Extract and structure text from scanned PDFs and document images with a local-first OCR workflow, layout-aware fallbacks, and explicit heavyweight dependency controls.
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./packages/ekko-agent/skills/ocr-and-documents/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow processes scanned PDFs and document images provided via local files or selected URLs, representing user or fetched content rather than monitored feeds or automated outsider-authored inputs.
EKKOLearnAI/hermes-studio
4e4d18e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.