← Back to Skills Marketplace
Zeelin Patent Retriever
by
Yuwen Yang
· GitHub ↗
· v0.1.2
373
Downloads
0
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install patent-retriever-bigquery
Description
Team ZeeLin’s production-grade patent evidence retrieval skill for Google Patents BigQuery. Converts natural-language research intent into auditable multi-ro...
Usage Guidance
This bundle appears coherent for querying Google Patents via BigQuery. Before running: (1) ensure the GOOGLE_APPLICATION_CREDENTIALS you provide follow least-privilege (only BigQuery query + storage if needed) to limit blast radius; (2) be aware BigQuery queries can incur cost—inspect and test queries with low limits first; (3) avoid committing credentials into the repository (.env) — scripts will load a local .env if present; (4) review the generated SQL in a safe environment if you have sensitive billing or data constraints; (5) validate outputs and JSON schemas before using results for downstream decisions.
Capability Analysis
Type: OpenClaw Skill
Name: patent-retriever-bigquery
Version: 0.1.2
The skill bundle is a legitimate tool designed for patent retrieval and analysis using Google Patents BigQuery. The code follows security best practices by using parameterized queries (ScalarQueryParameter) to prevent SQL injection and relies on standard, well-known dependencies like google-cloud-bigquery and jsonschema. The instructions in SKILL.md and the logic in scripts like patent_search_plan.py and build_query_plan.py are strictly aligned with the stated purpose of patent research, with no evidence of data exfiltration, unauthorized credential access, or malicious prompt injection.
Capability Assessment
Purpose & Capability
Name/description claim BigQuery patent retrieval and the bundle requires python3 and Google Cloud credentials (GOOGLE_APPLICATION_CREDENTIALS, GOOGLE_CLOUD_PROJECT) and includes BigQuery client code—these are expected and proportionate.
Instruction Scope
SKILL.md instructs installing listed Python deps and running the included scripts (seed -> build_plan -> execute_plan). The scripts only read/write local files, build SQL queries for BigQuery, and echo planned/effective filters. They do not reference unrelated system paths or remote endpoints beyond Google Cloud.
Install Mechanism
There is no remote download/install hook in the skill bundle. Dependencies are declared in requirements.txt (python-dotenv, google-cloud-bigquery, jsonschema) which is appropriate for a Python BigQuery client tool.
Credentials
Only GOOGLE_APPLICATION_CREDENTIALS and GOOGLE_CLOUD_PROJECT are required, which are the normal credentials for BigQuery access. The only additional behavior is optional loading of a local .env (scripts/config.py), which is a convenience and not a hidden exfiltration channel.
Persistence & Privilege
The skill is not always-enabled, does not modify other skills, and does not request persistent elevated platform privileges. It writes outputs to local result files as expected for a retrieval tool.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install patent-retriever-bigquery - After installation, invoke the skill by name or use
/patent-retriever-bigquery - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
Major update: Enhanced documentation, workflow clarity, and usability for patent evidence retrieval with Google Patents BigQuery.
- Skill renamed to **zeelin-patent-retriever** with a new, comprehensive SKILL.md focused on production workflows and cross-team use.
- Quickstart and standard command templates now included for faster onboarding and clear execution steps.
- Documentation expanded: clarified supported search filters, parameter mapping from natural language, and explicit rules for handling user-specified constraints (country, date, assignee, etc.).
- Added post-execution response template and common troubleshooting advice.
- All output contracts and validation requirements are now explicitly documented for downstream analysis and integration.
v0.1.1
- Added homepage field to skill metadata and Openclaw metadata section.
- Declared required environment variables and Python 3 binary under Openclaw's metadata.requires.
- No functional changes to the retrieval workflow or output contract.
v0.1.0
Initial release of patent-retriever-bigquery:
- Enables structured patent retrieval via Google Patent BigQuery based on topics/keywords.
- Guides users to build search plans and retrieve at least 20 patent records per request.
- Outputs results as structured JSON files for analysis.
- Provides command-line workflow for seed retrieval, plan building, execution, and output validation.
- Requires user configuration of Google Cloud environment variables and installation of Python dependencies.
Metadata
Frequently Asked Questions
What is Zeelin Patent Retriever?
Team ZeeLin’s production-grade patent evidence retrieval skill for Google Patents BigQuery. Converts natural-language research intent into auditable multi-ro... It is an AI Agent Skill for Claude Code / OpenClaw, with 373 downloads so far.
How do I install Zeelin Patent Retriever?
Run "/install patent-retriever-bigquery" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Zeelin Patent Retriever free?
Yes, Zeelin Patent Retriever is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Zeelin Patent Retriever support?
Zeelin Patent Retriever is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Zeelin Patent Retriever?
It is built and maintained by Yuwen Yang (@yangyuwen-bri); the current version is v0.1.2.
More Skills