figure-extractor

evernote-backup incrementally syncs notes and notebooks into a local SQLite database, then exports them as ENEX files grouped by notebook or as individual notes. Interrupted synchronization can resume, and later runs download only new changes. Once the local database is populated, exports run entirely offline. The tool supports both Evernote and Yinxiang.

docx-cli gives agents such as Claude and Codex commands for reading, editing, commenting on, and redlining Word documents. Text is addressed through stable paragraph-and-offset locators, while edits mutate the existing OOXML instead of rebuilding the file from a lossy document model. This preserves custom styles, theme colors, embedded objects, and other untouched content, and the resulting revision can still be accepted or rejected in Word. It can be installed as an Agent Skill or used through prebuilt standalone binaries on major desktop platforms.

PDF Email Optimizer converts common Office files when needed, then reduces the resulting PDF toward a requested attachment limit through structural cleanup and controlled image recompression. It keeps the source untouched, reports the chosen strategy and quality trade-offs, and can render before-and-after pages for visual checks. Office inputs require LibreOffice, while unusually tight size targets may require an explicit lossy compression mode.

pubmed-reference-resolver extracts References sections from PDF, DOCX, or TXT files, resolves citations against PubMed, and writes a PubMed-compatible CSV, numbered abstract text, integrated audit report, and journal-mismatch JSON sidecar. It handles common citation styles, PDF line-number noise, an offline MDPI fast path, unresolved-reference preservation, composite-key deduplication, and possible fabricated-citation detection. Python 3.11+, Anthropic, and NCBI credentials are required.