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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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 patent-novelty workflow with strong sequencing, gating checkpoints, and concrete templates that assume Claude's competence. The main gap is progressive disclosure: at ~145 lines it stays monolithic rather than offloading templates and jurisdiction detail into reference files.

Suggestions

Move the cross-model examiner prompt template and the full output markdown template into reference files under references/ (e.g. references/examiner-prompt.md, references/output-template.md) and link to them from the body to reduce inline bulk.

Consider splitting the jurisdiction-specific assessment (US 102/103, CN Article 22, EP Article 54/56) into a references/jurisdictions.md file referenced one level deep.

Remove the duplicated 'research novelty is not the same as patent novelty' statement, keeping it only in Key Rules, to tighten conciseness further.

Dimension	Reasoning	Score
Conciseness	Lean and efficient for a complex legal workflow: it assumes Claude knows patent-law basics (uses POSITA, 102/103, EPC, Article 22/54/56 without explaining them) and every section — matrices, examiner prompt, output template — earns its place. Only mild redundancy exists (the 'research novelty ≠ patent novelty' point appears in both the intro and Key Rules), not enough to drop below 3.	3 / 3
Actionability	Provides concrete, copy-paste-ready guidance: defined-column anticipation and obviousness matrices, a fully specified mcp__codex__codex call with config and prompt template, per-jurisdiction statutory PASS/FAIL structure, and a complete output markdown template. Placeholders are unavoidable for user-supplied invention content.	3 / 3
Workflow Clarity	A clearly sequenced six-step process with an explicit gating checkpoint ('If the invention is novel (passes Step 2), test for obviousness') and a fallback ('If mcp__codex__codex is not available, skip ... and note it'). Cross-model examiner verification acts as a verification step before the final jurisdiction/output stages.	3 / 3
Progressive Disclosure	Sections are well organized and external standards are clearly signaled via 'Load ../shared-references/...' (one level deep), but the skill is essentially monolithic: the full examiner prompt, jurisdiction-specific assessment, and output template are all inline rather than split into reference files. No bundle files exist in references/ scripts/ or assets/ to verify, and content that could be separated is kept inline.	2 / 3
	Total	11 / 12 Passed

Description

90%

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 explicitly pairs what-it-does with natural bilingual use-when triggers and a distinctive patent-law niche. The only weakness is specificity: it summarizes two actions rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('patent novelty and non-obviousness against prior art') and a couple of actions (assess novelty, assess non-obviousness), but does not list multiple distinct concrete actions the way a score-3 anchor does; it is a focused two-action summary rather than a comprehensive action list.	2 / 3
Completeness	Clearly answers 'what' (assess patent novelty and non-obviousness against prior art) and 'when' via an explicit 'Use when user says ... or wants to evaluate if an invention is patentable' clause.	3 / 3
Trigger Term Quality	Includes natural multilingual trigger phrases a user would actually say — "专利查新", "patent novelty", "可专利性评估", "patentability check" — covering both English and Chinese variations a user would naturally utter.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (legal patentability / 102-103 style novelty) with distinctive bilingual triggers, making it unlikely to fire for unrelated skills like research-novelty or prior-art-search.	3 / 3
	Total	11 / 12 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
Commit: 82076e5

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.