Soul Question

Generate deep questions the user can't ask themselves, by finding cracks in their thinking from any context they provide — conversations, meeting notes, jour...

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.

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.