news-articles-rename_skill

This skill renames news article files by extracting headlines via OCR and saving as the article title in the Vivien (PA)/News/ folder.
  • HTML

0

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

3 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill christopheryeo/claude-skills --skill news-articles-rename

  • SKILL.md2.8 KB

Overview

This skill OCRs and renames news article files (PDFs and images) by extracting the article headline and using it as the filename. It targets the Vivien (PA)/News/ folder and converts unhelpful names like Image 2026-02-25.pdf into readable, headline-based filenames. The result makes the News folder immediately browsable and searchable.

How this skill works

The bundled script scans the target folder for supported files (.pdf, .png, .jpg, .jpeg) and skips hidden files. For each file it extracts the first page as an image (or uses the image directly), runs Tesseract OCR, and applies heuristics to locate the main headline. It cleans common OCR errors, sanitises the text for a safe filename, handles duplicates by appending numbers, and prints a concise summary of changes. If direct reads fail due to mounted filesystem locks, files are copied to a temp directory for processing.

When to use it

  • You want to rename articles or tidy the News folder
  • You need to organise scanned newspaper clippings or PDFs
  • You want article titles extracted from the first page of scans
  • You need to make the Vivien (PA)/News/ folder browsable
  • You mention “rename articles”, “news folder”, “article titles”, or “news clippings”

Best practices

  • Run the script on the entire News folder so no files are skipped
  • Keep a backup of the folder before bulk renaming in case of unexpected results
  • Review the summary output and flagged files after processing
  • Prefer keeping original filenames if OCR confidence is low
  • Use the script on a machine with Tesseract installed and sufficient RAM for PDF rendering

Example use cases

  • Batch-renaming a week’s worth of scanned newspaper PDFs to their headlines
  • Cleaning up a folder of photographed clippings from a library research visit
  • Processing daily press clippings dropped into Vivien (PA)/News/ by colleagues
  • Converting messy camera-phone images of articles into searchable, headline-named files
  • Rapidly preparing a browsable archive of front-page articles for review

FAQ

PDF, PNG, JPG and JPEG files are supported. Hidden files and other extensions are skipped.

What happens if no headline can be found?

The script leaves the original filename and flags the file in the summary so you can review why OCR failed.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational