zotero-browse

v1.0.1

Browse, search, and read papers from a local Zotero library. Use when the user wants to: (1) Search their Zotero library by title, author, or keyword, (2) Re...

0· 78·0 current·0 all-time
byLiang Guo@lyononthemoon
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 match the actual behavior: the scripts query a local Zotero SQLite DB and locate PDFs in a local storage folder. The required binary (python3 with PyMuPDF) is appropriate. Note: the repository uses Windows-specific default paths (E:\Refer.Hub\zotero.sqlite and storage) which are plausible for the author's environment but will need adjustment on other machines.
Instruction Scope
SKILL.md and the scripts stay within scope: they open the specified sqlite DB, list/search items, resolve storageHash folders, and extract PDF text with PyMuPDF. They do not access network endpoints, environment secrets, or unrelated system files. Note the instructions and code print paths and file sizes and prompt for an attachment key when using interactive search; they assume user consent to read local files.
Install Mechanism
There is no install spec (instruction-only with code files). That is low-risk. The only external dependency is PyMuPDF (fitz), which must be installed in the Python environment before running; no remote downloads or archive extraction are performed by the skill itself.
Credentials
The skill requests no environment variables or credentials. The operations require filesystem access to the Zotero DB and storage, which is proportionate to its stated purpose.
Persistence & Privilege
always:false and user-invocable:true (default) — the skill is not force-included and does not modify other skills or system config. It performs read-only DB queries (PRAGMA read_only=ON) and reads files; it does not write to system-wide settings or other skills.
Assessment
This skill appears to do what it says: query a local Zotero sqlite DB and extract PDF text. Before installing: (1) ensure you are comfortable granting the agent access to your local Zotero DB and storage folders (the code uses E:\Refer.Hub\... by default — change the --db/--db path or DEFAULT_DB/STORE constants if your library is elsewhere), (2) install Python 3 and PyMuPDF (fitz) in the environment you will run it in, (3) be aware the scripts will print PDF text to stdout or write extracted text to a file if you pass --output, and (4) review the two scripts yourself; they perform only local reads and contain no network calls or secret-exfiltration logic. If you plan to run on a non-Windows system, update paths and the 'py -3' invocation accordingly.

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

latestvk97a5rrdpd5t23135wc49tpv7n84jvnm

License

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

Runtime requirements

📚 Clawdis
Binspython3 (with pymupdf, sqlite3 built-in)

Comments