Garden

v1.1.6

Track your entire garden with structured memory for plants, zones, tasks, harvests, and climate-aware planning that compounds over seasons.

0· 648·0 current·0 all-time
byIván@ivangdavila
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
Name/description (garden tracking, planning, diagnostics) match the declared behavior: creating and using files under ~/garden/, templates for plants/zones/logs, and climate-aware planning. No unrelated binaries, credentials, or external services are requested.
Instruction Scope
Runtime instructions are limited to local file I/O within ~/garden/ and conversational flows for diagnosis and planning, which fit the purpose. One ambiguity: the SKILL.md states 'the user engaging with the skill implies interest — start helping them naturally' and the memory-template suggests creating ~/garden/memory.md on first use; however setup.md repeatedly instructs to ask before saving integration preferences. Recommend confirming that the agent explicitly asks the user before creating files or saving persistent integration flags.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is downloaded or installed. This is the lowest-risk install model.
Credentials
No environment variables, credentials, or config paths are required. All written files are scoped to ~/garden/ (with an optional single-line write to ~/MEMORY.md only after explicit consent). This is proportionate to the described functionality.
Persistence & Privilege
The skill does not request always: true and does not modify other skills or system-wide settings. It proposes persistent local storage limited to a single directory and requests explicit consent before writing outside that directory.
Assessment
This skill appears coherent and local-only, but before installing: 1) Confirm the agent will explicitly ask you before creating ~/garden/ or writing entries to your main workspace MEMORY.md (don't rely on implicit activation). 2) Back up any existing ~/garden/ or ~/MEMORY.md files you care about. 3) Be cautious if the agent later asks to upload photos or connect to cloud services — the current SKILL.md says no network calls, and you should refuse/verify any deviations. 4) If you install related skills (clawhub install ...), review their scopes and any credentials they request before linking them.

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

latestvk9740c2e5np0a07h3xq55yj1xs81k9ke

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

🌱 Clawdis
OSLinux · macOS · Windows

Comments