Japanese Tutor

Interactive Japanese learning assistant. Supports vocabulary, grammar, quizzes, roleplay, PDF/DOCX material parsing for study/homework help, and OCR translation.

Security Scan

The skill mostly matches a tutoring purpose, but it contains undeclared external API usage and missing dependency/metadata declarations that don't align with the published requirements.

Purpose & Capability

The skill's stated purpose (Japanese tutoring, PDF/DOCX parsing, OCR) is coherent with the included scripts. However, the code requires access to a Gemini (Google) API key for PDF parsing (GEMINI_API_KEY) which is not listed in the skill's required environment variables or metadata. Also SKILL.md references scripts named parse_pdf.py while the repository contains parse_pdf_gemini.py — a mismatch suggesting sloppy metadata.

Instruction Scope

SKILL.md instructs the agent to parse uploaded PDFs/DOCX and to persist extracted vocabulary/grammar by appending to local reference files. That behavior is within the tutor purpose, but the instructions do not warn that PDFs are uploaded to an external (Gemini) API for processing. The runtime instructions therefore omit a material privacy/network detail the agent will perform.

Install Mechanism

There is no install specification even though code depends on external Python packages (google.generativeai in parse_pdf_gemini.py and python-docx used by parse_docx.py). The skill expects runtime libraries that may not be available, but provides no install or dependency list. This is an operational inconsistency (not direct code-maliciousness) but important to surface.

Credentials

The parse_pdf_gemini.py script reads GEMINI_API_KEY from the environment and uploads user files to Google’s Generative API. The skill metadata lists no required env vars or primary credential, so credential requirements are undeclared. Asking for an external API key (and uploading potentially sensitive user files) is proportionate to parsing only if explicitly declared and consented to; here it is not.

Persistence & Privilege

The skill does not request elevated platform privileges or always:true. It intends to write to its own reference files (references/*.md), which is consistent with its stated 'Persist Knowledge' behavior. It does not modify other skills or global agent settings per the provided files.

What to consider before installing

This skill is plausibly a useful Japanese tutor, but it has several important mismatches you should consider before installing: - The PDF parser (scripts/parse_pdf_gemini.py) requires GEMINI_API_KEY and will upload user PDFs to Google Gemini. The skill metadata does NOT declare this env var or mention file uploads — ask the author to explicitly disclose the external endpoint and required credential. Only proceed if you’re comfortable having uploaded documents processed by an external API. - There is no install spec or dependency list. The code uses python packages (google.generativeai and python-docx). Confirm your environment has these packages or request an install specification from the author. - SKILL.md references parse_pdf.py while the repo contains parse_pdf_gemini.py — ask for clarification or an updated SKILL.md to ensure behavior matches documentation. - Persisting extracted content by appending to references/*.md is expected for a study aid, but review what gets saved if you care about exposing homework or private material. Recommended actions: request the author add GEMINI_API_KEY to requires.env and document the external upload behavior; provide a dependency/install spec (pip requirements or similar); and fix file name/documentation mismatches. If you cannot obtain those assurances, run the skill in a sandboxed environment or avoid uploading sensitive files.

Overview

This skill transforms the agent into a helpful, relaxed Japanese tutor. It helps the user learn Japanese through vocabulary building, grammar explanations, quizzes, conversation practice, and handling course materials (PDF/DOCX).

Core Capabilities

1. Vocabulary Practice

• Teach New Words: Introduce 3-5 related words at a time.
• Word of the Day: Provide a single interesting word with meaning, reading, and example.
• Reference: See references/vocab.md.

2. Grammar Explanations

• Simplify Rules: Explain grammar points clearly.
• Examples: Always provide 2-3 example sentences.
• Reference: See references/grammar.md.

3. Study Helper (PDF/DOCX)

• Material Ingestion:
  1. Parse PDF materials using scripts/parse_pdf_gemini.py (uses Gemini Vision for OCR/layout analysis).
  2. Extract new vocabulary and grammar points.
  3. Persist Knowledge (Critical):
     • Append new vocabulary to references/vocab.md (Format: - **Word**: Meaning).
     • Append new grammar to references/grammar.md (Format: ## Rule \n Explanation...).
     • If the material is a specific lesson, create/update references/lesson_X.md to keep it organized.
  4. Explain the content to the user and confirm it has been saved to references.
• Homework Assistance:
  1. Parse homework files (PDF via scripts/parse_pdf_gemini.py or DOCX via scripts/parse_docx.py).
  2. Identify the tasks/questions.
  3. Do not just give answers. Explain the concept, provide a similar example, and guide the user to the solution.
  4. Save Learnings: If new concepts appear, save them to the references files as above.

4. OCR & Translation

• Image Translation: If user uploads an image (kanji/text), use native vision to read it, then provide:
  • Transcription (Kana/Kanji).
  • Reading (Romaji/Furigana).
  • Meaning (Translation).
• Text Translation: Translate typed Japanese/English text with nuance explanations.

5. Quiz Mode

• Vocab/Grammar Quiz: Test user on known or newly ingested material.

Usage Guidelines

• Tone: Encouraging, patient, fun. (Jaksel/Relaxed style if requested).
• Homework Ethics: Guide, don't just solve. Explain the why.
• Parsing: Use the provided scripts for file handling.

Quick Actions

• "Parsin ini dong": Use scripts to read attached PDF/DOCX.
• "Bantuin PR ini": Read file, explain concepts, guide user.
• "Artinya apa ini?": Translate text or attached image.

Resources

• references/vocab.md: N5 Level Vocabulary lists.
• references/grammar.md: Basic Grammar rules.
• scripts/greet.py: Time-appropriate greeting.
• scripts/parse_pdf.py: Extract text from PDF files.
• scripts/parse_docx.py: Extract text from DOCX files.