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.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description with excellent trigger term coverage in both English and Chinese, a clear 'Use when' clause, and a distinctive niche. The main weakness is that the 'what' portion could be more specific by listing additional concrete actions beyond assessing novelty and non-obviousness (e.g., comparing patent claims, summarizing prior art findings, drafting novelty reports).
Suggestions
Expand the capability list with more concrete actions, e.g., 'compare patent claims against prior art references, summarize overlapping disclosures, draft novelty assessment reports' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (patent assessment) and two specific actions (assess novelty and non-obviousness against prior art), but doesn't list additional concrete actions like comparing claims, generating prior art search reports, or identifying overlapping references. | 2 / 3 |
Completeness | Clearly answers both 'what' (assess patent novelty and non-obviousness against prior art) and 'when' (explicit 'Use when' clause with specific trigger terms and a general condition about evaluating patentability). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both English and Chinese: '专利查新', 'patent novelty', '可专利性评估', 'patentability check', and the natural phrase 'evaluate if an invention is patentable'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — patent novelty and non-obviousness assessment is a very specific domain unlikely to conflict with other skills. The bilingual trigger terms and domain-specific vocabulary (prior art, patentability) further reduce conflict risk. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable patent novelty assessment skill with clear multi-step workflow, concrete analysis matrices, and jurisdiction-specific guidance. Its main weaknesses are moderate verbosity (some repeated concepts and sections that could be more compact) and lack of supporting bundle files for the referenced shared resources. The cross-model verification step and fallback handling demonstrate thoughtful design.
Suggestions
Consolidate the repeated distinction between patent novelty and research novelty into a single concise statement rather than mentioning it in multiple places.
Provide the referenced shared files (patent-writing-principles.md, patent-format-us.md) as bundle files, or remove the references if they don't exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary elaboration. The distinction between patent novelty and research novelty is repeated multiple times, and the jurisdiction-specific section could be more compact. The matrix templates and structured formats are useful but add length. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific matrix formats for anticipation and obviousness analysis, exact MCP call syntax with prompt template, structured output format, and clear claim element extraction steps. The jurisdiction-specific legal citations (35 USC 102/103, Article 22 CN Patent Law, Article 54/56 EPC) are precise and executable. | 3 / 3 |
Workflow Clarity | The six-step workflow is clearly sequenced with logical dependencies (novelty before obviousness, cross-model verification after analysis). Each step has explicit inputs and outputs, the matrices serve as validation checkpoints, and the cross-model examiner review acts as a verification/feedback loop. The fallback for unavailable MCP is also specified. | 3 / 3 |
Progressive Disclosure | The skill references shared files (patent-writing-principles.md, patent-format-us.md, PRIOR_ART_REPORT.md) but no bundle files are provided to verify these exist. The content is somewhat monolithic — the jurisdiction-specific assessments and the detailed matrix templates could potentially be split into separate reference files. However, the overall structure with clear sections is reasonable for the complexity. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
66b974e
- Reviewed
Table of Contents
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.