Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Convert academic papers into complete Chinese invention patent application deliverables, including DOCX/PDF application documents, claims, specifications, abstracts, drawing specifications, and fidelity reviews. Use when drafting patent text, generating Word or PDF patent applications, preparing patent drawings, or checking paper-to-patent fidelity.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 136% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 85% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 16% | 0% |
Use this skill to convert an academic paper into a complete Chinese invention patent application deliverable. The default full-draft output is a Word document (.docx) and, when a converter is available, a PDF copy. Keep the work faithful to the supplied paper: do not invent technical features, embodiments, data, hardware, scenarios, or effects that are not present in the source material.
direct by default, human-in-loop when the user asks to review choices before generation, and text-only when the user explicitly wants no files.references/input-requirements.md when the user provides partial paper content, a PDF path, source paper figures, figure descriptions, or unclear source material.references/text-conversion-workflow.md for the five-part content model and execution order. Treat the repository reference_skills/meterial.md prompt as the normative source for the five patent sections, claim rules, specification depth, and fidelity constraints.references/claims-and-specification-rules.md before writing or revising claims, background, invention content, or embodiments.references/drawing-generation.md; first derive patent reference drawings from the source paper figures, captions, and method text when available, then align them with the claims and specification. Generate black-and-white SVG reference drawings, converter-compatible PNG fallbacks when possible, and Image2-style refinement prompts.references/document-generation.md, then use scripts/generate_patent_drawings.py to create clean SVG/PNG drawings, scripts/generate_patent_docx.py to embed them in DOCX, and scripts/export_patent_pdf.py for PDF conversion when available.references/quality-checklist.md before finalizing..docx file with embedded visible drawings, and a .pdf copy when possible.text-only mode, output plain patent text with no Markdown headings, code fences, checklists, or hidden reasoning.direct mode, if source information is insufficient, generate explicit 【待补充：...】 placeholders and a material gap section instead of filling gaps with assumptions.human-in-loop mode, ask for missing source material before generating final files when the gap would affect the technical solution or claim scope.Other measured skills in the registry, with their headline benchmark lift.