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

Low

Low-risk findings worth noting

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.

A well-sequenced, lean router body with concrete validation commands and explicit stage gates. Its main weakness is progressive disclosure: the core workflow routing points to files that are not in the bundle while a rich reference bundle sits under-utilized.

Suggestions

Either ship the referenced manifest.yaml and static/core/* and static/fragments/task/* files, or rewrite Section 1 and Section 3 to route through the bundle paths that actually exist (references/ and references/disclosure/).

Explicitly signal the existing references/disclosure/ files (intake.md, disclosure_builder.md, prior_art_search.md, etc.) from the body so Claude can navigate to them by condition.

Make the validation feedback loop explicit in Section 5 (e.g., 'If validate reports ERRORs, fix and re-run until exit code 0 before packaging').

Dimension	Reasoning	Score
Conciseness	The body is lean and instruction-dense with no padding: it never explains what a patent, PDF, or DOCX is and uses terse declarative sentences ('Create stable source IDs before drafting', 'Exclude unsupported features from formal claims'), so every token earns its place.	5 / 5
Actionability	Provides concrete executable commands ('python scripts/validate_patent_draft.py draft.json', 'python scripts/build_patent_draft.py draft.json --output-dir outputs --prefix patent') and concrete ID schemes (P001/E001/F001/C001) and support states, but several referenced paths (manifest.yaml, static/core/workflow.md, static/fragments/task/*) do not exist in the bundle, leaving minor gaps in the executable path.	4 / 5
Workflow Clarity	Clear five-section sequence with explicit stage gates ('Do not move to formal claims until the source map, terminology ledger, inventories, evidence ledger, and invention concept pass their gates') and a dedicated validation step with the resolve-findings loop, but the validate->fix->re-run loop is implied rather than spelled out.	4 / 5
Progressive Disclosure	The body is structured as an overview router with one-level-deep references, but its primary navigation targets (manifest.yaml, static/core/workflow.md, static/fragments/task/technical-disclosure.md, static/fragments/task/disclosure-iteration.md, static/core/output-contract.md) are absent from the bundle, and the substantial existing references/disclosure/ bundle is largely not signaled from the body.	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 gives an explicit, multi-trigger 'Use when' clause covering both what and when. It is dense but every clause is informational rather than padded.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('mine patent points', 'draft or revise a Chinese technical disclosure', 'run prior-art comparison', 'map every claimed feature to source evidence', 'preserve core formulas as editable Office Math', 'generate claim-aligned flowcharts', 'audit support and consistency', 'deliver Chinese DOCX patent/disclosure files'), giving comprehensive coverage rather than generic phrasing.	5 / 5
Completeness	Explicitly answers 'what' ('Convert ... into evidence-grounded Chinese invention patent drafts and attorney-facing technical disclosure materials') and 'when' with a concrete 'Use when an AI agent must ...' clause enumerating multiple trigger scenarios.	5 / 5
Trigger Term Quality	Covers natural domain terms and synonyms users would say ('scientific papers, theses, technical reports, source code, figures, inventor notes, or research manuscripts', '技术交底书', 'prior-art comparison', 'Office project materials') plus a file extension ('DOCX'), matching comprehensive coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	A clearly defined niche (Chinese invention patent drafting from scientific sources) with distinctive triggers like '技术交底书' and 'map every claimed feature to source evidence' that are unlikely to fire for unrelated skills.	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: 3817cd1

Reviewed: about 8 hours 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.