patent-novelty-check

Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.

Quality

83%

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

75%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-structured, actionable instruction-only skill with a clear multi-step workflow, concrete examiner-verification call, and a defined output template. It is concise and well-organized, with only minor gaps around input-missing handling and scaffold matrices.

Suggestions

Add an explicit handling step for when patent/PRIOR_ART_REPORT.md is missing or incomplete (e.g., direct the user to run /prior-art-search first) to close the workflow-clarity gap.

Flesh out at least one example matrix row in Step 2 and Step 3 with realistic claim elements and references so the scaffolds read as concrete worked examples rather than empty templates.

Tighten the Key Rules section by merging the two novelty-definition bullets, since the research-vs-patent-novelty distinction is already stated in the opening line.

Dimension	Reasoning	Score
Conciseness	The body is lean — workflow steps, matrix scaffolds, a concrete Codex prompt block, and concise Key Rules — avoiding explanation of basics Claude already knows; a few template matrices with "..." placeholders could be tightened, keeping it just below a 5.	4 / 5
Actionability	Provides a copy-pasteable mcp__codex__codex call with full prompt, an exact output-file template, and matrix scaffolds; as an instruction-only legal-analysis skill code absence is fine, but the matrices are scaffolds rather than fully fleshed examples, so not a 5.	4 / 5
Workflow Clarity	Six steps are clearly sequenced with a conditional gate (obviousness only if novel) and an explicit fallback when Codex is unavailable; the destructive/batch cap does not apply to this analytical skill, but handling for a missing PRIOR_ART_REPORT.md input is not specified.	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references to ../shared-references/*.md and patent/PRIOR_ART_REPORT.md; no local bundle files exist, and bulk detail is appropriately externalized with minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

91%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, well-formed description that clearly states the skill's purpose and provides rich bilingual trigger coverage. It is mostly distinct from sibling patent skills with only minor overlap risk.

Dimension	Reasoning	Score
Specificity	"Assess patent novelty and non-obviousness against prior art" names the domain plus several concrete analyses (novelty, non-obviousness, prior-art comparison), with only minor coverage gaps; not a 5 because the action set is essentially one verb over two objects rather than a comprehensive list.	4 / 5
Completeness	Explicitly answers both what ("Assess patent novelty and non-obviousness against prior art") and when ("Use when user says ... or wants to evaluate if an invention is patentable") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes bilingual synonyms and natural phrases users would say — "专利查新", "可专利性评估", "patent novelty", "patentability check", "evaluate if an invention is patentable" — giving comprehensive coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear patent-novelty niche with distinct bilingual triggers; minor overlap risk remains with sibling skills like /prior-art-search and /novelty-check referenced in the body.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/patent-novelty-check/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.