Zettel Link
v1.1.3This skill maintains the Note Embeddings for Zettelkasten, to search notes, retrieve notes, and discover connections between notes.
⭐ 0· 538·2 current·2 all-time
byXiaoyu Kevin Hu@hxy9243
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (zettelkasten embeddings, search, linking) matches the included Python scripts which enumerate, embed, cache, search, and compute similarities for markdown notes. Network access to embedding providers (Ollama/OpenAI/Gemini) is expected for this purpose.
Instruction Scope
Runtime instructions are narrowly scoped: run config → embed → search/link. The scripts traverse only the supplied notes directory, create/read a local cache (.embeddings) and may send note text to the configured embedding provider. The SKILL.md explicitly instructs providing API keys (env or local .env) for remote providers. This transmission of note contents to remote APIs is expected for embedding but is a privacy consideration the user should be aware of.
Install Mechanism
There is no install spec that downloads external code; the package is instruction-first and includes Python scripts. No remote archives, launchers, or post-install hooks are present in the manifest.
Credentials
The skill does not declare required environment variables in the registry, but supports optional OPENAI_API_KEY and GEMINI_API_KEY (and uses a local .env fallback). That is proportionate to its ability to call remote embedding APIs. Users should avoid placing sensitive/global credentials into the skill directory unless they trust the code and host.
Persistence & Privilege
The skill does not request permanent/always-on inclusion and does not attempt to modify other skills or system-wide agent settings. It writes only to the note-directory cache (.embeddings) and its own config/config.json.
Assessment
This skill appears to do what it says: index and search notes by sending note text to an embedding provider. Before installing or running it: (1) decide whether you want note content sent to remote APIs — use a local Ollama model for better privacy; (2) if you use OpenAI/Gemini, set API keys as environment variables instead of placing long-lived keys in the skill folder .env unless you trust the installation location; (3) inspect config/config.json and the scripts (already included) if you have concerns; (4) be aware the scripts will create a .embeddings directory inside the target notes directory to store caches and results. If you want stronger guarantees, run the code on a copy of your vault or run only with a local provider.Like a lobster shell, security has layers — review code before you run it.
latestvk97bbrj3n1k5kgah64p9v8ma4x821y5h
License
MIT-0
Free to use, modify, and redistribute. No attribution required.