SuperAPI AI Directory

linkfox-zhihuiya-abstract-image

Design & creation

View repository

Updated 10-16 00:00

About this skill

Zhihuiya Patent Abstract Image

This skill guides you on how to retrieve abstract images (drawings) from the Zhihuiya patent database, helping users quickly obtain the illustrative figures associated with specific patents.

Core Concepts

Abstract images (abstract drawings) are the representative figures attached to a patent document's abstract section. They provide a quick visual overview of the invention. This tool queries the Zhihuiya patent database and returns download paths for these images.

Lookup logic: You must provide at least one of two identifiers -- a patent ID or a publication number. If both are provided, patent ID takes priority. You can query up to 100 patents in a single request by separating values with commas.

Parameter Guide

Parameter API Name Required Description Example
Patent ID patentId Conditionally (one of the two must be provided) Internal patent identifier; multiple values separated by commas, max 100 5e6f7a8b9c
Publication Number patentNumber Conditionally (one of the two must be provided) Patent publication/announcement number; multiple values separated by commas, max 100 CN115059423A, US11234567B2
  • At least one of patentId or patentNumber must be supplied.
  • If both are supplied, patentId takes precedence.
  • Multiple values are separated by commas (English commas), with an upper limit of 100.

Response Fields

Field API Name Description
Patent ID patentId The internal patent identifier
Publication Number pn The publication/announcement number
Abstract Drawing Path abstractDrawingPath URL path to the abstract image file
Total total Total number of records returned
Cost Token costToken Tokens consumed by the query

How to Call

  • API Endpoint:POST /zhihuiya/abstractImage(For full parameters/responses/error codes, see references/api.md)
  • Python Script:python scripts/zhihuiya_abstract_image.py '<JSON 参数>' [--inline]
  • Cost Constraints: This tool consumes computing power; by default, the same parameter combination in the same session is called only once, and the script has a 24h local cache. On failure/empty results, do not automatically try different keywords, paginate, or change the zip code to probe continuously; if you need to continue searching, first explain to the user that additional consumption will be incurred.

Output Strategy (Script Default Behavior):

  • Alwayswrite the complete response to <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-zhihuiya-abstract-image-<timestamp>.json(<cwd> is the working directory when the script is executed, which in Claude Code is the current project directory;<session> is taken from the environment variable SESSION_ID, automatically aggregated 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 writing to disk, print the complete JSON to stdout
  • Response body > 8 KB: after writing 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 --inline to force full printing to stdout (also written to disk)

Data Reading Recommendations: First look at the summary to determine whether it is sufficient; when specific fields are needed, prefer using jqorConvertFrom-Json to extract on demand from the saved json file, avoiding putting the entire JSON into the context.

Resolving 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, and LINKFOXAGENT_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/package expired/recharge required/please recharge", or content with a similar meaning.

Usage Examples

1. Single patent lookup by publication number

Retrieve the abstract image for patent CN115059423A.

2. Multiple patents lookup by publication number

Get abstract drawings for patents US11234567B2, EP3456789A1, and CN115059423A.

3. Lookup by patent ID

Fetch the abstract image for patent ID 5e6f7a8b9c.

4. Batch lookup with mixed identifiers

I have the following patent IDs: abc123, def456. Please get their abstract images.

Display Rules

  1. Show the image: When the response includes an abstractDrawingPath, display the image directly using Markdown image syntax so the user can see the drawing inline.
  2. Patent identification: Always show the publication number (pn) alongside each image so the user knows which patent each drawing belongs to.
  3. Missing images: If a patent has no abstract drawing (empty abstractDrawingPath), explicitly inform the user that no abstract image is available for that patent.
  4. Batch results: When multiple patents are queried, present results in a clear, organized list or table format.
  5. Error handling: When a query fails, explain the reason based on the response and suggest the user verify their patent IDs or publication numbers.
  6. No subjective analysis: Present the retrieved images and metadata without adding subjective patent analysis or legal interpretations.

User Expression & Scenario Quick Reference

Applicable -- Patent abstract image retrieval:

User Says Scenario
"Show me the abstract image for patent XX" Single patent image lookup
"Get the drawings for these patents" Batch patent image lookup
"What does the patent figure look like" Abstract drawing retrieval
"Retrieve patent illustrations for XX" Image download path retrieval
"I need the abstract drawing for publication number XX" Lookup by publication number

Not applicable -- Needs beyond abstract image retrieval:

  • Full patent text or claims analysis
  • Patent search by keyword or classification
  • Patent legal status or family information
  • Patent citation or prior art analysis
  • Patent valuation or infringement analysis

Computing Power Consumption Rules

Billed according to dynamic rules: computing power consumed = 81 × number of returned data entries. Each entry is 1 patent abstract image result

Important: The service of this skill is dynamically calculated by a multiplier and may consume a large amount of computing power at once. The user must be reminded, and the user decides whether to continue.

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

  1. The functionality or purpose described in this skill does not match actual behavior
  2. The skill's results do not match the user's intent
  3. The user expresses dissatisfaction or praise about this skill
  4. 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.