← 返回 Skills 市场
Soul Question
作者
jerryChenyipeng
· GitHub ↗
· v1.0.0
· MIT-0
200
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install soul-question
功能描述
Generate deep questions the user can't ask themselves, by finding cracks in their thinking from any context they provide — conversations, meeting notes, jour...
安全使用建议
This skill is internally consistent and only needs the text you paste to generate questions. Before installing or using it, remember: any content you paste will be processed by whatever model/runtime the agent uses — if that runtime is a remote API (e.g., a cloud-hosted Claude or other LLM), your text may be transmitted to that provider. The README asserts local/no-external calls, but that depends on how your agent is hosted. Avoid pasting secrets, passwords, or highly sensitive PII unless you confirm the model runs locally and no external telemetry occurs. If you need stronger guarantees, verify the agent runtime (local vs cloud) and data-handling policies first.
功能分析
Type: OpenClaw Skill
Name: soul-question
Version: 1.0.0
The 'soul-question' skill is a purely logic-based prompt engineering tool designed to analyze user-provided text for cognitive biases and contradictions. The SKILL.md file contains well-defined instructions for the AI agent to generate reflective questions without any directives for data exfiltration, unauthorized command execution, or prompt injection attacks. The included test-skill.sh is a standard validation script that performs local file checks and content linting using grep and python3, with no suspicious network activity or obfuscated code.
能力评估
Purpose & Capability
Name/description claim to generate deep, context-anchored questions from user-supplied text. The skill requires no binaries, env vars, or external services — this is coherent and proportionate for an instruction-only text-processing skill.
Instruction Scope
SKILL.md only instructs the agent to read the user-provided text and produce 1–3 anchored questions; it does not tell the agent to read unrelated files, secrets, or to call external endpoints. The rules and quality gates are explicit and narrowly scoped.
Install Mechanism
No install spec (instruction-only), so nothing is written to disk by an installer. There is a benign test-skill.sh that validates documentation/structure; it is a local validation script and does not contact external hosts.
Credentials
Requires no environment variables, credentials, or config paths. Declared privacy claims (no external calls/storage) are consistent with an instruction-only skill, but see user guidance about runtime model handling.
Persistence & Privilege
always:false and no special privileges requested. The skill does not attempt to modify other skills or system-wide agent settings; autonomous model invocation is permitted (platform default) but not combined with other concerning privileges.
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 soul-question - 安装完成后，直接呼叫该 Skill 的名称或使用
/soul-question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
Initial release
元数据
常见问题
Soul Question 是什么？
Generate deep questions the user can't ask themselves, by finding cracks in their thinking from any context they provide — conversations, meeting notes, jour... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 200 次。
如何安装 Soul Question？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install soul-question」即可一键安装，无需额外配置。
Soul Question 是免费的吗？
是的，Soul Question 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Soul Question 支持哪些平台？
Soul Question 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 Soul Question？
由 jerryChenyipeng（@chenyipeng1）开发并维护，当前版本 v1.0.0。
推荐 Skills