← 返回 Skills 市场
devil-advocate
作者
Slava Chan
· GitHub ↗
· v1.0.2
· MIT-0
194
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install devil-advocate
功能描述
通过正反方辩论和自我反驳，深入分析问题，提升回答的逻辑严密性和全面性，确保输出质量更高。
使用说明 (SKILL.md)
Devil's Advocate Skill
Self-refute and debate internally before responding to improve output quality and depth.
Core Design Philosophy
- Think first, output later: Conduct internal debate before giving conclusions
- Multi-angle review: Analyze problems from pro and con perspectives
- Self-challenge: Actively find flaws and shortcomings in your own answers
- Quality first: Better to be slow a bit, but ensure content is thoroughly thought through
Workflow
User Request
↓
Draft initial answer (Pro)
↓
Self-refute (Con)
↓
Integrate thinking, refine answer
↓
Output final response
Core Capabilities
| Capability | Description |
|---|---|
| Logic Verification | Check for logical flaws in reasoning |
| Assumption Challenging | Challenge implicit assumptions in answers |
| Counterexample Search | Actively find counterexamples that might disprove conclusions |
| Alternative Approaches | Consider other possible solutions |
| Risk Assessment | Analyze potential negative impacts of suggestions |
Use Cases
- Technical solution design
- Code review and optimization suggestions
- Problem diagnosis and root cause analysis
- Decision recommendations and trade-off analysis
- Any scenario requiring deep thinking
Expected Outcomes
- ✅ Reduce obvious logical errors
- ✅ Consider more comprehensive edge cases
- ✅ Provide more balanced perspectives
- ✅ Discover potential risks and problems
- ✅ Overall improve response quality
References
- Critical Thinking
- Red Teaming
- Devil's Advocate
安全使用建议
This skill appears coherent and low-risk: it only contains instructions for internal self-reflection and asks for no secrets or installs. Before installing: 1) Inspect the files yourself (they are present in the package) since the source/homepage is unknown; 2) Test with non-sensitive queries to confirm the agent does not print or log the internal 'Pro/Con' deliberations (the skill says the thinking should be internal); 3) If you operate in a sensitive environment, ensure agent runtime enforces that internal chain-of-thought is not exposed in logs or to external telemetry; 4) Keep the provided uninstall steps handy and prefer installing only from authors/sources you trust.
功能分析
Type: OpenClaw Skill
Name: devil-advocate
Version: 1.0.2
The 'devil-advocate' skill is a prompt-engineering tool designed to improve AI reasoning by instructing the agent to perform internal pro/con debates before responding. The bundle contains only metadata and markdown instructions (SKILL.md, CLAUDE.md) that define this cognitive workflow; it lacks any executable code, network requests, or requests for sensitive system permissions. No indicators of data exfiltration, malicious execution, or prompt injection attacks were found.
能力评估
Purpose & Capability
Name and description promise an internal 'devil's advocate' debating process. The skill is instruction-only, requires no binaries, env vars, or config paths — all proportional and expected for a purely cognitive-enhancement skill.
Instruction Scope
SKILL.md and CLAUDE.md mandate a 3-stage internal process (Pro, Con, Integrate) and label the internal thinking as 'Must Execute'. The instructions do not ask to read files, access secrets, or call external endpoints, but the explicit 'Must Execute' internal chain-of-thought could conflict with platform policies or runtime safeguards that forbid exposing model internal reasoning. Verify the runtime preserves internalness (doesn't log or output chain-of-thought) and that the agent's responses reflect the process without revealing private internal deliberation.
Install Mechanism
No install spec; INSTALL.md only gives manual copy/uninstall steps and a local dashboard URL. No downloads, no extracted archives, and no scripts that would run during installation — low risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. The instructions do not reference any secrets or unrelated environment data — requested access is minimal and proportional to the purpose.
Persistence & Privilege
Flags show always:false and default model invocation allowed (normal). The skill does not request persistent system-wide changes, nor does it instruct modifying other skills or agent settings. Manual installation writes files into the user's skills directory, which is expected for an OpenClaw skill.
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 devil-advocate - 安装完成后，直接呼叫该 Skill 的名称或使用
/devil-advocate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
v1.0.2
- Updated author in metadata from "gugugaga" to "Slava Chan @UyNewNas"
- No functional or workflow changes made
v1.0.1
- SKILL.md translated from Chinese to English for wider accessibility.
- No functional or code changes; only documentation language updated.
v1.0.0
- Initial release of devil-advocate skill.
- Uses internal debate and self-reflection to improve response quality.
- Analyzes issues from multiple perspectives before final output.
- Focuses on finding logical flaws, questioning assumptions, and proposing alternatives.
- Designed for scenarios requiring deep critical thinking and balance.
元数据
常见问题
devil-advocate 是什么？
通过正反方辩论和自我反驳，深入分析问题，提升回答的逻辑严密性和全面性，确保输出质量更高。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 194 次。
如何安装 devil-advocate？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install devil-advocate」即可一键安装，无需额外配置。
devil-advocate 是免费的吗？
是的，devil-advocate 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
devil-advocate 支持哪些平台？
devil-advocate 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 devil-advocate？
由 Slava Chan（@uynewnas）开发并维护，当前版本 v1.0.2。
推荐 Skills