Prior Art Search
SkillSearchLets your agent search patent databases and academic papers to find prior art for an invention.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Prior Art Search skill
About this skill
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.
What this skill tells your AI
The instructions your AI receives, as published by wanshuiyin/auto-claude-code-research-in-sleep in skills/prior-art-search/SKILL.md and read by ahel’s review.
Search patents and literature for prior art relevant to: $ARGUMENTS
Adapted from /research-lit for patent-specific searching.
Constants
MAX_PATENT_RESULTS = 20— Maximum patent documents to analyze in detailMAX_PAPER_RESULTS = 15— Maximum academic papers to analyze in detailSEARCH_YEARS = 10— How many years back to searchPATENT_DATABASES = "google-patents, espacenet"— Patent databases to search
Inputs
Read the invention description from:
$ARGUMENTSif it contains technical detailspatent/INVENTION_BRIEF.mdif it existsINVENTION_BRIEF.mdif it exists at project root
Shared References
Load ../shared-references/prior-art-databases.md for search strategy templates and IPC/CPC classification guidance.
Workflow
Step 1: Extract Search Concepts
From the invention description, identify:
- Core inventive concept: The primary technical contribution (1-2 sentences)
- Technical problem: What problem it solves
- Key technical features: 4-6 specific technical elements that define the invention
- IPC/CPC classes: Predict relevant classification codes (e.g., G06N, G06F)
Step 2: Patent Search
For EACH search concept, search via:
Google Patents (via WebSearch):
WebSearch: "site:patents.google.com [keywords]"
WebSearch: "[keywords] patent"
- Try primary keywords + technical problem keywords
- Search in English regardless of target jurisdiction
- For CN inventions, also search Chinese keywords via WebSearch
Espacenet (via WebFetch):
- WebFetch worldwide.espacenet.com/search results for key queries
- Search by predicted IPC/CPC classes
Assignee/Inventor Search:
- If known companies/universities work in this area, search their patent portfolios
- WebSearch: "[assignee name] patent [technical area]"
For each potentially relevant patent found:
- WebFetch the patent page to extract: title, abstract, representative claims, filing date, assignee, current status
- Record IPC/CPC classification codes
Step 3: Academic Literature Search
Search the same concepts in academic databases:
- Google Scholar (via WebSearch):
WebSearch "[keywords] site:scholar.google.com" - arXiv (via
/arxivif available, or WebSearch): Search for preprints - Semantic Scholar (via
/semantic-scholarif API key set, or WebSearch)
For each relevant paper found:
- Extract title, authors, venue, year, key contribution
Step 4: Classification and Analysis
For each reference found, assess:
- Relevance: How closely does it relate to the invention?
- Overlap Risk: Does it disclose the same or similar technical solution?
- HIGH: Anticipates one or more claim elements
- MEDIUM: Discloses a related but different approach
- LOW: Same general field, different approach
- Relationship: Is it anticipating, relevant, or merely background?
Organize results by IPC/CPC classification to see the technical landscape.
Step 5: Freedom-to-Operate Assessment (Preliminary)
Based on the search results:
- Identify patents with claims that potentially cover the invention
- Note any expired patents (public domain)
- Flag areas where claim scope overlap is significant
Disclaimer: This is a preliminary assessment only. A professional freedom-to-operate analysis by a patent attorney is recommended before filing.
Step 6: Output
Write patent/PRIOR_ART_REPORT.md with:
## Prior Art Search Report
### Invention Summary
[1-2 sentence description of the searched invention]
### Search Strategy
- Keywords used: [...]
- IPC/CPC classes searched: [...]
- Databases searched: Google Patents, Espacenet, Google Scholar, arXiv
- Date range: [year] to present
### Patent References Found
| # | Patent No. | Title | Date | Assignee | IPC/CPC | Key Teaching | Overlap Risk |
|---|-----------|-------|------|----------|---------|-------------|-------------|
| 1 | CN... / US... | [title] | [date] | [assignee] | [codes] | [2-3 sentences] | HIGH/MEDIUM/LOW |
### Non-Patent Literature Found
| # | Reference | Title | Authors/Venue | Year | Key Contribution | Relevance |
|---|-----------|-------|--------------|------|-----------------|-----------|
| 1 | [DOI/link] | [title] | [authors] | [year] | [1-2 sentences] | HIGH/MEDIUM/LOW |
### Prior Art Landscape
[Organized by technical approach or IPC class, not just chronological]
### Freedom-to-Operate Preliminary Assessment
[Which existing patents might block the invention? What is the risk level?]
### Recommendations
- Suggested claim scope adjustments based on prior art
- Areas where novelty appears strongest
- References to watch during prosecution
Key Rules
- Never fabricate patent numbers or citations. Mark uncertain references with
[VERIFY]. - Search in English AND the target jurisdiction language (Chinese for CN).
- Patent prior art includes everything published before the priority date, not just patents.
- Academic papers are valid prior art for both novelty and inventive step.
- Include expired patents -- they are public domain but still relevant for novelty.
Signals
- GitHub stars
- 17k
- Forks
- 1k
- Last commit
- Sep 2026
Others that do the same job
Advanced
- Item type
- skill
- Key
prior-art-search-wanshuiyin- Source
- github.com/wanshuiyin/auto-claude-code-research-in-sleep
github.com/wanshuiyin/auto-claude-code-research-in-sleep
Related picks
Skill · larksuite
The pick for Markdownmarkdown-mermaid-writing
Skill · k-dense-ai
The pick for Markdownsearch
Skill · davila7
The pick for Searchsummarize
Skill · zhouguoqing
The pick for Summarizelegal-writing
Skill · anthropics
The pick for Legaldisputes-and-legal-holds
Skill · cbrock84
The pick for Legal