Zhihuiya Patent Claims Data

This skill guides you on how to retrieve and present patent claims data from the Zhihuiya (PatSnap) patent database, helping IP professionals, patent analysts, and R&D teams quickly access the claims section of any patent.

Calling the Tool

• API Endpoint: /zhihuiya/claimData (full parameters/responses/error codes in references/api.md)
• Python Script: python scripts/patent_claims.py '<JSON params>' [--inline]
• Cost constraint: This tool consumes credits. Within the same session and same parameter combination, it defaults to a single call with a 24-hour local cache. Do not automatically retry with different keywords, pagination, or parameters on failure/empty results. Inform the user of additional credit consumption before continuing retrieval.

Output strategy (script default behavior):

• Always write the full response to <cwd>/nexscope/<YYYY-MM-DD>/<session>/data/ecommerce.patent-claims-<timestamp>.json (<cwd> is the working directory when the script executes, which in Claude Code is the current project directory; <session> is taken from the SESSION_ID environment variable, automatically grouped by user task; do not write to /tmp; error if the current directory is not writable)
• Response body <= 8 KB: write to disk then print full JSON to stdout
• Response body > 8 KB: write to disk then print only a summary to stdout (top-level fields, common counts like total/costToken, length of the largest list field + first 3 samples)
• Add --inline to force full output to stdout (still writes to disk)

Reading data: Check the summary first to determine if it is sufficient. When specific fields are needed, use jq or ConvertFrom-Json to extract from the saved JSON file as needed, avoiding loading the entire JSON into context.

Authentication & Credits