Thinking Framework

Loads any thinker's, leader's, philosopher's, or organization's complete mental operating system directly into the AI — so the AI reasons FROM inside that co...

This skill mostly does what it says (it provides a detailed protocol for 'thinking like X'), but it has two noteworthy red flags: (1) it instructs the model to produce explicit step-by-step chain-of-thought in responses (the 'compensation' guidance), which can reveal internal reasoning and encourage overconfident hallucination — you should disable or ignore any instruction that forces chain-of-thought to be emitted verbatim; (2) it encourages deep psychological profiling (core wounds, defense mechanisms) of named targets. Avoid using the skill to analyze private individuals or anyone for whom you lack strong, public primary sources. If you install it: prefer applying it to historical, public-domain figures or abstract philosophies; require the agent to cite specific primary sources for any psychological claim; turn off any prompts that require explicit chain-of-thought to be output; and review all outputs before using them for decisions involving people (hiring, legal, medical, etc.). If you need higher assurance, ask the author to remove or make optional the chain-of-thought requirement and add explicit guardrails against profiling living private persons.

Type: OpenClaw Skill Name: thinking-framework Version: 1.0.4 The 'thinking-framework' skill is a sophisticated prompt-engineering tool designed to guide an AI in modeling the cognitive and psychological reasoning patterns of specific thinkers, leaders, or philosophies. The bundle consists entirely of Markdown-based instructions and reference architectures (SKILL.md and the references/ directory) that define a structured '15-dimension excavation' process. It does not contain any executable code, requests no sensitive permissions (network, filesystem, or shell), and includes explicit guardrails against impersonation, fabrication of facts, and the generation of harmful content.