ClawHub

Take The Wheel

v1.0.0

Reverses roles by asking one focused question at a time to guide you step-by-step in creating scripts, plans, briefs, or strategies until completion.

⭐ 0· 167·2 current·2 all-time
by@harvnk
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name and description match the SKILL.md: the skill's goal is to take the lead by asking focused questions. It does not request unrelated binaries, environment variables, or config paths.
ℹ
Instruction Scope
SKILL.md instructs the agent to 'take control' of the conversation, ask one question at a time, and be 'urgent and insistent' until completion. That is consistent with the stated purpose, but the style guidance is broad — the agent may repeatedly prompt users and could elicit sensitive information if the user provides it. The instructions do not direct the agent to read files, env vars, or send data to external endpoints.
✓
Install Mechanism
No install spec and no code files — instruction-only skill. This is the lowest-risk install footprint (nothing is written to disk).
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. There is no disproportionate credential request.
✓
Persistence & Privilege
always is false and the skill is user-invocable (normal). disable-model-invocation is false (agent may invoke autonomously), which is the platform default; there are no other privileged persistence requests.
Assessment
This skill appears coherent and low-risk because it's instruction-only and asks no credentials. Before using it, avoid entering secrets or credentials when answering its questions (it may repeatedly prompt you). Test it first with non-sensitive tasks to confirm the behavior and stop if it asks for unrelated system data. If you need stricter control, only invoke it interactively rather than enabling autonomous invocation in agents that can act without your approval.

Like a lobster shell, security has layers — review code before you run it.

latestvk97631vga4eyawe35me4jx4vb1836grx

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments