Ecommerce.Patent References logo

Ecommerce.Patent References

Organization
nexscope-ai
ecommerce.patent-references

Query patent forward citation details from the Nexscope patent database. Triggered when users ask about patent citations, cited patents, cited references, patent references, forward citations, prior art citations, or want to see which patents and non-patent literature specific patents cited during the application process, patent cited references, forward citations, patent references, citation analysis, or Nexscope. When users provide a patent ID or publication number and need citation information, even if they do not explicitly say "forward citation," any request about which references a patent cited applies.

Overview

Publishernexscope-ai
Repositorynexscope-ecommerce-skills
Skill nameecommerce.patent-references
Stars
104
Forks
14
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by nexscope-ai on GitHub. Read the source before you install it.

Installation

Install the Ecommerce.Patent References AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/nexscope-ai/nexscope-ecommerce-skills/tree/main/ecommerce-patent-references
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/nexscope-ai/nexscope-ecommerce-skills.git /tmp/nexscope-ecommerce-skills
mkdir -p .claude/skills
cp -r /tmp/nexscope-ecommerce-skills/ecommerce-patent-references .claude/skills/ecommerce.patent-references
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ecommerce.Patent References in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ecommerce.Patent References on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ecommerce.Patent References is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Nexscope Patent Forward Citation

This skill guides you on how to query patent forward citation data from the Nexscope patent database, helping users discover the patents and non-patent literature cited by specific patents during their application process.

Core Concepts

Forward citation refers to the patents and non-patent literature that a given patent has cited in its application documents. This is a fundamental aspect of patent analysis -- understanding what prior art a patent references helps assess its novelty, scope, and technological lineage.

  • Patent citations (citedPatents): Other patents referenced by the queried patent.
  • Non-patent literature citations (citedOthers): Academic papers, technical reports, and other non-patent documents referenced by the queried patent.

Parameter Guide

You must provide at least one of the following two parameters. If both are provided, patentId takes priority.

ParameterTypeRequiredDescription
patentIdstringConditionallyUp to 100 comma-separated patent IDs.
patentNumberstringConditionallySingle publication/announcement number only. Do NOT pass comma-separated multiple numbers.

Rules:

  1. At least one of patentId or patentNumber must be provided.
  2. If both are present, patentId is used preferentially.
  3. A request may contain up to 100 comma-separated patents. Confirm the intended batch before a multi-patent call.

Batch limit: patentId or patentNumber may contain up to 100 comma-separated values. Because the endpoint consumes significant credits, confirm the intended batch before submitting a multi-patent request.

Response Fields

FieldTypeDescription
totalintegerTotal number of records returned
dataarrayList of patent citation results
data[].patentIdstringPatent ID of the queried patent
data[].pnstringPublication/announcement number
data[].citedPatentsarrayList of cited patent documents
data[].citedOthersarrayList of cited non-patent literature
columnsarrayColumn definitions for rendering
costTokenintegerTokens consumed by the query
typestringRendering style hint

Invocation

  • API Endpoint: POST /zhihuiya/patentForwardCitation (full parameters/response/error codes in references/api.md)
  • Python Script: python scripts/patent_references.py '<JSON params>' [--inline]
  • Cost Constraints: This tool consumes credits. The same parameter combination defaults to a single call per session. The script includes a 24-hour local cache. Do not automatically retry after failure or empty results. Batch requests may contain up to 100 comma-separated patents; confirm the intended batch first.

Output Strategy (default script behavior):

  • Always write the full response to <cwd>/nexscope/<YYYY-MM-DD>/<session>/data/nexscope-zhihuiya-patent-forward-citation-<timestamp>.json (<cwd> is the working directory at script execution time, which in Claude Code is the current project directory; <session> is taken from the SESSION_ID environment variable, auto-grouped by user task; writing to /tmp is forbidden -- error if the current directory is not writable)
  • Response body <= 8 KB: print the full JSON to stdout after writing to disk
  • Response body > 8 KB: print only a summary to stdout after writing to disk (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)

Data Reading Tip: Check the summary first to determine if it is sufficient; when specific fields are needed, prefer using jq or ConvertFrom-Json to extract from the saved JSON file on demand to avoid loading the entire JSON into context.

Authentication

Set the NEXSCOPE_API_KEY environment variable. If credentials are missing or expire, visit https://www.nexscope.ai/help/skills-external-access?co-from=skillNS to top up credits.

Usage Examples

1. Query forward citations by publication number

Look up the forward citations for patent US10000000B2.

Parameters: {"patentNumber": "US10000000B2"}

2. Query forward citations by patent ID

Retrieve the cited references for patent ID 12345678.

Parameters: {"patentId": "12345678"}

3. Query forward citations using both identifiers

Look up citations for patent ID 12345678 (publication number US10000000B2).

Parameters: {"patentId": "12345678", "patentNumber": "US10000000B2"} (patentId takes priority)

Display Rules

  1. Present data clearly: Show citation results in well-structured tables, separating patent citations from non-patent literature citations.
  2. Summarize counts: Always state the total number of cited patents and cited non-patent literature items.
  3. No fabrication: Only display data returned by the API. Do not infer or fabricate citation details.
  4. Error handling: When a query fails, explain the reason based on the error response and suggest the user verify their patent ID or publication number.
  5. Per-patent results: Present each returned patent's citation data separately.
  6. Empty results: If a patent has no citations, explicitly inform the user rather than showing an empty table.

User Expression & Scenario Quick Reference

Applicable -- Patent citation queries:

User SaysScenario
"What patents does XX cite"Forward citation lookup
"Show me the references for patent XX"Citation detail retrieval
"What prior art is cited by XX"Prior art reference query
"List the cited literature for XX"Non-patent literature lookup
"Citation analysis for patent XX"Combined patent + literature citation
"What documents does patent XX reference"General citation query

Not applicable -- Needs beyond forward citation data:

  • Backward/reverse citations (who cites this patent)
  • Patent validity or legal status
  • Patent family analysis
  • Patent full-text search
  • Patent classification or landscape analysis

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ecommerce.Patent References AI skill do?

Query patent forward citation details from the Nexscope patent database. Triggered when users ask about patent citations, cited patents, cited references, patent references, forward citations, prior art citations, or want to see which patents and non-patent literature specific patents cited during the application process, patent cited references, forward citations, patent references, citation analysis, or Nexscope. When users provide a patent ID or publication number and need citation information, even if they do not explicitly say "forward citation," any request about which references a pa...

Why use Ecommerce.Patent References on TypingMind?

Because you install it once and use it with any model. Ecommerce.Patent References is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ecommerce.Patent References in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nexscope-ai/nexscope-ecommerce-skills/tree/main/ecommerce-patent-references. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ecommerce.Patent References?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ecommerce.Patent References?

As many as you like. As long as a model supports skills, you can use Ecommerce.Patent References with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ecommerce.Patent References AI skill free?

It is published on GitHub by nexscope-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇