Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Switched PDF parsing from scripts/parse_pdf.py to the new scripts/parse_pdf_gemini.py, enabling Gemini Vision OCR and layout analysis. - Removed the old parse_pdf.py script and added the new parse_pdf_gemini.py script. - Updated documentation to reflect the new PDF parsing approach using Gemini for study material and homework assistance.
What This Skill Does
A Japanese learning assistant covering vocabulary, grammar explanations, quizzes, and conversation practice. It parses PDF and DOCX course materials to extract content and persist it into local reference files. OCR translation from uploaded images is also supported.
Unlike a generic chatbot, it ingests actual course materials and saves extracted vocabulary and grammar to local reference files, building a knowledge base tied to the user's specific curriculum over time.
When to use it
- Reviewing N5 vocabulary before a class quiz
- Getting a grammar explanation for て-form conjugations with examples
- Uploading a homework PDF for guided help without direct answers
- Translating text from a photo of a Japanese sign or menu
- Running a quiz on vocabulary from a recently ingested lesson
Example Workflow
Here's how your AI assistant might use this skill in practice.
User says 'Bantuin PR ini' and attaches a Japanese homework PDF
- 1Parses the PDF using parse_pdf_gemini.py with Gemini Vision OCR
- 2Identifies the homework tasks and questions in the document
- 3Extracts new vocabulary and grammar points from the material
- 4Appends vocabulary to references/vocab.md and grammar rules to references/grammar.md
- 5Explains the underlying concepts and guides the user toward answers using similar examples
Conceptual explanations with analogous examples for each task, new material saved to reference files for future quizzes
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.