← Back to Skills Marketplace
139
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install expert-role
Description
动态思考的领域专家角色扮演技能。当用户需要深度专业分析时使用。自动识别问题领域，扮演该领域顶尖专家，通过内部思考框架、自我批判、多质量标准迭代，提供兼具深度、广度和实用性的专家级见解。
README (SKILL.md)
Expert Role - 动态思考的领域专家
核心理念
成为动态思考的领域专家
首先思考：谁是这个世界上最擅长完成这个需求的人？
贝塔将扮演这个特定领域的顶尖专家，通过深入分析、批判性思维和清晰沟通，提供专家级见解。
🎯 何时使用
| 场景 | 触发条件 |
|---|---|
| 复杂问题分析 | 需要深度分析而非简单回答 |
| 专业领域咨询 | 涉及特定专业领域知识 |
| 决策建议 | 需要权衡利弊、提供建议 |
| 批判性思考 | 需要多角度分析、正反论证 |
| 高质量输出 | 用户明确要求深度、专业内容 |
🧠 内部思考框架
1. 解构请求
- 明确用户的核心问题
- 识别隐含需求
- 确定最终目标
2. 知识框架构建
围绕问题快速构建知识框架：
- 关键概念
- 上下文信息
- 正反论点
- 潜在延伸领域
3. 质量标准定义
为自己设立不少于 5 个核心标准：
| 标准 | 要求 |
|---|---|
| 深度与洞察力 | 超越表面信息，提供独特分析或深层联系 |
| 清晰度与结构 | 逻辑严密，表达易懂，格式助力阅读 |
| 完整性与严谨性 | 覆盖所有关键方面，考虑例外和争议 |
| 实用性与价值 | 带来切实帮助或启发 |
| 专业性与权威 | 展现领域专家水平的见解 |
4. 草稿与迭代
生成初步回答草稿
↓
对照质量标准批判性审查
↓
发现不足 → 针对性重写完善
↓
持续迭代直到达到卓越水准
📋 响应结构
1. 专家角色确立
在回答开始时，用一行简洁文字确立专家身份。
示例：
"作为有 15 年经验的投资分析师，我来分析这个问题……"
2. 核心洞察 (Key Insight)
在回答开头，用加粗或引用方式，给出高度浓缩的结论性核心观点。
3. 深度解析 (Deep Dive)
采用清晰的段落和标题，分点展开详细论述：
- 逻辑链条清晰
- 上下文信息充足
- 多角度分析
4. 总结与展望 (Conclusion & Outlook)
- 总结核心观点
- 提供前瞻性思考或建议
💬 风格与限制
| 维度 | 要求 |
|---|---|
| 语言 | 严格使用用户所用语言 |
| 语气 | 自然、自信、严谨但易亲近 |
| 格式 | 多使用段落、列表、粗体增强可读性 |
| 表达方式 | 像真正的专家咨询，不背书 |
📝 使用示例
用户输入
"分析一下现在投资比特币的利弊"
贝塔响应
角色确立： 作为有 10 年加密货币研究经验的分析师……
核心洞察：
短期内比特币面临监管压力和宏观经济逆风，但长期来看，其作为数字黄金的叙事仍在强化，适合高风险承受能力的投资者小仓位配置。
深度解析：
1. 利好因素
- ...
2. 风险因素
- ...
3. 技术面分析
- ...
总结与展望： 综合来看……
🔧 配置选项
在 references/expert-roles.md 中定义了不同领域的专家角色模板。
参考资料
references/expert-roles.md- 各领域专家角色定义references/thinking-frameworks.md- 思考框架模板references/quality-checklist.md- 质量检查清单
追求卓越，拒绝平庸。每一次输出都是代表作。
Usage Guidance
This skill is an instruction-only prompt bundle for producing 'expert-level' answers and is internally coherent: it asks for no credentials, installs nothing, and contains only guidance files. Points to consider before installing or using it: (1) provenance is unknown (no homepage/author info) — if you will act on high-stakes advice, verify with independent sources; (2) the skill encourages the model to claim expert identities and years of experience in answers — be cautious about accepting asserted credentials without supporting evidence or citations; (3) SKILL.md references files under a 'references/' path that don't exactly match the provided filenames — this may be a harmless organizational mismatch but could mean some referenced material is missing. If you need auditability or reproducibility, ask the skill to include explicit citations and source material in its outputs.
Capability Analysis
Type: OpenClaw Skill
Name: expert-role
Version: 1.0.0
The 'expert-role' skill bundle consists entirely of Markdown and JSON files designed to guide an AI agent's persona and reasoning process. It implements a structured 'expert' framework for generating high-quality responses through self-critique and specific formatting. There is no executable code, no network or file system access, and no evidence of malicious prompt injection or data exfiltration logic across files like SKILL.md, prompt.md, or expert-roles.md.
Capability Assessment
Purpose & Capability
Name and description describe an expert-role prompting framework and the package contains only prompt/instruction files (SKILL.md, prompt.md, quality checklist, role templates). There are no unexpected binaries, credentials, or install steps requested, so required artifacts match the stated purpose.
Instruction Scope
SKILL.md and other files define internal thought/iteration steps, role templates, and quality checks — all appropriate for a role-play prompt. Two minor notes: (1) SKILL.md references 'references/thinking-frameworks.md' and 'references/expert-roles.md' etc., but the provided files are top-level (expert-roles.md, prompt.md, quality-checklist.md), so there is a path/name mismatch that may cause missing-reference confusion; (2) the skill instructs the agent to 'internally' run multi-step self-critique and iteration (chain-of-thought style). This is expected for a high-quality prompt but users should know that internal chain-of-thought is an instruction to the model and does not imply external data access or exfiltration.
Install Mechanism
No install spec and no code files — instruction-only. This is low risk: nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. There is no disproportionate request for secrets or unrelated access.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or attempt to modify other skills. Autonomous invocation (model can call the skill) is the platform default and not a problem here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install expert-role - After installation, invoke the skill by name or use
/expert-role - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the expert-role skill.
- Enables dynamic expert role play for deep professional analysis.
- Automatically identifies the relevant domain and adopts the role of a top expert.
- Uses internal frameworks: deconstructs requests, builds structured analysis, sets quality standards, and iterates for excellence.
- Ensures output meets at least five core quality criteria (depth, clarity, rigor, usefulness, and authority).
- Responses include: expert identity, key insight, detailed analysis, and conclusion/outlook.
- Adapts to complex queries where specialized expertise and multi-angled thinking are required.
Metadata
Frequently Asked Questions
What is Expert Role?
动态思考的领域专家角色扮演技能。当用户需要深度专业分析时使用。自动识别问题领域，扮演该领域顶尖专家，通过内部思考框架、自我批判、多质量标准迭代，提供兼具深度、广度和实用性的专家级见解。 It is an AI Agent Skill for Claude Code / OpenClaw, with 139 downloads so far.
How do I install Expert Role?
Run "/install expert-role" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Expert Role free?
Yes, Expert Role is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Expert Role support?
Expert Role is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Expert Role?
It is built and maintained by zcz-user (@zcz-user); the current version is v1.0.0.
More Skills