ClawHub

Decision Mental Models

v0.1.0

Apply the most relevant mental models (First Principles, Inversion, Second-Order Thinking, Occam's Razor, and 16 others) to any problem or decision, surfaces...

⭐ 0· 88·0 current·0 all-time
by@arbazex
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 skill's name and description match the SKILL.md and README: both describe selecting and applying 2–3 mental models from a 20-item library. There are no unexpected required binaries, environment variables, or config paths.
✓
Instruction Scope
The runtime instructions are narrowly scoped to (1) extracting the user's problem, (2) selecting relevant models, and (3) applying them to the user's details. The instructions do not direct the agent to read files, system state, or external endpoints, and they limit clarifying questions to one.
✓
Install Mechanism
No install spec or code files are provided — this is instruction-only. Nothing will be downloaded or written to disk by an installer, which minimizes risk.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. All declared and implied resource needs are proportionate to an instruction-only reasoning helper.
✓
Persistence & Privilege
The skill does not request always: true and does not claim system-wide configuration changes. Autonomous invocation (disabled-model-invocation is false) is the platform default and is not, by itself, a concern here.
Assessment
This skill is instruction-only and appears safe and coherent for its purpose. Before using it, avoid pasting private secrets, account credentials, or other sensitive data into queries — the skill operates on whatever you supply. If you want added privacy, remove personal identifiers from examples you provide. If future versions add downloads, external API calls, or new required environment variables, reassess — those would change the risk profile.

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

latestvk9761n86q8zthj3e3aaprrxt8583dyfr

License

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

Runtime requirements

🧠 Clawdis

Comments