nature-paper-to-patent

Convert scientific papers, theses, technical reports, source code, figures, inventor notes, or research manuscripts into evidence-grounded Chinese invention patent drafts and attorney-facing technical disclosure materials. Use when an AI agent must mine patent points, draft or revise a Chinese technical disclosure (技术交底书), run prior-art comparison, convert Office project materials, map every claimed feature to source evidence, preserve core formulas as editable Office Math, generate claim-aligned flowcharts and methodology figures, compare a paper with an existing patent, audit support and consistency, or deliver Chinese DOCX patent/disclosure files.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An efficiently written, well-sequenced router body with concrete validation commands and stage-gate checkpoints. Its main weakness is progressive disclosure: the manifest/static routing files it instructs Claude to load are absent from the bundle, and several present bundle assets are not surfaced from the body.

Suggestions

Ship or restore the referenced routing backbone — manifest.yaml, static/core/workflow.md, static/fragments/task/technical-disclosure.md, static/fragments/task/disclosure-iteration.md, and static/core/output-contract.md — so the very first instruction ('Read manifest.yaml, then read every file under always_load') actually resolves.

Cross-link the present-but-unreferenced bundle assets from SKILL.md or via the manifest (e.g., references/cn-patent-drafting-guide.md, references/patent-figure-guide.md, scripts/render_flowchart_svg.py, scripts/math_to_omml.py, scripts/render_patent_docx.py) so each rendering/formula step names the exact file to use.

In section 4, add concrete script invocations for 'generate the main flowchart' and 'render formulas as native editable Office Math' (mirroring the executable commands in section 5) to raise copy-paste actionability.

Dimension	Reasoning	Score
Conciseness	Lean and directive throughout — compact source-ID formats, enumerated support states, and stage gates with no padding or explanations of concepts Claude already knows; every line is operational.	5 / 5
Actionability	Provides copy-paste-ready validation commands ('python scripts/validate_patent_draft.py draft.json', 'python scripts/build_patent_package.py draft.json --output-dir outputs --prefix patent') and concrete enums (P001/E001/F001/C001, explicit support states), but the bulk of executable detail is delegated to manifest/static files that are absent from the bundle.	4 / 5
Workflow Clarity	A clear five-stage sequence with explicit stage gates in section 3 and a validate-then-build feedback loop in section 5 ('Resolve all validation ERROR findings. Review every WARNING'), but the detailed per-stage ordering lives in static/core/workflow.md which is not present, leaving minor checkpoint gaps in the router itself.	4 / 5
Progressive Disclosure	The router pattern and one-level path references are well signaled, but the central navigation backbone is broken in the actual bundle: manifest.yaml, static/core/workflow.md, static/fragments/task/technical-disclosure.md, static/fragments/task/disclosure-iteration.md, and static/core/output-contract.md are all referenced but missing, while several present files (cn-patent-drafting-guide.md, render_flowchart_svg.py, math_to_omml.py, render_patent_docx.py) are never linked.	3 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and an explicit 'Use when...' trigger clause covering multiple distinct task modes. It uses synonyms and a file extension for trigger breadth and is clearly distinct from other skills.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete actions — 'mine patent points, draft or revise a Chinese technical disclosure, run prior-art comparison, convert Office project materials, map every claimed feature to source evidence, preserve core formulas as editable Office Math, generate claim-aligned flowcharts' — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' ('Convert scientific papers, theses... into evidence-grounded Chinese invention patent drafts and attorney-facing technical disclosure materials') and 'when' ('Use when an AI agent must mine patent points...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural task phrases users would say ('draft or revise a Chinese technical disclosure', 'compare a paper with an existing patent', 'deliver Chinese DOCX patent/disclosure files') plus synonyms (technical disclosure / 技术交底书) and the DOCX file extension, matching the comprehensive-synonym anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (evidence-grounded Chinese invention patent drafting from scientific papers) with highly specific triggers, making accidental activation by unrelated skills very unlikely.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: Yuan1z0825/nature-skills
Path: skills/nature-paper-to-patent/SKILL.md
Commit: 7e626a8

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.