CMS, document processing, and media generation.
Vectorized string manipulation using the char module and modern string alternatives, including cleaning and search operations. Triggers: string operations, numpy.char, text cleaning, substring search.
Capture conversation context in a single diff-friendly file
CellCharter 本地离线文档 (Sphinx 构建), 从下载目录启动 HTTP 服务后抓取
Extract edits from client/team emails and apply to documents. Use when emails arrive with document changes, comments, or markup that need to be implemented into the working document.
Parallel PDF to MP3 conversion using MiniMax. Convert multiple PDF chapters to audio simultaneously using parallel subagents. Use when: (1) User says 'generate mp3 for the story of [STORY_NAME]', (2) User says '为故事[STORY_NAME]生成mp3', (3) User says '为故事[STORY_NAME]第[X]章生成mp3', (4) User says 'generate mp3 for story of [STORY_NAME], chapter [X]', (5) Converting a range of PDFs like 'story-[01-05].pdf' to MP3, (6) Batch audiobook creation from PDF chapters.
Translates English patents to Korean with 4-agent collaboration. Use when: patent translation, specification translation, claims translation, En-Ko technical document localization, 특허 번역, 영한 번역. Features: analyze→translate→review→learn loop, dynamic term base, 95-point quality threshold, 2-stage review (mechanical + semantic).
Convert PowerPoint (.pptx) presentations to standalone HTML format with FULL style, position, and formatting preservation. Accurately replicates slides with exact fonts, colors, shapes, backgrounds, layouts, hyperlinks, videos, audio, and tables. Use for web-friendly presentations that maintain visual fidelity and interactivity.
Split large CLAUDE.md into child files. Use when context files exceed line limits, are too verbose, or cover multiple distinct topics that should be separate.
Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.
日本語テキストを音声に変換するTTS（Text-to-Speech）スキル。ナレーション原稿の読み上げ、コンテンツの音声化、アクセシビリティ対応に使用。
Parse Claude command frontmatter and expose body/meta for Codex CLI.
Expert in BIDIRECTIONAL Kabardian↔Russian translation using CORPUS-FIRST approach. Translates both Russian→Kabardian AND Kabardian→Russian. Learns from 292k real translation examples, then falls back to dictionaries. Provides accurate translations by copying patterns from verified corpus. For rus→kbd ensures proper SOV word order and morphology. Activates when user requests translation, mentions "перевод", "translate", "переведи", "Kabardian", "кабардинский", provides sentences in Russian or Kabardian to translate.
Import Chinese language works into Zotero with proper pinyin transliteration and translations following Chicago style guidelines
Review and improve English in daily journal entries. Use when the user wants to review their daily English practice with Japanese originals in `::ja` and `::en` sections.
Specialized database operations for Chuukese language data including dictionary management, phrase collections, translation pairs, and linguistic metadata. Use when working with Chuukese language databases, managing translation data, or performing database operations on linguistic datasets.
.opencode/配下のドキュメント・設定を修正する際の品質保証プロセス（修正→レビュー→修正の反復ループ）
Analyze email messages and mailbox data for forensic investigation. Use when investigating phishing attacks, business email compromise, insider threats, or any scenario requiring email evidence analysis. Supports PST, OST, MBOX, EML, and MSG formats.
Create, fix, and refine deterministic receipt/invoice parsers in curlys-books, including vendor detection, OCR text extraction routing (pdfplumber for text PDFs → AWS Textract fallback; images → Textract), golden fixture creation, and updates to the vendor dispatcher/registry. Use when adding a new vendor parser, debugging mis-detections, improving totals/tax/date/line extraction, or deciding when to rely on Claude Vision fallback for vendors without a tested parser.
