This skill guides you on how to query patent bibliography (bibliographic) data from the Zhihuiya patent database, helping users retrieve detailed metadata for specific patents.
Core Concepts
Patent bibliography data (also called bibliographic data) is the structured metadata associated with a patent document. It includes the patent title, applicants, inventors, classification codes, priority claims, cited references, abstracts, and more. This tool allows querying by patent ID or publication number, returning comprehensive bibliographic records for up to 100 patents per request.
Patent types: The patentType field indicates the type of patent document:
APPLICATION-- Invention application (published but not yet granted)PATENT-- Granted invention patentUTILITY-- Utility modelDESIGN-- Design patent
Data Fields
| Field | API Name | Description |
|---|---|---|
| Patent ID | patentId | Internal patent identifier |
| Publication Number | pn | Publication/announcement number |
| Invention Title | inventionTitle | Patent title with language info |
| Abstracts | abstracts | Patent abstract text |
| Patent Type | patentType | APPLICATION, PATENT, UTILITY, or DESIGN |
| Applicants | applicants | Original applicant(s) |
| Assignees | assignees | Current patent holder(s) / assignee(s) |
| Inventors | inventors | Inventor(s) listed on the patent |
| Agents | agents | Patent attorney / agent(s) |
| Agency | agency | Filing agency / patent firm |
| Examiners | examiners | Patent examiner(s) |
| Priority Claims | priorityClaims | Priority right declarations |
| Application Reference | applicationReference | Application filing data |
| Publication Reference | publicationReference | Publication data |
| Dates of Public Availability | datesOfPublicAvailability | Public availability dates |
| IPC Classification | classificationIpcr | International Patent Classification |
| CPC Classification | classificationCpc | Cooperative Patent Classification |
| UPC Classification | classificationUpc | US Patent Classification |
| LOC Classification | classificationLoc | Locarno Classification (designs) |
| FI Classification | classificationFi | FI classification codes (Japan) |
| F-term Classification | classificationFterm | F-term codes (Japan) |
| GBC Classification | classificationGbc | GBC classification |
| Cited Patents | referenceCitedPatents | Patent documents cited as references |
| Cited Non-Patent Literature | referenceCitedOthers | Non-patent literature cited |
| Related Documents | relatedDocuments | Divisional / continuation application info |
| PCT Filing Data | pctOrRegionalFilingData | PCT or regional phase filing data |
| PCT Publishing Data | pctOrRegionalPublishingData | PCT or regional phase publication data |
| Estimated Expiry Date | exdt | Estimated patent expiration date (Zhihuiya) |
How to call
- API endpoint：
POST /zhihuiya/bibliography(for full parameters/responses/error codes seereferences/api.md） - Python script：
python scripts/zhihuiya_bibliography.py '<JSON 参数>' [--inline] - Cost constraints: This tool consumes compute; 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 repeatedly; if you need to continue searching, first explain to the user that additional consumption will be incurred.
Output strategy (default script behavior)：
- Alwayswrite the full response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-zhihuiya-bibliography-<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, 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 saving to disk, print the full 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 suggestions: First look at the summary to determine whether it is sufficient; when specific fields are needed, prefer to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into the context.
Resolve authentication and compute 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 compute or balance: The message contains "insufficient compute balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge", or similar meaning.
Parameter Guide
The tool accepts two parameters. At least one must be provided; if both are supplied, patentId takes priority.
| Parameter | When to Use | Format |
|---|---|---|
patentId |
When the user provides an internal Zhihuiya patent ID | Comma-separated string, up to 100 IDs |
patentNumber |
When the user provides a publication/announcement number | Comma-separated string, up to 100 numbers |
Tips for Identifying Input Type
- If the user provides something like
US10123456B2,CN112345678A,EP3456789B1, orWO2023123456A1, treat it as a publication number and usepatentNumber. - If the user provides a purely numeric or opaque identifier that does not match standard publication number patterns, treat it as a patent ID and use
patentId. - When the user provides multiple patents, join them with commas (no spaces around commas).
Usage Examples
1. Look up a single patent by publication number
User: "Show me the bibliography for US10123456B2"
Action: Call with patentNumber = "US10123456B2"
2. Look up multiple patents by publication number
User: "Get bibliographic data for CN112345678A, EP3456789B1, and US20210012345A1"
Action: Call with patentNumber = "CN112345678A,EP3456789B1,US20210012345A1"
3. Look up a patent by internal ID
User: "Query bibliography for patent ID 8fa3b2c1-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
Action: Call with patentId = "8fa3b2c1-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
4. Batch lookup of patents
User: "I have a list of 20 publication numbers, look up all their inventors and assignees"
Action: Call with patentNumber = "<comma-separated list>"
Then extract and present inventors and assignees from the results.
Display Rules
- Present data clearly: Show query results in well-structured tables or organized sections. For each patent, highlight the most commonly needed fields: title, applicants/assignees, inventors, filing/publication dates, classification codes, and abstract.
- Respect the query scope: Only display the fields the user asked about. If they asked for "inventors", do not dump the entire bibliography unless requested.
- Patent type labels: Translate
patentTypecodes into human-readable labels (APPLICATION = Invention Application, PATENT = Granted Invention, UTILITY = Utility Model, DESIGN = Design Patent). - Multi-patent results: When results contain multiple patents, use a summary table first, then expand details per patent if the user wants more.
- Error handling: When a query returns an error or empty results, explain clearly and suggest the user verify their patent ID or publication number.
- No subjective analysis: Present factual bibliographic data without speculative legal or commercial interpretations.
User Expression & Scenario Quick Reference
Applicable -- Patent bibliography / metadata lookups:
| User Says | Scenario |
|---|---|
| "Look up patent info for XX" | Single patent bibliography |
| "Who are the inventors of patent XX" | Inventor lookup |
| "Who owns patent XX", "current assignee" | Assignee / applicant query |
| "What IPC/CPC class is patent XX" | Classification lookup |
| "Show me the abstract of patent XX" | Abstract retrieval |
| "What patents does XX cite" | Citation analysis |
| "When does patent XX expire" | Expiry date query |
| "Get bibliography for these patents: A, B, C" | Batch lookup |
| "Patent details", "patent metadata" | General bibliography |
Not applicable -- Needs beyond patent bibliography:
- Full-text patent search by keyword or semantic query
- Patent landscape / analytics reports
- Patent valuation or legal status tracking
- Freedom-to-operate or infringement analysis
- Patent family tree exploration (unless specific publication numbers are given)
Boundary judgment: When users say "find patents about X" or "search for patents in field Y", that is a patent search task, not a bibliography lookup. This skill only applies when the user already has a patent ID or publication number and wants to retrieve its metadata.
Compute consumption rules
Billed according to dynamic rules: compute consumption = 81 × number of returned data entries. Each entry is 1 patent bibliographic result
Important: The service of this skill is dynamically calculated by a multiplier and may consume a large amount of compute 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:
- 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.