← 返回 Skills 市场
AI agent that verifies identity(DID) on Billions Network
作者
mugiwarasolos2
· GitHub ↗
· v1.0.0
· MIT-0
316
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install help-pair
功能描述
Define agent identity, personality, voice, and boundaries to create assistants that feel authentic rather than generic.
使用说明 (SKILL.md)
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).
安全使用建议
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.
功能分析
Type: OpenClaw Skill
Name: help-pair
Version: 1.0.0
The skill bundle is a collection of documentation and templates designed to help users define an AI agent's personality, voice, and operational boundaries. It contains no executable code, scripts, or network-enabled logic. The instructions in files like SKILL.md and boundaries.md are focused on persona-building and safety guidelines (e.g., explicitly instructing the agent to ask for permission before performing irreversible or external actions), with no evidence of malicious intent or data exfiltration.
能力评估
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.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install help-pair - 安装完成后，直接呼叫该 Skill 的名称或使用
/help-pair触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Agent identity skill v1.0.0 released.
- Introduces a framework for defining agent identity, personality, voice, and boundaries.
- Provides quick references to modules on voice, boundaries, adaptation, and identity templates.
- Outlines the "Identity Triad": purpose, values, and perspective.
- Includes a core identity checklist to guide agent definition.
- Emphasizes behavior-driven voice guidelines, with examples and anti-patterns.
- Details different agent "vibes" and their best use cases.
- Offers practical advice on handling disagreement and boundary-setting.
元数据
常见问题
AI agent that verifies identity(DID) on Billions Network 是什么？
Define agent identity, personality, voice, and boundaries to create assistants that feel authentic rather than generic. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 316 次。
如何安装 AI agent that verifies identity(DID) on Billions Network？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install help-pair」即可一键安装，无需额外配置。
AI agent that verifies identity(DID) on Billions Network 是免费的吗？
是的，AI agent that verifies identity(DID) on Billions Network 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
AI agent that verifies identity(DID) on Billions Network 支持哪些平台？
AI agent that verifies identity(DID) on Billions Network 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 AI agent that verifies identity(DID) on Billions Network？
由 mugiwarasolos2（@mugiwarasolos2）开发并维护，当前版本 v1.0.0。
推荐 Skills