prior-art-search
Search patent databases and academic literature for prior art relevant to an invention. Use when user says "现有技术检索", "prior art search", "专利检索", "check patents", or wants to find relevant prior art.
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/prior-art-search/SKILL.mdQuality
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 solid skill description with excellent trigger term coverage (including bilingual terms) and a clear 'Use when' clause that makes it highly complete and distinctive. The main weakness is that the 'what' portion could be more specific about the concrete actions performed beyond just 'search' — e.g., analyzing claims, ranking relevance, generating search strategies.
Suggestions
Expand the capability description with more specific actions, e.g., 'Search patent databases and academic literature for prior art, analyze patent claims, rank relevance to the invention, and summarize findings.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (patent databases, academic literature) and the core action (search for prior art), but doesn't list multiple specific concrete actions like analyzing claims, generating search queries, comparing patent families, or summarizing findings. | 2 / 3 |
Completeness | Clearly answers both 'what' (search patent databases and academic literature for prior art relevant to an invention) and 'when' (explicit 'Use when' clause with specific trigger phrases and a general condition). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms in both English and Chinese: '现有技术检索', 'prior art search', '专利检索', 'check patents', and 'find relevant prior art'. These cover common variations users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of patent-specific terminology, prior art focus, and bilingual trigger terms creates a clear niche that is unlikely to conflict with general search or document skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill for prior art searching with concrete search commands, a well-defined workflow, and a comprehensive output template. Its main weaknesses are the lack of validation/feedback loops in the workflow (e.g., what if searches yield nothing relevant?) and some verbosity in the inline report template that could be externalized. The referenced shared-references file is missing from the bundle, which undermines progressive disclosure.
Suggestions
Add validation checkpoints: after Step 2, verify sufficient patent results were found before proceeding; include a feedback loop to broaden/narrow search terms if results are too few or too many.
Move the detailed output markdown template to a separate file (e.g., `templates/PRIOR_ART_REPORT_TEMPLATE.md`) and reference it from the skill to reduce inline bulk.
Provide the referenced `../shared-references/prior-art-databases.md` bundle file or remove the reference if it doesn't exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity, such as explaining what overlap risk levels mean (HIGH/MEDIUM/LOW definitions that Claude can infer) and the FTO disclaimer. The output template is detailed but justified given the complexity of the task. Some tightening is possible. | 2 / 3 |
Actionability | The skill provides concrete, executable search commands (WebSearch and WebFetch patterns with specific syntax), specific databases to query, exact output file paths, and a complete markdown template for the report. Each step has clear, specific instructions rather than vague guidance. | 3 / 3 |
Workflow Clarity | The six-step workflow is clearly sequenced and logically ordered, but it lacks explicit validation checkpoints. There's no feedback loop for verifying search completeness, no step to cross-check found references, and no guidance on what to do if searches return too few or too many results. For a multi-step research process, validation gaps are notable. | 2 / 3 |
Progressive Disclosure | The skill references `../shared-references/prior-art-databases.md` for search strategy templates and IPC/CPC guidance, and mentions other skills like `/arxiv` and `/semantic-scholar`. However, no bundle files are provided, so the referenced file doesn't exist. The output template is quite long and could potentially be in a separate reference file. The structure is reasonable but the inline report template adds bulk. | 2 / 3 |
Total | 9 / 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
6f1302d
- 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.