Uspto Database
jaechang-hits/SciAgent-Skills
Access USPTO patent data via PatentsView REST API and Google Patents Public Data (BigQuery).
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification
Install Prior Art Search
$ npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RobThePCGuy/Claude-Patent-Creator prior-art-search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prior-art-search .claude/skills/prior-art-search && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "prior-art-search" agent skill from https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/prior-art-search into .claude/skills/prior-art-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prior-art-search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/prior-art-searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RobThePCGuy/Claude-Patent-Creator prior-art-search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/prior-art-search .agents/skills/prior-art-search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prior-art-search" agent skill from https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/prior-art-search into .agents/skills/prior-art-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prior-art-search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RobThePCGuy/Claude-Patent-Creator prior-art-search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/prior-art-search .cursor/skills/prior-art-search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prior-art-search" agent skill from https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/prior-art-search into .cursor/skills/prior-art-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prior-art-search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/RobThePCGuy/Claude-Patent-Creator.git --path skills/prior-art-search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RobThePCGuy/Claude-Patent-Creator prior-art-search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/prior-art-search .gemini/skills/prior-art-search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prior-art-search" agent skill from https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/prior-art-search into .gemini/skills/prior-art-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prior-art-search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install RobThePCGuy/Claude-Patent-Creator prior-art-searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creator.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/prior-art-search .github/skills/prior-art-search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prior-art-search" agent skill from https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/prior-art-search into .github/skills/prior-art-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prior-art-search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RobThePCGuy/Claude-Patent-Creator prior-art-search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/prior-art-search .opencode/skills/prior-art-search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prior-art-search" agent skill from https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/prior-art-search into .opencode/skills/prior-art-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prior-art-search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
prior-art-search- GitHub stars
- 196
- Token cost
- ~2.2k tokens
- SKILL.md length
- 661 words
- Files
- 2
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- MIT
At a glance
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification
- Works in 7 steps: Invention Definition (2-3 min) → Keyword Strategy (2-3 min) → Broad Keyword Search (3-5 min) → …
- Tasks that involve Intellectual property
- SKILL.md covers When to Use, What This Skill Does, The 7-Step Methodology and Report Format, plus 4 more sections
- Runs Python scripts from its folder
What it does
Prior Art Search is an agent skill from RobThePCGuy/Claude-Patent-Creator. Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `prior_art_types.py`).
It sits in Legal & Compliance, covering Intellectual property. It works with Google BigQuery. The repository describes itself as: USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks… The licence is MIT.
When your agent uses it
- Tasks that involve Intellectual property
Example prompts
- “/prior-art-search”
Requirements
- Python 3
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit a089731. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Prior Art Search loads about 2.2k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 661 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from RobThePCGuy/Claude-Patent-Creator at commit a089731, republished under its MIT licence (© RobThePCGuy). 661 words, ~2,248 tokens.
Download SKILL.mdSave it as
.claude/skills/prior-art-search/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- prior-art-search
- description
- Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification
- tools
- Bash, Read, Write
- model
- sonnet
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 (BigQuery)
- 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:
- Interview user about invention
- Extract core technical elements
- Identify novel features
- List all components/steps
- 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:
- Primary keywords from invention
- Synonyms and variations
- Technical terminology
- Industry-specific terms
- 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
ORin 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" signatureStep 3: Broad Keyword Search (3-5 min)
Goal: Cast wide net to find relevant patents
Process:
- Run keyword searches on BigQuery
- Review top 20-30 results per query
- Identify most relevant patents
- Refine keyword strategy based on results
- Document relevant patents found
Code:
from mcp_server.bigquery_search import BigQueryPatentSearch
searcher = BigQueryPatentSearch()
results = searcher.search_by_keywords(
query="blockchain authentication", # terms AND-matched, ranked by relevance
limit=30,
country="US",
start_year=2015, # filing year; look back 5-10 years
)Output: List of 10-20 potentially relevant patents
Step 4: CPC Code Identification (2-3 min)
Goal: Find relevant classification codes
Process:
- Extract CPC codes from relevant patents found in Step 3
- Analyze CPC code descriptions
- Identify primary classification areas
- Select 3-5 most relevant CPC codes
- 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
Show full SKILL.md (252 more words)Show less
Step 5: Deep CPC Search (5-10 min)
Goal: Comprehensive search within classifications
Process:
- Search each CPC code identified
- Review 50-100 patents per CPC code
- Read abstracts and claims of top matches
- Document closest prior art
- Note key differences from invention
Code:
results = searcher.search_by_cpc(
cpc_code="G06F21/", # Security arrangements
limit=100,
country="US"
)Output: Comprehensive list of potentially blocking patents
Step 6: Timeline Analysis (2-3 min)
Goal: Understand technology evolution
Process:
- Filter results by date ranges
- Identify filing trends over time
- Find recent developments (last 2 years)
- Check priority dates
- Note technology progression
Code:
# Search by year ranges
recent = searcher.search_by_keywords(query, start_year=2022, end_year=2024)
older = searcher.search_by_keywords(query, start_year=2015, end_year=2021)Output: Timeline showing technology development
Step 7: Patentability Report (5-10 min)
Goal: Professional assessment and recommendations
Process:
- Analyze top 10 closest prior art
- Assess novelty (35 USC 102)
- Assess non-obviousness (35 USC 103)
- Rank prior art by relevance
- Provide claim strategy recommendations
- 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: BigQuery (100M+ patents), USPTO API
- 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 LanguageA 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:
- BigQuery Patent Search skill (Step 3, 5, 6)
- MPEP Search skill (For legal guidance)
- Patent Claims Analyzer (For claim drafting)
Required Data Access
- Google Cloud BigQuery (100M+ patents)
- USPTO API (optional, for additional coverage)
- 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
© RobThePCGuy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/prior-art-search of RobThePCGuy/Claude-Patent-Creator.
- SKILL.md
- prior_art_types.py
Open the folder on GitHubat commit a089731
Compare with similar skills
Prior Art Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prior Art Search this skillRobThePCGuy/Claude-Patent-Creator | 196 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Uspto Databasejaechang-hits/SciAgent-Skills | 374 | 1 repos | ~4.6k | Automated safety check: Pass | CC0-1.0 | |
| Paper to Chinese Patent DrafterYuan1z0825/nature-skills | 47k | 1 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill | 107 | 1 repos | ~959 | Automated safety check: Pass | None | |
| Patent Examinegfodor/legal-skills | 393 | — | ~4.8k | Automated safety check: Pass | GPL-3.0 | |
| Patent Auditgfodor/legal-skills | 393 | — | ~2.9k | Automated safety check: Pass | GPL-3.0 |
Similar skills
Paper to Chinese Patent Drafter
Yuan1z0825/nature-skills
Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.
Paper To Cn Patent
snipp-zha/Paper-to-patent-Skill
Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.
Patent Examine
gfodor/legal-skills
Iteratively examine and revise a draft U.S. An agent skill from gfodor/legal-skills.
Patent Audit
gfodor/legal-skills
Audit a draft U.S. An agent skill from gfodor/legal-skills.
Replica Brand
Jakeschincariol/replica-skill
Names and rebrands an app clone so it is the user's own: name candidates with the trademark, domain, store and handle checks to run, a new palette checked for contrast, a logo brief, a voice guide…
More from RobThePCGuy/Claude-Patent-Creator
All 17 skills in this repoBigquery Patent Search
RobThePCGuy/Claude-Patent-Creator
Fast, cloud-based patent searching across 100 million+ worldwide patents using Google BigQuery - keyword search, CPC classification, patent details retrieval
Development Assistant
RobThePCGuy/Claude-Patent-Creator
Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.
Epc Search
RobThePCGuy/Claude-Patent-Creator
RAG search across EPC provisions, EPO Guidelines for Examination, and PCT rules for European and international patent law research
Epo Patent Analyzer
RobThePCGuy/Claude-Patent-Creator
Automated analysis of patent applications for EPO compliance with Art.
Epo Patent Search
RobThePCGuy/Claude-Patent-Creator
Search European patents using EPO OPS API (full-text, legal status, families) and BigQuery (100M+ patents, EP filter) for prior art, competitive intelligence, and freedom-to-operate analysis
Index Manager
RobThePCGuy/Claude-Patent-Creator
Manages MPEP index lifecycle including downloads, building, maintenance, and optimization.
Related
Works with
Categories
Questions about Prior Art Search
What does Prior Art Search do?
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification. Prior Art Search is an agent skill from RobThePCGuy/Claude-Patent-Creator.
When should I use Prior Art Search?
Prior Art Search fits situations like: tasks that involve Intellectual property.
How do I install Prior Art Search in Claude Code?
Run `npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a claude-code`. Or copy the skill folder (skills/prior-art-search in RobThePCGuy/Claude-Patent-Creator) into .claude/skills/prior-art-search in your project. Claude Code loads it when a task matches its description.
How do I install Prior Art Search in Codex?
Run `npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a codex`. Or copy the skill folder (skills/prior-art-search in RobThePCGuy/Claude-Patent-Creator) into .agents/skills/prior-art-search in your project. Codex loads it when a task matches its description.
Can I use Prior Art Search in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RobThePCGuy/Claude-Patent-Creator --skill prior-art-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prior-art-search, .gemini/skills/prior-art-search, .github/skills/prior-art-search and .opencode/skills/prior-art-search in your project.
What does Prior Art Search need to run?
Going by SKILL.md and its folder, Prior Art Search needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Prior Art Search access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Prior Art Search safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Prior Art Search use?
Prior Art Search is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Prior Art Search use?
About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Prior Art Search?
Skills that share tags, products or a category with Prior Art Search: Uspto Database (jaechang-hits/SciAgent-Skills, 374 stars), Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars), Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 107 stars) and Patent Examine (gfodor/legal-skills, 393 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prior Art Search?
RobThePCGuy (a GitHub user) maintains it in RobThePCGuy/Claude-Patent-Creator, which has 196 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 6, 2026.
Source: RobThePCGuy/Claude-Patent-Creator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.