Intuition
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: intuition Version: 1.0.0 The OpenClaw AgentSkills bundle 'intuition' is benign. All files (SKILL.md, domains.md, feedback.md, safeguards.md, techniques.md) are documentation and instructions aimed at shaping the AI agent's 'cognitive' style and response patterns, focusing on rapid, pattern-based judgments. There are no instructions for system interaction, data exfiltration, malicious execution, persistence, or any other harmful activities. The Python code snippet in `techniques.md` is an illustrative example of how to prompt an LLM, not an instruction for the agent to execute code.
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.
You may receive a short, confident judgment even when a more cautious explanation would be useful.
The skill intentionally makes answers sound decisive and withholds explanation unless requested; this matches its stated intuition purpose but can increase user overtrust.
"Commit — Deliver confidently without hedging" and "Justify only if asked"
Use this skill for low-stakes quick reads; for consequential choices, explicitly ask the agent to analyze, compare alternatives, and explain uncertainty.
If your agent has memory enabled, details about your judgments or outcomes could be retained and influence later responses.
The skill encourages creating a calibration record that could become persistent context if the host agent stores it; this is purpose-aligned but may capture sensitive decision history.
"For high-stakes intuitive calls: 1. Record the intuition 2. Record confidence level 3. Record domain 4. Record outcome when known 5. Review monthly"
Confirm where any calibration notes are stored, avoid recording sensitive details unnecessarily, and clear or review memory if the judgments involve private matters.