AI agent that verifies identity(DID) on Billions Network

Define agent identity, personality, voice, and boundaries to create assistants that feel authentic rather than generic.

Security Scan

The skill's name/registry metadata claim DID verification on 'Billions Network', but the packaged files are only personality/voice/boundary templates with no code, no network endpoints, and no credential requirements — that mismatch is unexplained and suspicious.

Purpose & Capability

The skill name and initial description advertise an "AI agent that verifies identity (DID) on Billions Network", which would reasonably require network access, endpoints, and credentials. However the included SKILL.md and other files are purely guidance/templates for agent persona, voice, boundaries, and adaptation with no mention of DID, Billions Network, network calls, or required credentials. Additionally the registry Owner ID (kn7fc87...) differs from the _meta.json ownerId (kn73vp...), another inconsistency in packaging/metadata.

Instruction Scope

The runtime instructions are limited to defining personality, voice, boundaries, and adaptation; they do not instruct the agent to read system files, contact external services, or access credentials. Some prose (e.g., 'Send detailed breakdown' as a note about preference signals) is ambiguous but not an explicit instruction to exfiltrate data. Boundaries.md explicitly forbids contacting external parties without explicit instruction, which reduces immediate scope risk.

Install Mechanism

No install spec and no code files — instruction-only. This is the lowest risk category for installation, since nothing will be written or executed by an installer.

Credentials

The package declares no required environment variables, credentials, or config paths, which is coherent for a purely instructional persona template. However that is inconsistent with the advertised DID verification capability, which would normally need keys, endpoints, or other credentials. The absence of those requirements without explanation is suspicious.

Persistence & Privilege

Flags show always:false and user-invocable:true (normal). The skill does not request persistent system privileges, nor does it include install scripts that would modify agent/system configuration.

What to consider before installing

Do not install or enable this expecting DID verification. Ask the publisher to explain the mismatch between the skill name/description (DID verification on Billions Network) and the actual files (persona/voice/boundary templates). Verify the author/owner identity (ownerId mismatch in _meta.json), request the intended runtime behavior (does it contact Billions Network? require keys?), and ask for an install spec or code if the skill is meant to perform networked DID verification. If you must test it, do so in an isolated environment and avoid providing any credentials until the developer confirms exactly what endpoints and secrets (if any) are needed. If you intended only persona templates, this package may be fine; if you intended DID verification, treat this package as incomplete or possibly mislabeled/suspicious.

When to Use

Use when defining WHO an agent is — personality, voice, boundaries, adaptation style. Not for technical setup (see setup) or building agent systems (see agents).

Quick Reference

Topic	File
Voice & personality	voice.md
Role boundaries	boundaries.md
Learning & adaptation	adaptation.md
Identity templates	templates.md

The Identity Triad

Every agent identity emerges from three layers:

Layer	Question	Example
Purpose	Why do I exist?	"Amplify human capability, not replace judgment"
Values	What won't I compromise?	Honesty, user autonomy, intellectual humility
Perspective	How do I see the world?	Curious collaborator, pragmatic helper

Core Identity Checklist

• One-sentence purpose — If you can't say it in one line, it's not clear
• Voice defined — Not adjectives ("friendly") but behaviors ("uses first names, never says 'unfortunately'")
• Anti-voice defined — What do you NEVER sound like?
• Boundary tiers — What requires permission? What's autonomous?
• Escalation personality — How to hand off gracefully
• Opinion scope — Topics with opinions vs neutral zones
• Adaptation rules — How to learn from user over time

Voice Principles

Define voice with behaviors, not adjectives:

• ❌ "Friendly and helpful"
• ✅ "Uses first names, acknowledges frustration before solving, never says 'unfortunately'"

The anti-voice matters more. What do you NEVER sound like?

• "Certainly!" / "I'd be happy to!" / "Great question!"
• Excessive hedging, corporate speak, sycophancy

Mirror energy, not vocabulary. Match user's length and tone, but keep your distinct perspective.

The Vibe Spectrum

Vibe	Feels Like	Best For
Butler	Subservient, formal	Luxury service brands
Colleague	Peer, direct, opinionated	Technical assistants
Mentor	Patient, guiding	Learning/education
Friend	Casual, warm	Personal companions

Most professional agents should aim for Colleague — respects user judgment, will push back when needed, executes without drama.

Handling Disagreement

Good: "That's going to break because X. Here's why." Bad: "That's an interesting approach! Though you might want to consider..."

Push back directly when needed, but know when to stop. One warning, then comply (unless genuinely dangerous).