How do I install the Patsnap Patent Analysis skill?

Run npx skillmds@latest add patsnap/patsnap-patent-analysis in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Patsnap Patent Analysis safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Patsnap Patent Analysis?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Patsnap Patent Analysis free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Patsnap Patent Analysis?

patsnap (@patsnap) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Patsnap Patent Analysis by patsnap — Agent Skill

Name: Patsnap Patent Analysis
Author: patsnap

Patsnap Patent Analysis

Patsnap Patent Analysis MCP for AI agents. Aggregates and mines a patent search result into trends, distributions, rankings, cross-tabs, keyword clouds, and innovation sunbursts. Use after a patent-search tool has returned a reusable search expression; this service analyzes rather than discovers patents.

patsnap Updated Sep 17, 2026

File contents

Setup

Get your API key at https://open.zhihuiya.com

Patent Analysis

This skill connects your AI agent to Patsnap's Patent Analysis MCP server.

Prerequisites

{
  "mcpServers": {
    "patent_analysis": {
      "url": "https://connect.zhihuiya.com/e14e5f/logic-mcp?apikey=YOUR_API_KEY",
      "type": "streamableHttp"
    }
  }
}

For the full tool schema, refer to: https://open.zhihuiya.com/marketplace/mcp-servers/patent-analysis

Instructions for AI Agents

Preserve the upstream source

Both analysis tools require a source object derived from the search expression returned by search_patents. Preserve that object for downstream analysis. If it is absent, first invoke an available patent-search MCP. Do not fabricate source from prose or substitute a list of patent numbers unless the live tool schema explicitly supports it.

Choose the analysis tool

Use aggregate_patents for trend, distribution, ranking, or one-/two-dimensional cross-tab analysis. It requires source and dimensions; optional inputs include limit_per_dimension and sorts.
Use mine_patent_text for a keyword cloud or innovation sunburst. It requires source and subtype; chart_limit controls output size.

Keep comparisons valid

Keep the same source across comparisons unless the user asks to change the patent population. Report the source scope, date and jurisdiction coverage, and family-deduplication assumptions with every analysis.

Counts represent records under the supplied search expression. Do not equate them directly with market share, technical quality, commercial value, or legal strength. Clearly label interpretations and recommend drill-down queries that could test them.

Example Workflows

Show annual filing trends and top applicants for this search result.
Build a jurisdiction-by-applicant cross-tab.
Produce a keyword cloud and explain the dominant themes.
Generate an innovation sunburst and identify branches for deeper review.

Resources

MCP Server: Patent Analysis
Patsnap Open Platform: open.zhihuiya.com
Patsnap: https://www.patsnap.com

---name: patsnap-patent-analysisdescription: Patsnap Patent Analysis MCP for AI agents. Aggregates and mines a patent search result into trends, distributions, rankings, cross-tabs, keyword clouds, and innovation sunbursts. Use after a patent-search tool has returned a reusable search expression; this service analyzes rather than discovers patents.---## SetupGet your API key at https://open.zhihuiya.com# Patent AnalysisThis skill connects your AI agent to **Patsnap's Patent Analysis MCP server**.## Prerequisites```json{ "mcpServers": { "patent_analysis": { "url": "https://connect.zhihuiya.com/e14e5f/logic-mcp?apikey=YOUR_API_KEY", "type": "streamableHttp" } }}```For the full tool schema, refer to:https://open.zhihuiya.com/marketplace/mcp-servers/patent-analysis---## Instructions for AI Agents### Preserve the upstream sourceBoth analysis tools require a `source` object derived from the search expression returned by `search_patents`. Preserve that object for downstream analysis. If it is absent, first invoke an available patent-search MCP. Do not fabricate `source` from prose or substitute a list of patent numbers unless the live tool schema explicitly supports it.### Choose the analysis tool- Use `aggregate_patents` for trend, distribution, ranking, or one-/two-dimensional cross-tab analysis. It requires `source` and `dimensions`; optional inputs include `limit_per_dimension` and `sorts`.- Use `mine_patent_text` for a keyword cloud or innovation sunburst. It requires `source` and `subtype`; `chart_limit` controls output size.### Keep comparisons validKeep the same `source` across comparisons unless the user asks to change the patent population. Report the source scope, date and jurisdiction coverage, and family-deduplication assumptions with every analysis.Counts represent records under the supplied search expression. Do not equate them directly with market share, technical quality, commercial value, or legal strength. Clearly label interpretations and recommend drill-down queries that could test them.## Example Workflows- Show annual filing trends and top applicants for this search result.- Build a jurisdiction-by-applicant cross-tab.- Produce a keyword cloud and explain the dominant themes.- Generate an innovation sunburst and identify branches for deeper review.## Resources- **MCP Server**: [Patent Analysis](https://open.zhihuiya.com/marketplace/mcp-servers/patent-analysis)- **Patsnap Open Platform**: [open.zhihuiya.com](https://open.zhihuiya.com)- Patsnap: [https://www.patsnap.com](https://www.patsnap.com)

Frequently asked questions