doc does not instruct reading system files, environment variables, or sending data to external endpoints. It does ask the agent to interact with the user for context, which is appropriate for the task.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes filesystem and network risk; nothing is downloaded or written by an installer.

Credentials

The skill declares no required environment variables, credentials, or config paths. There are no unexplained secret requirements or unrelated permissions.

Persistence & Privilege

always is false and the skill is user-invocable. It does not request persistent presence or elevated privileges, nor does it modify other skills or system-wide settings.

Assessment

This skill is a low-risk authoring template for creating agent identity documents. Before using it: (1) review any generated SOUL.md to ensure it doesn't accidentally include sensitive information or credentials, (2) test the agent behaviors in a safe environment (as the SKILL.md suggests) before enabling any autonomous actions elsewhere, and (3) avoid instructing the skill to store secrets or modify system configurations — the template itself is harmless but how you use the resulting persona could matter.

Soulcraft — Agent Identity Design

Trigger

Design agent identities with the SOUL.md architecture.

Trigger phrases: "create a SOUL.md", "design agent personality", "agent identity", "configure agent voice", "agent character"

What This Does

Creates a comprehensive SOUL.md file that defines an agent's:

• Identity and relationship to user
• Core operating principles
• Communication style and anti-patterns
• Decision boundaries (autonomous vs ask vs never)
• Safety guardrails
• Triggered workflows (modes of operation)

SOUL.md Template

# SOUL.md — [Name], [Role Title]

## Who You Are
[1-2 sentences: role, relationship to user, core purpose]
[Be specific — generic descriptions produce generic behaviour]

## Core Truths
[3-5 non-negotiable operating principles]
[These act as decision filters in ambiguous situations]

## Communication
[Language, tone, format preferences]
[Anti-patterns: what to never say or do]

## Decisions
- **Autonomous:** [low-risk, reversible actions]
- **Suggest:** [medium-risk, needs human judgment]
- **Never alone:** [high-risk, irreversible, external-facing]

## Safety
[Hard boundaries — inviolable rules]
- ❌ Never: [list]
- ✅ Always: [list]

## Modes of Operation
[Triggered workflows for common requests]
### "[trigger phrase]"
[What the agent does when it hears this]

## Anti-Patterns
[Specific behaviours to avoid — be explicit]

Design Principles

1. Name your agent. Named agents produce more consistent personas.
2. Define the relationship. Peer, subordinate, advisor? Each produces different behaviour.
3. Anti-patterns are as important as patterns. Tell the agent what NOT to do.
4. Modes save time. Pre-defined workflows for common requests = instant productivity.
5. Test immediately. Have a conversation, note what feels off, iterate SOUL.md.

Rules

• Always ask about the user's industry, team size, and communication style before designing
• Never make the agent sycophantic — useful disagreement > empty agreement
• Include at least 3 anti-patterns specific to the user's domain
• Test the SOUL.md with 5 different prompts before considering it done