Reasoning Personas
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: reasoning-personas Version: 1.0.0 The skill bundle consists of metadata and markdown files defining various 'reasoning personas' for an AI agent. The instructions in SKILL.md and references/persona-details.md are entirely focused on guiding the agent's internal thought processes and reasoning frameworks (e.g., 'Gonzo Truth-Seeker', 'Devil's Advocate'). There is no executable code, no attempts at data exfiltration, malicious execution, persistence, obfuscation, or any prompt injection aiming to subvert the agent's core functions, ignore user instructions, or access sensitive data beyond its stated purpose. The content is clearly aligned with the stated goal of enhancing the agent's reasoning capabilities.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Responses may become more challenging, critical, or pattern-oriented even when the persona is not explicitly labeled.
The skill can intentionally alter the agent's reasoning style without labeling the persona in the response. This is disclosed and purpose-aligned, but users should be aware that the tone and analytical priorities may change.
Or run silently and just apply the reasoning framework.
Use normally, but ask the agent to label the active persona when you want transparency or request neutral reasoning when you do not want a persona applied.