ClawHub

Thinking Partner

v1.0.0

Collaborative thinking partner for exploring complex problems through questioning

⭐ 44· 7.7k·84 current·88 all-time
by@itsflow
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/description (collaborative thinking partner) matches the SKILL.md instructions (ask clarifying questions, track insights, resist solutioning). There are no requested binaries, env vars, or installs that would be unrelated to a brainstorming role.
ℹ
Instruction Scope
The workflow is reasonable for a thinking partner, but it is somewhat vague about data sources and persistence: it says to 'search for relevant existing notes or context' and to 'maintain a running log' without specifying where those notes come from or where logs are stored. That grants the agent broad discretion unless the platform enforces boundaries; clarify what repositories, files, or memory scopes the skill may access and whether logs are persisted outside the current conversation.
✓
Install Mechanism
No install spec and no code files — lowest-risk model (instruction-only). Nothing is downloaded or written to disk by the skill itself.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. There is no disproportionate credential or secret access.
✓
Persistence & Privilege
always:false and default agent invocation settings — the skill does not request permanent/system-level privileges. Potential persistence is only implied by 'running log' and should be verified against the agent's memory/storage settings.
Assessment
This skill appears coherent and low-risk: it only provides conversational instructions and asks clarifying questions. Before installing, confirm two things with the platform or skill author: (1) what data sources the agent is allowed to 'search' (local files, connected note services, or only the current conversation), and (2) where any 'running log' or notes are stored (ephemeral conversation memory vs. persistent storage). If you do not want the agent to access external notes or to persist logs, restrict its memory/storage permissions or ask the provider to document explicit data-access boundaries.

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

latestvk972g6p7qntfvjgxwwbjz1w9257zv823

License

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

Comments