Agent skill

Prior Art Search

by illusionaireal in illusionaireal/oh-my-patent

A skill your agent uses when searching patents and technical literature for prior art, novelty, or patentability assessment.

MITAuto-check passedLegal & Compliance

Install Prior Art Search

skills CLI

$ npx skills add illusionaireal/oh-my-patent --skill prior-art-search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install illusionaireal/oh-my-patent prior-art-search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/illusionaireal/oh-my-patent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/skills/prior-art-search .claude/skills/prior-art-search && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "prior-art-search" agent skill from https://github.com/illusionaireal/oh-my-patent/tree/master/src/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

$skill-installer install https://github.com/illusionaireal/oh-my-patent/tree/master/src/skills/prior-art-search

Type 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.

skills CLI

$ npx skills add illusionaireal/oh-my-patent --skill prior-art-search -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install illusionaireal/oh-my-patent prior-art-search --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/illusionaireal/oh-my-patent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/skills/prior-art-search .agents/skills/prior-art-search && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "prior-art-search" agent skill from https://github.com/illusionaireal/oh-my-patent/tree/master/src/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.

skills CLI

$ npx skills add illusionaireal/oh-my-patent --skill prior-art-search -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install illusionaireal/oh-my-patent prior-art-search --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/illusionaireal/oh-my-patent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/skills/prior-art-search .cursor/skills/prior-art-search && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "prior-art-search" agent skill from https://github.com/illusionaireal/oh-my-patent/tree/master/src/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

$ gemini skills install https://github.com/illusionaireal/oh-my-patent.git --path src/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.

skills CLI

$ npx skills add illusionaireal/oh-my-patent --skill prior-art-search -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install illusionaireal/oh-my-patent prior-art-search --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/illusionaireal/oh-my-patent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/skills/prior-art-search .gemini/skills/prior-art-search && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "prior-art-search" agent skill from https://github.com/illusionaireal/oh-my-patent/tree/master/src/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.

GitHub CLI

$ gh skill install illusionaireal/oh-my-patent prior-art-search

Installs 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).

skills CLI

$ npx skills add illusionaireal/oh-my-patent --skill prior-art-search -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/illusionaireal/oh-my-patent.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/skills/prior-art-search .github/skills/prior-art-search && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "prior-art-search" agent skill from https://github.com/illusionaireal/oh-my-patent/tree/master/src/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.

skills CLI

$ npx skills add illusionaireal/oh-my-patent --skill prior-art-search -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install illusionaireal/oh-my-patent prior-art-search --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/illusionaireal/oh-my-patent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/skills/prior-art-search .opencode/skills/prior-art-search && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "prior-art-search" agent skill from https://github.com/illusionaireal/oh-my-patent/tree/master/src/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: 104
Token cost: ~1.8k tokens
SKILL.md length: 595 words
Files: 1
Skills in repo: 7
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when searching patents and technical literature for prior art, novelty, or patentability assessment.

Works in 5 steps: google_scholar → uspto_patent (optional but recommended) → semantic_scholar (optional) → …
Searching patents and technical literature for prior art
SKILL.md covers Overview, Usage, Input Parameters and Output Format, plus 7 more sections
Reaches connect.zhihuiya.com

What it does

Prior Art Search is an agent skill from illusionaireal/oh-my-patent. Use when searching patents and technical literature for prior art, novelty, or patentability assessment.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Legal & Compliance, covering Intellectual property. It works with Model Context Protocol and Semantic Scholar. The repository describes itself as: 🏛️ The patent plugin for AI coding agents — turn technical ideas into patent disclosures with Claude Code, Codex, and OpenCode. The licence is MIT.

When your agent uses it

Searching patents and technical literature for prior art
Patentability assessment

Example prompts

“/prior-art-search”

Requirements

A credential in YOUR_PATSNAP_MCP_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

google_scholar
uspto_patent (optional but recommended)
semantic_scholar (optional)
cnipa_patent (recommended, required for CN jurisdiction)
patsnap_search (recommended)

What it can do on your machine

Read from SKILL.md and the folder at commit f44755c. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, typescript and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- connect.zhihuiya.com
Also links to:
- open.zhihuiya.com
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 1.8k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 595 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~30
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

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 illusionaireal/oh-my-patent at commit f44755c, republished under its MIT licence (© illusionaireal). 595 words, ~1,794 tokens.

Download SKILL.mdSave it as .claude/skills/prior-art-search/SKILL.md (or your agent's skills folder).

name: prior-art-search
description: Use when searching patents and technical literature for prior art, novelty, or patentability assessment.

Prior Art Search Skill

Search existing patents and technical literature to identify prior art for novelty and patentability assessment.

Overview

This skill integrates with multiple MCP servers (Google Scholar, USPTO, Semantic Scholar) to conduct comprehensive prior art searches across patents, academic papers, and technical documentation.

Usage

The skill is typically invoked by the patent-landscape-analyst agent during the RESEARCH stage of the patent workflow.

Basic Usage Pattern

typescript

// The skill is invoked through agent orchestration
// Agent: patent-landscape-analyst
// Input: topic keywords, technical domain
// Output: aggregated landscape report

Input Parameters

Required

query: Search keywords and technical terms
- Example: "homomorphic encryption privacy-preserving computation"

Optional

searchScope: Time range for results
- Default: Last 5 years
- Options: 1year, 3years, 5years, 10years, all
maxResultsPerSource: Maximum results from each source
- Default: 5
- Range: 1-20
sources: Which databases to query
- Default: All enabled MCP servers
- Options: google_scholar, uspto_patent, semantic_scholar, cnipa_patent, patsnap_search
jurisdiction: Filter by patent jurisdiction
- Default: All jurisdictions
- Options: CN, US, PCT
- EP / JP are not supported (REQ-017): if the user asks for them, say so explicitly, then proceed without a jurisdiction filter (or suggest PCT for international filings). Never pass an unsupported code downstream.

Output Format

Primary Output

File: references/landscape_{topic_slug}.md

Contains aggregated search results organized by:

Patent references (with classification codes)
Academic literature
Technical standards
Industry implementations

Secondary Output

Files: references/{source}_{id}.md

Individual evidence cards for each finding:

Full citation
Abstract/summary
Relevance score
Key technical features
Novelty comparison notes

Examples

Example 1: Basic Prior Art Search

markdown

<!-- Invoked by patent-landscape-analyst -->

Input:
- Topic: "blockchain-based cross-border payment with privacy"
- Scope: Last 5 years
- Max results: 10 per source

Output:
references/landscape_blockchain-cross-border-payment.md
  - 8 relevant patents (USPTO, EPO, CNIPA)
  - 12 academic papers (Google Scholar, Semantic Scholar)
  - 3 technical standards (ISO, IEEE)

references/uspto_US10123456.md
references/cnipa_CN108234567.md
references/scholar_arxiv2023-12345.md
...

Example 2: Targeted Patent Search

markdown

Input:
- Query: "federated learning differential privacy medical data"
- Jurisdiction: CN
- Scope: 3 years
- Sources: uspto_patent, semantic_scholar

Output:
references/landscape_federated-learning-medical.md
  - 5 CN patents with IPC codes H04L29/06, G06N20/00
  - 8 academic papers from top conferences
  - Novelty gaps identified in medical-specific privacy

Example 3: Comprehensive Technical Search

markdown

Input:
- Query: "zero-knowledge proof identity authentication edge computing"
- Scope: All time
- Max results: 20

Output:
references/landscape_zkp-identity-edge.md
  Organized sections:
  1. Core patents (15 references)
  2. Academic foundations (25 papers)
  3. Implementation examples (8 systems)
  4. Novelty analysis summary

MCP Server Dependencies

Required MCP Servers

google_scholar
- Academic literature search
- Citation tracking
- Conference/journal papers
uspto_patent (optional but recommended)
- US patent database
- Patent classification lookup
- Full-text patent search
semantic_scholar (optional)
- Academic paper search with AI-powered relevance
- Citation graphs
- Influence metrics
cnipa_patent (recommended, required for CN jurisdiction)
- China National Intellectual Property Administration
- CN patent database with IPC classification
- Chinese patent full-text search
patsnap_search (recommended)
- 智慧芽 (Patsnap) patent + literature fusion search
- 2.1 billion+ global patent data across 174 patent offices
- Includes legal status, patent family, and citation data
- REST API + native MCP service (Streamable HTTP)

Configuration

MCP servers should be configured in .claude/settings.json:

json

{
  "mcpServers": {
    "google_scholar": {
      "command": "mcp-google-scholar",
      "args": []
    },
    "semantic_scholar": {
      "command": "mcp-semantic-scholar",
      "args": []
    },
    "patsnap_search": {
      "url": "https://connect.zhihuiya.com/mcp?apikey=YOUR_PATSNAP_MCP_KEY",
      "type": "streamableHttp"
    }
  }
}

智慧芽 MCP Key 获取：

登录 https://open.zhihuiya.com/
在 API 密钥页面创建新的 MCP Key（格式 sk-xxxxxxxxxxxx）
将 Key 填入 url 的 apikey 参数中

注意：智慧芽 MCP 使用 Streamable HTTP transport，不是传统的 stdio MCP。配置时需使用 url + type: "streamableHttp" 格式，而非 command + args。

Show full SKILL.md (226 more words)Show less

Integration with Workflow

Stage: RESEARCH

User provides patent topic
archimedes routes to patent-landscape-analyst
Analyst invokes prior-art-search skill
Results written to references/landscape_{topic_slug}.md
Feature matrix written to references/feature-matrix_{topic_slug}.md
Problem map written to references/problem-map_{topic_slug}.md
Workflow advances to BRAINSTORM_R1

Outputs Used By

patentability-evaluator: Assesses novelty against prior art
patent-innovation-architect: Identifies gaps for innovation
patent-adversarial-examiner: Challenges novelty claims

Performance Notes

Search time: 30-90 seconds per query (depends on sources)
Network required: MCP servers make external API calls
Rate limits: Respect source-specific rate limits (handled by MCP)
Caching: Results cached per session to avoid redundant searches

Error Handling

Common Errors

MCP Server Not Available
- Falls back to available sources
- Logs warning in landscape report
No Results Found
- Returns empty landscape with suggestions to broaden query
- Recommends alternative keywords
Rate Limit Exceeded
- Pauses and retries with exponential backoff
- Notifies user of delay

Best Practices

Query Construction
- Use technical terms, not business descriptions
- Include domain-specific keywords
- Combine multiple concepts with proper connectors
Scope Selection
- Start with 5 years for fast iteration
- Expand to 10 years if few results
- Use "all time" only for emerging technologies
Result Validation
- Always review landscape_{topic_slug}.md before proceeding
- Verify relevance of top 3 references manually
- Cross-check patent classifications

evidence-card: Formats individual prior art entries
quality-gate: Validates landscape report completeness
jurisdiction: Filters by patent jurisdiction rules

Files

Just SKILL.md in src/skills/prior-art-search of illusionaireal/oh-my-patent.

Open the folder on GitHubat commit f44755c

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.

Prior Art Search compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Prior Art Search this skillillusionaireal/oh-my-patent	104	—	~1.8k	Automated safety check: Pass	MIT	2 days ago
Patsnap Ip Searchingpatsnap/mcp	113	—	~1.1k	Automated safety check: Pass	Apache-2.0	1 mo ago
Patsnap Triz Case Librarypatsnap/mcp	113	—	~885	Automated safety check: Pass	Apache-2.0	1 mo ago
Patsnap Workspacepatsnap/mcp	113	—	~777	Automated safety check: Pass	Apache-2.0	1 mo ago
Mpep SearchRobThePCGuy/Claude-Patent-Creator	196	—	~978	Automated safety check: Pass	MIT	4 days ago
Patsnap Advanced Patent Searchpatsnap/mcp	113	—	~650	Automated safety check: Pass	Apache-2.0	1 mo ago

Similar skills

Patsnap Ip Searching
patsnap/mcp
Patsnap Patent Research MCP for AI agents. An agent skill from patsnap/mcp.
113 GitHub stars~1.1k tokensUpdated 1 mo ago
Legal & ComplianceAuto-check passed
Patsnap Triz Case Library
patsnap/mcp
Patsnap TRIZ Case Library MCP for AI agents. An agent skill from patsnap/mcp.
113 GitHub stars~885 tokensUpdated 1 mo ago
Legal & ComplianceAuto-check passed
Patsnap Workspace
patsnap/mcp
Patsnap Workspace MCP for AI agents. An agent skill from patsnap/mcp.
113 GitHub stars~777 tokensUpdated 1 mo ago
Legal & ComplianceAuto-check passed
Mpep Search
RobThePCGuy/Claude-Patent-Creator
Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.
196 GitHub stars~978 tokensUpdated 4 days ago
Legal & ComplianceAuto-check passed
Patsnap Advanced Patent Search
patsnap/mcp
Patsnap Advanced Patent Search MCP for AI agents. An agent skill from patsnap/mcp.
113 GitHub stars~650 tokensUpdated 1 mo ago
Legal & ComplianceAuto-check passed
Patsnap Biological Modality
patsnap/mcp
Biological sequence and modality intelligence via Patsnap MCP.
113 GitHub stars~771 tokensUpdated 1 mo ago
Legal & ComplianceAuto-check passed

Questions about Prior Art Search

What does Prior Art Search do?

A skill your agent uses when searching patents and technical literature for prior art, novelty, or patentability assessment. Prior Art Search is an agent skill from illusionaireal/oh-my-patent. Use when searching patents and technical literature for prior art, novelty, or patentability assessment.

When should I use Prior Art Search?

Prior Art Search fits situations like: searching patents and technical literature for prior art; patentability assessment.

How do I install Prior Art Search in Claude Code?

Run `npx skills add illusionaireal/oh-my-patent --skill prior-art-search -a claude-code`. Or copy the skill folder (src/skills/prior-art-search in illusionaireal/oh-my-patent) 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 illusionaireal/oh-my-patent --skill prior-art-search -a codex`. Or copy the skill folder (src/skills/prior-art-search in illusionaireal/oh-my-patent) 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 illusionaireal/oh-my-patent --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?

SKILL.md names no scripts, command-line tools or credentials: Prior Art Search is instructions for the agent only. Our summary lists: A credential in YOUR_PATSNAP_MCP_KEY.

Does Prior Art Search access the network?

SKILL.md names 2 domains. In commands or code: connect.zhihuiya.com; the agent is likely to contact it when it follows the instructions. As links in the text: open.zhihuiya.com. 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 1.8k tokens (SKILL.md is roughly 7.2k 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: Patsnap Ip Searching (patsnap/mcp, 113 stars), Patsnap Triz Case Library (patsnap/mcp, 113 stars), Patsnap Workspace (patsnap/mcp, 113 stars) and Mpep Search (RobThePCGuy/Claude-Patent-Creator, 196 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?

illusionaireal (a GitHub user) maintains it in illusionaireal/oh-my-patent, which has 104 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 9, 2026.

Source: illusionaireal/oh-my-patent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Prior Art Search

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Prior Art Search Skill

Overview

Usage

Basic Usage Pattern

Input Parameters

Required

Optional

Output Format

Primary Output

Secondary Output

Examples

Example 1: Basic Prior Art Search

Example 2: Targeted Patent Search

Example 3: Comprehensive Technical Search

MCP Server Dependencies

Required MCP Servers

Configuration

Integration with Workflow

Stage: RESEARCH

Outputs Used By

Performance Notes

Error Handling

Common Errors

Best Practices

Related Skills

Files

Compare with similar skills

Similar skills

More from illusionaireal/oh-my-patent

Related

Questions about Prior Art Search