How do I install the Patent Search skill?

Run npx skillmds add robthepcguy/patent-search 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 Patent Search safe to use?

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

Which AI agents work with Patent Search?

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 Patent Search free to use?

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

Who published Patent Search?

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

Patent Search by robthepcguy — Agent Skill

Name: Patent Search
Rating: 4.5 (4 reviews)
Author: robthepcguy

File contents

Patent Search Skill

This skill points Claude at the BigQuery patent-search tools registered by the patent-creator MCP server. Call the tools directly; do not shell out to Python.

When to use

Find prior art by keyword, classification, or family.
Pull full patent records (title, abstract, claims, description) for US patents.
Cross-reference an EP/WO patent into its US family member to get full text.

Available MCP tools

Tool	What it does
`search_patents_bigquery`	Keyword search across abstract / title / claims (US only for claims).
`get_patent_bigquery`	Full patent details by publication number.
`search_patents_by_cpc_bigquery`	Search by CPC classification prefix.
`search_patents_by_ipc_bigquery`	Search by IPC classification prefix (good for older or non-US patents).
`search_patent_family_bigquery`	All publications sharing a family ID across jurisdictions.
`check_bigquery_status`	Verify auth and quota project before a long workflow.

Cost notes

BigQuery on-demand pricing is $6.25 / TiB (1 TiB free per month). The MCP server enforces a per-query bytes-billed ceiling, defaulting to 350 GiB. Override via PATENT_BIGQUERY_MAX_BYTES_BILLED if you need a larger scan window.

Choosing keywords

2-3 keywords work better than long phrases (BigQuery LIKE matching is literal).
For non-US patents, claims is empty in the dataset; the MCP keyword tool already searches title/abstract for those jurisdictions. For full text on EP/WO, use the EPO OPS tools instead.
Use search_patent_family_bigquery to bridge from an EP/WO hit to its US family member when you need claims.

Common workflows

Prior art sweep:

search_patents_bigquery(query=…, country="US") — broad scan.
Pick the top hits' CPC codes from get_patent_bigquery.
search_patents_by_cpc_bigquery(cpc_code=…) — pull adjacent technology.

Cross-jurisdiction lookup:

search_patents_bigquery(query=…, country="EP").
For any EP hit, get_patent_bigquery to get its family_id.
search_patent_family_bigquery(family_id=…) to find the US member with full claims.

---name: patent-searchdescription: Search 100M+ patents via the MCP server's BigQuery tools. No standalone scripts; everything goes through the MCP tools registered by the patent-creator server.--- # Patent Search Skill This skill points Claude at the BigQuery patent-search tools registered by the patent-creator MCP server. Call the tools directly; do not shell out to Python. ## When to use - Find prior art by keyword, classification, or family. - Pull full patent records (title, abstract, claims, description) for US patents. - Cross-reference an EP/WO patent into its US family member to get full text. ## Available MCP tools | Tool | What it does | |------|--------------| | `search_patents_bigquery` | Keyword search across abstract / title / claims (US only for claims). | | `get_patent_bigquery` | Full patent details by publication number. | | `search_patents_by_cpc_bigquery` | Search by CPC classification prefix. | | `search_patents_by_ipc_bigquery` | Search by IPC classification prefix (good for older or non-US patents). | | `search_patent_family_bigquery` | All publications sharing a family ID across jurisdictions. | | `check_bigquery_status` | Verify auth and quota project before a long workflow. | ## Cost notes BigQuery on-demand pricing is $6.25 / TiB (1 TiB free per month). The MCP server enforces a per-query bytes-billed ceiling, defaulting to 350 GiB. Override via `PATENT_BIGQUERY_MAX_BYTES_BILLED` if you need a larger scan window. ## Choosing keywords - 2-3 keywords work better than long phrases (BigQuery `LIKE` matching is literal). - For non-US patents, `claims` is empty in the dataset; the MCP keyword tool already searches title/abstract for those jurisdictions. For full text on EP/WO, use the EPO OPS tools instead. - Use `search_patent_family_bigquery` to bridge from an EP/WO hit to its US family member when you need claims. ## Common workflows **Prior art sweep:** 1. `search_patents_bigquery(query=…, country="US")` — broad scan. 2. Pick the top hits' CPC codes from `get_patent_bigquery`. 3. `search_patents_by_cpc_bigquery(cpc_code=…)` — pull adjacent technology. **Cross-jurisdiction lookup:** 1. `search_patents_bigquery(query=…, country="EP")`. 2. For any EP hit, `get_patent_bigquery` to get its `family_id`. 3. `search_patent_family_bigquery(family_id=…)` to find the US member with full claims.

Frequently asked questions