Total 30,649 skills, Document Processing has 448 skills
Showing 12 of 448 skills
Reads Google Sheets and converts content to markdown. Use when the user asks to read, fetch, or convert Google Sheets data to markdown.
This skill should be used when the user requests to "write documents", "compose articles", "write emails", "edit Chinese text", "check formatting", "correct typography", "mix Chinese and English layout", "format documents", "review document formatting", or "proofread", or when the user is preparing to write or edit Chinese documents, emails, messages, or any formal Chinese text content. This skill provides formatting and typographical corrections based on the Chinese Style Guide, focusing on layout and formatting without altering the author's intended expression.
Use when python-docx paragraphs created via OxmlElement ignore the intended style or fall back to Normal - explains the style-name vs style-ID mismatch, shows the fix, and notes the related section-break removal pitfall.
Create/edit .pptx presentations with charts, templates, and speaker notes. Use when asked for pitch decks, QBR decks, or slide automation.
Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report. **Trigger**: latex compile, build PDF, LaTeX errors, missing refs, 编译PDF, 引用错误. **Use when**: 已有 `latex/main.tex`（通常来自 `latex-scaffold`），需要确认可编译并输出失败原因报告。 **Skip if**: 还没有 LaTeX scaffold（先跑 `latex-scaffold`）。 **Network**: none. **Guardrail**: 编译失败也要落盘 `output/LATEX_BUILD_REPORT.md`；不做“内容改写”，只做编译/QA。
Create and manipulate PDF files programmatically. Use when the user needs to generate PDFs, fill PDF forms, extract PDF content, add watermarks/overlays, or merge documents. Supports both template-based generation (form filling, overlays) and from-scratch creation. Keywords: PDF, document, form, fillable, merge, watermark, extract, text, report.
Reviews and edits copy to remove AI-generated patterns and make text sound natural. Use when editing drafts, reviewing copy, "humanize this", "make it less AI", "sounds too AI", "remove AI patterns", "edit my copy", "this sounds robotic", or when text feels machine-generated.
This skill should be used when docs-researcher agent needs guidance on "how to search documentation", "WebSearch query patterns", "filtering search results", "documentation research strategy", or "creating knowledge files". Provides systematic methodology for effective technical documentation research.
Guidance for fixing LaTeX overfull hbox warnings by replacing words with shorter synonyms from an allowed list. This skill applies when tasks involve modifying LaTeX documents to eliminate typographic warnings while adhering to strict word replacement constraints. Use when dealing with synonym-constrained text editing in LaTeX or similar markup languages.
Parse PDFs locally (CPU) into Markdown/JSON using MinerU. Assumes MinerU creates per‑doc output folders; supports table/image extraction.
Index and search culture documentation
Use when generating PDFs from markdown with Pandoc - covers differences from Python-Markdown, blank line rules, fix scripts for labels/anchors/metadata, and visual testing workflow