skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
robthepcguy/claude-patent-creator253 installs

prior-art-search

Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using Google Patents (SerpApi), EPO OPS or BigQuery, CPC classification and research-paper search

How do I install this agent skill?

npx skills add https://github.com/robthepcguy/claude-patent-creator --skill prior-art-search
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill provides a systematic methodology for patent prior art searches using trusted services like Google BigQuery and the European Patent Office. No malicious code or hidden backdoors were found. A minor security concern is the potential for indirect prompt injection if an attacker provides a malicious invention description intended to influence the agent's behavior during the analysis phase.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

  • Runlayerwarn

    2/2 files flagged

  • ZeroLeakspass

    Score: 93/100 · 2 sections analyzed

What does this agent skill do?

Prior Art Search Skill

Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments.

When to Use

Invoke this skill when users ask to:

  • Conduct prior art search for an invention
  • Assess patentability of an idea
  • Perform freedom-to-operate analysis
  • Find blocking patents
  • Research patent landscapes
  • Prepare for patent filing

What This Skill Does

Implements a professional 7-step prior art search methodology combining:

  • Keyword searches across 100M+ patents (Google Patents via SerpApi, EPO OPS, or BigQuery)
  • Research papers before the priority date (search_non_patent_literature)
  • CPC classification searches
  • USPTO API searches
  • Timeline analysis
  • Patentability assessment
  • IDS (Information Disclosure Statement) preparation

The 7-Step Methodology

Step 1: Invention Definition (2-3 min)

Goal: Extract key features and define innovation scope

Process:

  1. Interview user about invention
  2. Extract core technical elements
  3. Identify novel features
  4. List all components/steps
  5. Define search scope

Output: Structured invention summary with key features

Questions to Ask:

  • What problem does this solve?
  • What are the key components/steps?
  • What makes this different from existing solutions?
  • What is the core innovation?

Step 2: Keyword Strategy (2-3 min)

Goal: Develop comprehensive search keyword list

Process:

  1. Primary keywords from invention
  2. Synonyms and variations
  3. Technical terminology
  4. Industry-specific terms
  5. Synonym sets to run as separate searches

Query syntax (important): the keyword search splits a query into terms and requires every term to appear (AND), each matching the title, abstract, or claims (results are ranked by relevance, title hits weighted highest). It does not parse Boolean operators — AND/OR/parentheses are ignored. So:

  • Use plain space-separated terms for the AND set: blockchain authentication.
  • Wrap a phrase in double quotes to require it verbatim: "distributed ledger".
  • For OR / synonyms, run separate searches and merge the results — don't put OR in one query.

Output: Keyword search strategy document

Example:

Primary: blockchain authentication
Synonyms: distributed ledger verification, cryptographic authentication
Technical: public key infrastructure, digital signature
Related: decentralized identity, trustless verification
Searches (run each separately, then merge/dedupe):
- blockchain authentication
- "distributed ledger" verification
- cryptographic authentication
- "public key infrastructure" signature

Step 3: Broad Keyword Search (3-5 min)

Goal: Cast wide net to find relevant patents

Which patent search to use: call check_google_patents_status first. If it is ready (the free SerpApi key from the README's Quick Start, Step 3), run every keyword search with search_patents_google. If not, call check_epo_api_status; when EPO OPS is ready, run the keyword searches with search_epo_patents (worldwide titles and abstracts, CQL ta=) and the CPC step with cpc= codes, reading available claims/description with get_epo_patent (EP, WO and selected national publications). Empty text and not-found/error messages are not a successful read; record coverage limits. Use search_patents_bigquery only when check_bigquery_status says BigQuery is configured; each keyword search there scans about 341 GiB. search_uspto_api (after check_uspto_api_status) searches ODP application metadata (including titles, parties and status), without claims/description full-text search; use it only as a supplement. If none of Google Patents, EPO OPS and BigQuery is ready, report status errors and restore a provider or set up SerpApi (README Quick Start, Step 3) and run a no-key first screen in the meantime: several WebSearch queries restricted to Google Patents (allowed_domains: ["patents.google.com"]), then read the closest patent pages with WebFetch for claims, dates, CPC codes and citations. Label everything found this way a web first screen, not a prior-art search: web search ranks pages rather than matching claim text and misses much of the record, so a thin or empty result is never evidence of no prior art. A first screen never supports a novelty, obviousness or patentability verdict: in every later assessment, report section or phase that would give one (including any NOVEL / LIKELY NO verdict), write "Not assessed: only a web first screen was run; set up patent search and rerun" instead. CPC searches run through Google Patents (CPC=), EPO OPS (cpc=) or BigQuery (search_patents_by_cpc_bigquery); with none ready, mark the CPC step unverified and describe only the web queries actually run.

Process:

  1. Run keyword searches (search_patents_google, search_epo_patents, or search_patents_bigquery as above)
  2. Review top 20-30 results per query
  3. Identify most relevant patents
  4. Refine keyword strategy based on results
  5. Document relevant patents found

Tool calls (MCP tools, not Python imports):

search_patents_google(query="blockchain authentication", limit=30, start_year=2015)
# OPS fallback after check_epo_api_status reports ready (title/abstract search):
search_epo_patents(query='ta="blockchain" and ta="authentication"', limit=30)
# Alternative only when check_bigquery_status reports ready:
search_patents_bigquery(query="blockchain authentication", limit=30, country="US", start_year=2015)
# papers count as prior art too; set published_before to the priority date:
search_non_patent_literature(query="blockchain authentication", published_before="2024-01-15")

Output: List of 10-20 potentially relevant patents


Step 4: CPC Code Identification (2-3 min)

Goal: Find relevant classification codes

Process:

  1. Extract CPC codes from relevant patents found in Step 3
  2. Analyze CPC code descriptions
  3. Identify primary classification areas
  4. Select 3-5 most relevant CPC codes
  5. Note CPC hierarchies

Common CPC Categories:

  • G06F: Computing/data processing
  • H04L: Digital communication/networks
  • G06Q: Business methods
  • H04W: Wireless communication
  • G06N: AI/neural networks
  • G06T: Image processing

Output: List of relevant CPC codes with descriptions


Step 5: Deep CPC Search (5-10 min)

Goal: Comprehensive search within classifications

Process:

  1. Search each CPC code identified
  2. Review 50-100 patents per CPC code
  3. Read abstracts and claims of top matches
  4. Document closest prior art
  5. Note key differences from invention

Tool call (needs only the SerpApi key; write CPC= exactly, since cpc: silently finds almost nothing):

search_patents_google(query="CPC=G06F21/00", limit=100)
search_patents_google(query="CPC=G06F21/00 access token", limit=100)

With OPS ready, use search_epo_patents(query='cpc="G06F21/00"', limit=100), alone and combined with ta= keywords. With BigQuery configured, search_patents_by_cpc_bigquery(cpc_code="G06F21/", limit=100, country="US") is an alternative.

Output: Comprehensive list of potentially blocking patents


Step 6: Timeline Analysis (2-3 min)

Goal: Understand technology evolution

Process:

  1. Filter results by date ranges
  2. Identify filing trends over time
  3. Find recent developments (last 2 years)
  4. Check priority dates
  5. Note technology progression

Tool calls (whichever patent search is set up, as in Step 3):

search_patents_google(query=QUERY, start_year=2022, end_year=2024)
search_patents_google(query=QUERY, start_year=2015, end_year=2021)

Output: Timeline showing technology development


Step 7: Patentability Report (5-10 min)

Goal: Professional assessment and recommendations

If Step 3 ran only a web first screen, the report's novelty, obviousness and patentability lines each read "Not assessed: only a web first screen was run; set up patent search and rerun", and the report is titled a first screen, not a patentability report.

Process:

  1. Analyze top 10 closest prior art
  2. Assess novelty (35 USC 102)
  3. Assess non-obviousness (35 USC 103)
  4. Rank prior art by relevance
  5. Provide claim strategy recommendations
  6. Generate IDS list

Output: Comprehensive patentability report


Report Format

# PRIOR ART SEARCH REPORT

## Executive Summary
- Invention: [Brief description]
- Search Date: [Date]
- Searcher: Claude Patent Creator
- Databases: whichever answered: Google Patents (SerpApi), EPO OPS or BigQuery, plus the paper sources `search_non_patent_literature` reports as searched
- Time Period: [Year range]

## Patentability Assessment

### Novelty (35 USC 102)
[Assessment of whether invention is novel]

Score: [High/Medium/Low]

Analysis:
- No exact matches found
- Closest prior art: US10123456
- Key differences: [List]

### Non-Obviousness (35 USC 103)
[Assessment of whether invention is non-obvious]

Score: [High/Medium/Low]

Analysis:
- Combinations considered: [List]
- Motivation to combine: [Analysis]
- Unexpected results: [If any]

## Top 10 Most Relevant Prior Art

### 1. US10123456B2 - [Title] (95% Relevance)
**Assignee**: Example Corp
**Filed**: 2018-03-15
**Granted**: 2019-09-30
**CPC**: G06F21/31, H04L29/06

**Summary**: [Brief abstract]

**Similarities**:
- Uses blockchain for authentication
- Employs public key cryptography
- Distributed verification

**Differences**:
- Does not use [novel feature 1]
- Lacks [novel feature 2]
- Different approach to [aspect]

**Relevance**: High - core technology overlap

---

[Continue for top 10 patents...]

## Search Methodology

### Keywords Used
- Primary: blockchain, authentication, distributed ledger
- Synonyms: cryptographic verification, decentralized identity
- Technical: public key infrastructure, digital signature

### CPC Codes Searched
- G06F21/31 (Authentication)
- H04L29/06 (Security arrangements)
- G06Q20/40 (Payment authentication)

### Databases
- Google BigQuery: 247 results reviewed
- USPTO API: 89 results reviewed
- Total patents analyzed: 336
- Relevant patents identified: 47
- Top prior art selected: 10

## Claim Strategy Recommendations

### Recommended Approach
1. **Focus on novel aspects**: [Specific features]
2. **Claim breadth**: Start broad, add dependent claims
3. **Avoid prior art**: Distinguish from US10123456 by [...]

### Suggested Independent Claim Language

A system for [invention], comprising: [novel element 1]; [novel element 2]; wherein [novel relationship/function]


### Dependent Claim Opportunities
- Specific implementations of [feature]
- Combinations with [technology]
- Variations in [parameter/configuration]

## IDS (Information Disclosure Statement) List

Patents to be disclosed to USPTO:

1. US10123456B2 - [Title]
2. US10234567A1 - [Title]
3. US10345678B1 - [Title]
4. US10456789A1 - [Title]
5. US10567890B2 - [Title]
6. EP3123456A1 - [Title]
7. WO2019/123456 - [Title]
8. US2020/0123456A1 - [Title]
9. US10678901B2 - [Title]
10. US10789012A1 - [Title]

## Conclusion

**Patentability**: [High/Medium/Low]

**Rationale**:
[Summary of why invention is or is not patentable]

**Recommended Next Steps**:
1. [Action item 1]
2. [Action item 2]
3. [Action item 3]

Integration Points

This skill integrates with:

  • Patent Search skill (Steps 3, 5, 6); BigQuery Patent Search only when configured
  • MPEP Search skill (For legal guidance)
  • Patent Claims Analyzer (For claim drafting)

Required Data Access

  • Google Patents through SerpApi (default), EPO OPS (fallback), or Google Cloud BigQuery (optional)
  • USPTO ODP (optional application metadata supplement only)
  • Internet access for patent retrieval

Estimated Time

  • Quick Search (Steps 1-3): 10-15 minutes
  • Thorough Search (Steps 1-6): 25-35 minutes
  • Complete Report (All 7 steps): 40-60 minutes

Tools Available

  • Bash: To run Python searches
  • Write: To save report and findings
  • Read: To load invention descriptions
  • Grep: To search through results

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/robthepcguy/claude-patent-creator/prior-art-search">View prior-art-search on skillZs</a>