prior-art-search 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.
Is the prior-art-search skill safe?
Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.
No findings.
Install the prior-art-search skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git /tmp/Auto-claude-code-research-in-sleep mkdir -p ~/.claude/skills cp -r /tmp/Auto-claude-code-research-in-sleep/skills/prior-art-search ~/.claude/skills/prior-art-search
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
Prior Art Search
Search patents and literature for prior art relevant to: $ARGUMENTS
Adapted from /research-lit for patent-specific searching.
Constants
- MAXPATENTRESULTS = 20 — Maximum patent documents to analyze in detail
- MAXPAPERRESULTS = 15 — Maximum academic papers to analyze in detail
- SEARCH_YEARS = 10 — How many years back to search
- PATENT_DATABASES = "google-patents, espacenet" — Patent databases to search
Inputs
Read the invention description from:
- $ARGUMENTS if it contains technical details
- patent/INVENTION_BRIEF.md if it exists
- INVENTION_BRIEF.md if 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 /arxiv if available, or WebSearch): Search for preprints
- Semantic Scholar (via /semantic-scholar if 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/PRIORARTREPORT.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
- RefeKey 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.
More skills from wanshuiyin/Auto-claude-code-research-in-sleep
- Aablation-plannerUse when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
- Aablation-plannerUse when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.
- AalphaxivQuick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
- AalphaxivQuick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
- Aanalyze-resultsAnalyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
- Aanalyze-resultsAnalyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says \"analyze results\", \"compare\", or needs to interpret experimental data.
- AarxivSearch, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
- AarxivSearch, download, and summarize academic papers from arXiv. Use when user says \"search arxiv\", \"download paper\", \"fetch arxiv\", \"arxiv search\", \"get paper pdf\", or wants to find and save papers from arXiv to the local paper library.
- Aauto-paper-improvement-loopAutonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\", \"auto improve\", or wants to iteratively polish a generated paper.
- Aauto-paper-improvement-loopAutonomously improve a generated paper via Claude review through claude-review MCP → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\", \"auto improve\", or wants to iteratively polish a generated paper.
- Aauto-paper-improvement-loopAutonomously improve a generated paper via Gemini review through gemini-review MCP → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\", \"auto improve\", or wants to iteratively polish a generated paper.
- Aauto-paper-improvement-loopAutonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\", \"auto improve\", or wants to iteratively polish a generated paper.