Restaurants
v1.0.0Build a personal restaurant system for tracking places to try, favorites, and dining memories.
⭐ 2· 1.1k·1 current·1 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the instructions: the skill manages a local personal restaurant workspace, tracks places to try, favorites, and visit notes. It does not ask for unrelated credentials, binaries, or cloud access.
Instruction Scope
SKILL.md explicitly instructs creating and using a workspace at ~/restaurants/ and defines file formats and read/write behavior. This is within scope for a personal tracker, but it means the agent will create and modify files in the user's home directory and will read those files when making recommendations.
Install Mechanism
There is no install spec and no code files — lowest-risk instruction-only skill. Nothing is downloaded or written to disk by an installer beyond what the agent itself does when following the instructions.
Credentials
The skill requires no environment variables, credentials, or config paths. No disproportionate secrets or unrelated env access are requested.
Persistence & Privilege
always is false and the skill is user-invocable (normal). It will persist user data by creating files under ~/restaurants/, which is expected for its purpose; users should be aware these local files will contain personal data and may be read by the agent when invoked.
Assessment
This skill appears to do what it says: it will create and manage a ~/restaurants/ folder and plain-text markdown entries for places, favorites, and visits. Before installing/using it, consider: 1) Do you want a new directory and files created in your home folder? Back up or choose a different path if not. 2) The files will contain personal notes (preferences, visits); treat them like personal data — encrypt or avoid storing sensitive info if needed. 3) The skill makes no network calls or require credentials, but the agent will read those local files when recommending restaurants; ensure you’re comfortable with the agent having that local-file access. 4) If you prefer a cloud or encrypted store, modify the workflow accordingly. Overall the package is internally consistent and not requesting excessive privileges.Like a lobster shell, security has layers — review code before you run it.
latestvk97e36ppn78rx4dhwnbvf4r6q580y9ye
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🍽️ Clawdis
OSLinux · macOS · Windows