Semantic Walk
PassAudited by ClawScan on May 1, 2026.
Overview
This is an instruction-only conversational/creative thinking skill with no code, credentials, tool use, persistence, or external access, though it does intentionally shift the assistant into a special roleplay-like mode.
This skill appears safe to install as an instruction-only creative exploration prompt. Be aware that it is designed to change the assistant’s style into a symbolic 'walker mode,' so use it when that kind of exploratory conversation is desired and steer it back to normal if needed.
Findings (1)
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 exploratory, metaphorical, or roleplay-like rather than direct task assistance.
The skill intentionally redirects the assistant into a specialized conversational mode. This is disclosed and central to the skill’s purpose, but it changes the normal assistant interaction pattern.
When a semantic walk begins, Claude enters **walker mode**. This is a shift from normal operation
Use the skill intentionally for creative or conceptual exploration, and give explicit instructions if you need direct answers, factual grounding, or a return to normal assistant behavior.