This skill guides you on how to retrieve fulltext images (drawings, figures, diagrams) from patent documents using the Zhihuiya patent data service, helping users access and analyze visual content within patents.
Core Concepts
Patent fulltext images are the figures, drawings, and diagrams embedded in patent documents. They are essential for understanding the technical details of an invention. This tool queries the Zhihuiya patent database and returns image metadata including download paths and image types for a given patent.
Lookup methods: You can look up images by either patent ID (an internal identifier) or publication number (the publicly visible patent number such as US20230012345A1 or CN115000000A). At least one of these must be provided.
Parameter Guide
| Parameter | API Name | Required | Description | Example |
|---|---|---|---|---|
| Patent ID | patentId | No* | Internal patent identifier | 8a7b6c5d-... |
| Publication Number | patentNumber | No* | Public patent publication/grant number | US20230012345A1 |
| Limit | limit | No | Maximum number of images to return (max 100, default 100) | 50 |
| Offset | offset | No | Pagination offset for image results | 0 |
*At least one of
patentIdorpatentNumbermust be provided.
Response Fields
| Field | Description |
|---|---|
| total | Total number of image records available |
| data | Array of image entries |
| data[].patentId | Patent identifier |
| data[].pn | Publication/grant number |
| data[].fulltextImagePath | URL path to download the image |
| data[].imageType | Type/category of the image |
| columns | Column rendering metadata |
| costToken | Token cost of the request |
| type | Rendering style hint |
How to invoke
- API endpoint：
POST /zhihuiya/fulltextImage(for complete parameters/responses/error codes, seereferences/api.md） - Python script：
python scripts/zhihuiya_fulltext_image.py '<JSON 参数>' [--inline] - Cost constraints: This tool consumes computing power; within the same session, the same parameter combination is by default invoked only once, and the script has a 24h local cache. On failure/empty results, do not automatically switch keywords, turn pages, or change postal codes to probe repeatedly; if further retrieval is needed, first explain to the user that it will incur additional consumption.
Output strategy (default script behavior)：
- Alwayswrite the complete response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-zhihuiya-fulltext-image-<timestamp>.json（<cwd>is the working directory when the script runs, which in Claude Code is the current project directory;<session>is taken from the environment variableSESSION_ID, aggregated automatically according to the user's task;writing to /tmp is prohibited, and an error is reported if the current directory is not writable) - Response body ≤ 8 KB: after saving to disk, print the complete JSON to stdout
- Response body > 8 KB: after saving to disk, stdout outputs only a summary (top-level fields, common counts such as
total/costToken, the length of the largest list field + the first 3 samples) - Add
--inlineto force full printing to stdout (also saved to disk)
Data reading recommendations: First look at the summary to judge whether it is sufficient; when specific fields are needed, prefer jqorConvertFrom-Json to extract on demand from the saved json file, avoiding putting the entire JSON into the context.
Resolve authentication and computing power issues
When the following abnormal situations occur, use references/onboarding.md to guide resolution:
Abnormal situations
- API Key not configured: The environment variable is not configured
LINKFOX_AGENT_API_KEY, andLINKFOXAGENT_API_KEY。 - Response 401 or 402 status code
- Response indicates insufficient computing power or balance: The message contains "insufficient computing power balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/plan expired/recharge required/please recharge", or content with a similar meaning.
Usage Examples
1. Get all images for a patent by publication number
Retrieve fulltext images for patent US20230012345A1.
Parameters: {"patentNumber": "US20230012345A1"}
2. Get images for a patent by patent ID
Fetch the drawings for patent ID abc123def456.
Parameters: {"patentId": "abc123def456"}
3. Paginated retrieval of images
Get the first 20 images for patent CN115000000A.
Parameters: {"patentNumber": "CN115000000A", "limit": "20", "offset": "0"}
4. Get the next page of images
Get images 21-40 for patent CN115000000A.
Parameters: {"patentNumber": "CN115000000A", "limit": "20", "offset": "20"}
Display Rules
- Present data clearly: Show image results in a structured table with image type, download path, and patent number
- Image links: Always present
fulltextImagePathvalues as clickable links so users can view or download images directly - Pagination notice: When
totalexceeds the number of returned results, inform the user that more images are available and offer to fetch the next page - Error handling: When a query fails, explain the reason and suggest verifying the patent ID or publication number
- No fabrication: Never invent patent IDs, publication numbers, or image URLs -- only display data returned by the API
- Total count: Always mention the total number of images available for the patent
Important Limitations
- Image limit: Each request returns a maximum of 100 images
- Identifier required: At least one of
patentIdorpatentNumbermust be supplied - All parameters are strings: Even numeric values like
limitandoffsetmust be passed as strings
User Expression & Scenario Quick Reference
Applicable -- Requests involving patent visual content:
| User Says | Scenario |
|---|---|
| "Show me the drawings for patent XX" | Fulltext image retrieval |
| "Get the figures from this patent" | Fulltext image retrieval |
| "Download patent images for XX" | Fulltext image retrieval |
| "What diagrams does patent XX contain" | Fulltext image listing |
| "How many figures are in patent XX" | Image count query |
| "Show me the technical drawings" | Fulltext image retrieval |
Not applicable -- Needs beyond patent fulltext images:
- Patent text/abstract/claims search
- Patent family or citation analysis
- Patent legal status queries
- Patent assignee or inventor search
- General image search unrelated to patents
Computing power consumption rules
Consumes 81 computing power.
Users will pay fees due to computing power consumption. Please fully evaluate: when this skill needs to be invoked frequently, or when the user's expectation of computing power consumption is insufficient, be sure to remind the user and let the user decide whether to continue.
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
- The functionality or purpose described in this skill does not match actual behavior
- The skill's results do not match the user's intent
- The user expresses dissatisfaction or praise about this skill
- Anything you believe could be improved
Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.
For more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.