Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add davidtoby/agent-skills --skill chinese-pdf-document-workflowsgit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/davidtoby/agent-skills/chinese-pdf-document-workflows)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/chinese-pdf-document-workflows"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/chinese-pdf-document-workflows.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.00507 |
| Opus 5 | $0.00042 | $0.00253 |
| Sonnet 5 | $0.00017 | $0.00101 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
chinese-pdf-document-workflows scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chinese PDF and Document Workflows
Use this umbrella whenever the work centers on document extraction, document conversion, or polished Chinese PDF output.
Core workflow
- Determine the input type: PDF, scanned PDF/image, markdown, HTML, DOCX/PPTX/XLSX, transcript, or paper.
- Extract source content with the least lossy method:
- digital PDF text/table extraction first;
- OCR fallback for scans or image-only pages;
markitdown/document converters for Office/HTML/structured files.
- Preserve citations, page numbers, section headings, figures/tables, and source URLs.
- Build a Chinese deliverable with explicit structure: executive summary, key insights, evidence, implications, limitations, and next actions when relevant.
- Render with reliable Chinese fonts; avoid browser/PDF renderers that garble CJK glyphs.
- Verify the PDF visually/textually: Chinese characters render, no tofu boxes, page breaks are acceptable, and filenames are stable.
Labeled playbooks
Professional Chinese PDF rendering
Use ReportLab or another CJK-safe pipeline. Register known-good Chinese fonts on macOS/Linux and test a short sample before rendering a long report.
Academic paper to Chinese insight report
Extract title, authors, abstract, methodology, claims, evidence, limitations, and contribution. Translate/summarize into fluent Chinese and add independent interpretation rather than only a literal translation.
Consulting report from YouTube/transcripts
Combine transcript evidence with a consulting-style structure: context, key points, strategic implications, recommendations, and appendix timestamps.
PDF extraction and annotation
For tables/images/metadata, choose a PDF-specific extractor before generic text conversion. Use OCR only as fallback and label OCR uncertainty.
Natural-language PDF edits
For small PDF edits, prefer a purpose-built PDF edit CLI. Always make a backup and inspect the resulting PDF.
Reference files
Legacy narrow skill bodies are demoted to references/from-*.md for exact commands, fonts, and historical report templates.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/from-media-chinese-video-transcribe-pdf.md 5.2 KB
- references/from-media-youtube-bilingual-transcript-report.md 8.2 KB
- references/from-openclaw-imports-chinese-pdf-report.md 57 KB
- references/from-openclaw-imports-markdown-converter.md 2.5 KB
- references/from-openclaw-imports-skill-pdf-content-extractor.md 171 KB
- references/from-user-imports-academic-paper-to-chinese-insight-pdf.md 16 KB
- references/from-user-imports-chinese-pdf-report.md 57 KB
- references/from-user-imports-consulting-pdf-from-youtube.md 33 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 47 lines · 83 tokens per session scan A efcc8c37331b
chinese-pdf-document-workflows is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 507 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
paper2slides
Turn an academic paper PDF into a presentation deck (.pptx) end-to-end. Use this skill whenever the user wants to "make slides from a paper", "generate a deck from this PDF", "make a PPT from this paper", "generate slides from a PDF document", "make a deck from a research paper", or supplies a research paper PDF and…
taxonomy-vto
A reference guide for diagnosing visual problems in LaTeX research papers. It defines categories such as wasted page space, misplaced figures, inconsistent formatting, overflow, alignment, and template-migration issues.
latex-expert
Professional LaTeX for official documents: class and engine choice, fonts, microtype, booktabs tables, biblatex/biber, KOMA letters, academic CVs, Eisvogel/pandoc PDFs, IEEE/Elsevier/Springer submission. Use whenever the user writes, reviews, or compiles .tex/.sty/.cls, mentions XeLaTeX/LuaLaTeX/latexmk, wants a…
figure-quality-standards
Use whenever generating figures or tables for a research paper — enforces publication-quality visual standards including style consistency, readability, accessibility, and venue-appropriate formatting.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…