paper2patent: Skill for Claude Code

.claude/skills/paper2patent/SKILL.md

paper2patent is a skill for Claude Code, Codex from 7toCR/paper2patent. It costs 64 tokens per session (1,027 once invoked), scanned A, original, MIT.

A workflow for converting an academic paper into complete Chinese invention-patent materials, such as claims, a specification, an abstract, drawing descriptions, and usually Word or PDF files. It requires the patent text to stay faithful to the supplied paper.

In plain words
What is it for?
Use it to draft, review, or package patent applications from papers, including their claims, descriptions, abstracts, and drawing specifications.
Why use it?
It structures the conversion from research findings to patent documents and prevents invented features, data, scenarios, or effects from entering the draft.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present.

This is 7toCR/paper2patent's own configuration. It tells Claude Code and Codex how to work on paper2patent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paper2patent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 7toCR/paper2patent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/7toCR/paper2patent/main/.claude/skills/paper2patent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/7toCR/paper2patent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for paper2patent

README.md
[![agentmods](https://agentmods.dev/badge/skills/7tocr/paper2patent/paper2patent.svg)](https://agentmods.dev/skills/7tocr/paper2patent/paper2patent)
Your own site
<a href="https://agentmods.dev/skills/7tocr/paper2patent/paper2patent"><img src="https://agentmods.dev/badge/skills/7tocr/paper2patent/paper2patent.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,027 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high System Prompt Leakage · line 23
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.01027
Opus 5 $0.00032 $0.00513
Sonnet 5 $0.00013 $0.00205
Haiku 4.5 $0.00006 $0.00103

Measured 9d ago against content hash 761e1245723e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

paper2patent 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/export_patent_pdf.py, scripts/generate_patent_docx.py, scripts/generate_patent_drawings.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/skills/paper2patent/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper2Patent

Purpose

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.

Workflow

  1. Determine the output mode. Use 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.
  2. Collect and assess the paper input. Read references/input-requirements.md when the user provides partial paper content, a PDF path, source paper figures, figure descriptions, or unclear source material.
  3. Extract the patentable contribution. Build the closed chain of difference point, technical problem, technical solution, and technical effect.
  4. Draft the structured patent content. Read 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.
  5. Apply claim and specification rules. Read references/claims-and-specification-rules.md before writing or revising claims, background, invention content, or embodiments.
  6. Prepare drawings. Read 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.
  7. Generate files for full drafts. Read 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.
  8. Run the internal quality pass. Read references/quality-checklist.md before finalizing.

Read the full file on GitHub · 45 lines

Changes

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.

  1. 9d ago First seen · 45 lines · 64 tokens per session scan A 761e1245723e

Subscribe to this mod's changes

paper2patent is a skill published in the GitHub repository 7toCR/paper2patent (588 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,027 once invoked, about $0.0003 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 2026-08-30.