Retrieves patent claims data from Nexscope (Nexscope). Trigger when the user mentions patent claims, claim text, independent claims, dependent claims, claim count, claims tree, claims analysis, claim scope, claim language, viewing the claims section of a specific patent, patent claims, independent claims, dependent claims, claims text, Nexscope. Also trigger when the user requests patent claims information by patent ID or publication number, even without explicitly mentioning Nexscope or Nexscope.
npx skills add https://github.com/nexscope-ai/nexscope-ecommerce-skills --skill ecommerce.patent-claims
This skill guides you on how to retrieve and present patent claims data from the Nexscope (Nexscope) patent database, helping IP professionals, patent analysts, and R&D teams quickly access the claims section of any patent.
/zhihuiya/claimData (full parameters/responses/error codes in references/api.md)python scripts/patent_claims.py '<JSON params>' [--inline]Output strategy (script default behavior):
<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)total/costToken, length of the largest list field + first 3 samples)--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.
If you encounter authentication or credit issues:
NEXSCOPE_API_KEY environment variable is not set.NEXSCOPE_API_KEY environment variable with a valid API key.Patent claims define the legal scope of protection granted by a patent. They are the most critical part of a patent document for infringement analysis, freedom-to-operate assessments, and prior art comparisons. This tool retrieves the full set of claims for a single patent by its patent ID or publication number.
Family substitution: When a patent's claims are unavailable in the database, you can optionally request that claims from a related family member patent be returned instead. This is controlled by the replaceByRelated parameter.
| Field | API Name | Description | Example |
|-------|----------|-------------|---------|
| Patent ID | patentId | Internal Nexscope patent identifier | 98a1b2c3-... |
| Publication Number | pn | Publication or grant number of the patent | CN115000000A |
| Related PN | pnRelated | Publication number of the family member used as substitute (only present when family substitution occurred) | US20230001234A1 |
| Claims | claims | Array of claim objects containing the claim text and metadata | [...] |
| Claim Count | claimCount | Total number of claims in the patent | 15 |
You must provide at least one of the following two parameters. If both are provided, patentId takes priority.
| Parameter | Description | Format |
|-----------|-------------|--------|
| patentId | Single patent ID only. Do NOT pass comma-separated multiple IDs | Single string |
| patentNumber | Single publication/announcement number only. Do NOT pass comma-separated multiple numbers | Single string |
| Parameter | Description | Values |
|-----------|-------------|--------|
| replaceByRelated | Whether to substitute with a family member's claims when the target patent's claims are unavailable | 1 = yes, 0 = no (default) |
CN115000000A, US11234567B2). This is the most common scenario.> Skill single-patent policy: This endpoint consumes credits. To query multiple patents, obtain explicit user consent and make separate calls for each. This Skill sends one patent per call to control credits; the gateway accepts up to 100 English comma-separated identifiers.
1. Single patent by publication number
{"patentNumber": "CN115000000A"}
3. Single patent by patent ID
{"patentId": "98a1b2c3-xxxx-xxxx-xxxx-xxxxxxxxxxxx"}
4. With family substitution enabled
{"patentNumber": "CN115000000A", "replaceByRelated": "1"}
pnRelated is present in a result, explicitly inform the user that the claims shown are from a family member patent and provide the family member's publication number.patentId or patentNumber must be provided; omitting both will result in an error.replaceByRelated = 1 to attempt family member substitution when claims are missing.claims array may vary in structure depending on the patent office and data source.Applicable -- Patent claims retrieval and analysis:
| User Says | Scenario |
|-----------|----------|
| "Show me the claims of patent XX" | Single patent claims lookup |
| "How many claims does patent XX have" | Claim count query |
| "What are the independent claims of XX" | Claims retrieval + display |
| "The claims are not available, try a family member" | Family substitution query |
| "Patent claim scope", "claim language" | Claims retrieval |
Not applicable -- Needs beyond patent claims data:
Take nexscope-ai/ecommerce.patent-claims from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.