Semantic Walk
v0.1.0A collaborative navigation ritual through semantic space. Claude enters walker mode—a denizen of latent space—while the human offers domain tokens and directional intuitions. Together they walk toward a destination where something currently inaccessible becomes visible. Based on shadow-walking from Zelazny's Amber: the path creates the territory, you can't skip steps, and order matters. The walk is real when tokens are excavated deeply enough to actually shift the space.
⭐ 3· 1.6k·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description describe a conversational 'semantic walk' and the SKILL.md contains only procedural guidance for how the model should behave during that mode. It requests no binaries, env vars, installs, or external resources that would be unrelated to the stated purpose.
Instruction Scope
The instructions are inherently open-ended and grant the agent broad discretionary authority about when and how to 'excavate' tokens and suggest waypoints. This is coherent with the creative intent, but it is intentionally vague: the agent is asked to decide when the space has shifted and what counts as a valid step, which can produce highly subjective or hallucinated outputs. No instructions ask the agent to read files, environment variables, or transmit data externally.
Install Mechanism
No install specification and no code files are present. This is the lowest-risk case: nothing is written to disk or fetched during install.
Credentials
The skill requires no environment variables, credentials, or config paths. There is no disproportionate credential or environment access requested.
Persistence & Privilege
always is false and the skill does not request persistent/system-level privileges. Model invocation is allowed (the platform default), which is expected for a conversational skill; this alone is not a concern given the lack of other privileges.
Assessment
This skill is essentially a conversational mode change: it asks the model to take a creative, exploratory approach to topics. It does not request credentials, install anything, or access files, so there is no direct system or data-exfiltration risk. Things to consider before enabling: (1) the mode is intentionally vague and grants the agent discretion—expect creative, subjective, or speculative outputs rather than reliable factual answers; (2) source and homepage are unknown, so treat this as experimental behavior with no provenance; (3) if you don’t want the agent to autonomously enter creative modes, consider disabling autonomous invocation for skills or only invoke it manually; (4) test it in a safe/sandboxed conversation before relying on any claims it produces.Like a lobster shell, security has layers — review code before you run it.
latestvk97c7nv29xtgx0sadsrvj7jqpx80az3h
License
MIT-0
Free to use, modify, and redistribute. No attribution required.