skills.rest
dadafinger
dadafingerCOMMUNITY
Explore all skills by this author →
GitHub

jp-capture-text-consistency

Validates Japanese UI label consistency between requirement sheets and manual documents.

Updated May 10, 2026
Search Tags:#pdf#japanese#localization#xlsx#consistency check#docx#manual review
One-click install
npx skills add https://github.com/dadafinger/dadafinger-skills --skill jp-capture-text-consistency-dadafinger
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jp-capture-text-consistency
Source: https://github.com/dadafinger/dadafinger-skills/tree/main/jp-capture-text-consistency
Command: npx skills add https://github.com/dadafinger/dadafinger-skills --skill jp-capture-text-consistency-dadafinger

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf.

What problem does it solve? When UI labels change in a product release, Japanese manuals often retain outdated capture text. This Skill checks whether As-is/To-be terms from the requirements sheet are correctly reflected in Japanese manual DOCX and PDF files, producing a structured consistency report. ## Core Features & Use Cases - Term Consistency Scanning: Reads the WEB_UI capture sheet from the requirements xlsx and counts As-is and To-be term occurrences in manual documents. - Status Classification: Labels each row as APPLIED, RESIDUAL, or N/A based on term counts, flagging outdated labels that remain in the manual. - Report Generation: Writes a dated Markdown report under the review results folder summarizing counts and top residual terms. - Use Case: Before shipping a Japanese manual update, run this check against the latest requirements sheet to confirm every renamed UI label was actually applied in the DOCX and PDF deliverables. ## Quick Start Check whether the Japanese manual in my 305매뉴얼 folder reflects all UI label changes from the latest requirements sheet and write a consistency report.

Frequently Asked Questions about jp-capture-text-consistency

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check if UI label changes are reflected in a manual?▼

Compare As-is and To-be terms from the requirements sheet against the manual text. A change is applied when the old term count is zero and the new term appears; any remaining old term occurrences are flagged as residual.

How to extract text from DOCX and PDF files for comparison?▼

DOCX text is extracted by flattening word/document.xml after removing XML tags. PDF text is extracted with PyMuPDF (fitz) when available; if the PDF is missing, the check runs DOCX-only and marks the PDF section as skipped.

Does this check modify the original xlsx, DOCX, or PDF files?▼

No, the review is strictly read-only. Original requirement sheets and manual documents are never edited; results are written only to a separate Markdown report file.

Can OCR be used to read text from screenshot images?▼

OCR is not performed by default. Text is only extracted from the document text layers, and image-based OCR is applied only when explicitly requested by the user.

Why are some frequent Japanese terms only reported as residual candidates?▼

Generic terms like 削除 or 前に appear in many contexts, so a nonzero count does not prove an outdated label. They are listed as residual candidates for human review rather than auto-fix directives.

Related Skills

Explore More Content & Communication Skills→
Wenwen555Wenwen555

document-reader

Route PDF, Word, Excel, and PowerPoint files to matching readers and normalize outputs.

Community
Intermediate
evolsbevolsb
47

Contract Review & Redline Skill

Convert JSON-defined contract changes into tracked-change DOCX, PDF, and markdown deliverables.

Community
Advanced
adiytharpansaadiytharpansa

screenshot-ocr

Extracts text from images, screenshots, and scanned documents using OCR.

Community
Intermediate
liuridaliurida

gorm-many-to-many

Manage many-to-many relationships in GORM with join tables and associations.

Community
Advanced