← Back to Skills Marketplace
urhd528

gsdata-search

by urhd528 · GitHub ↗ · v1.0.3
cross-platform ✓ Security Clean
323
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install gsdata-search
Description
Searches the projects-databus.gsdata.cn API for data using provided project ID, signature, keywords, and returns results as JSON with optional limit.
README (SKILL.md)

GS Data Search

Description

A skill that provides a simple interface to search data from projects-databus.gsdata.cn API.

Installation

This skill is automatically available when installed in the Claude Code plugins directory.

Usage

To use this skill, you need to provide the following parameters:

  • project_id: Your project ID
  • sign: Your API signature
  • keywords: Search keywords
  • posttime_start: Start time for post (format: 2026-03-01 00:00:00)
  • posttime_end: End time for post (format: 2026-03-01 23:59:59)
  • limit: Number of results to return (default: 10)

Example

from gsdata_search import search

result = search(
    project_id="your_project_id",
    sign="your_signature",
    keywords="your_search_keywords",
    posttime_start="2026-03-01 00:00:00",
    posttime_end="2026-03-01 23:59:59",
    limit=20
)

print(result)

API Reference

search(project_id, sign, keywords, posttime_start, posttime_end, limit=10)

Searches the GS Data API for data matching the keywords.

Parameters:

  • project_id (str): The project ID
  • sign (str): The API signature
  • keywords (str): Keywords to search for
  • posttime_start (str): Start time for post (format: 2026-03-01 00:00:00)
  • posttime_end (str): End time for post (format: 2026-03-01 23:59:59)
  • limit (int): Number of results to return (default: 10)

Returns:

  • list: The search results as a Python list of dictionaries, each containing only the following fields:
    • news_title: News title
    • news_uuid: News UUID
    • media_name: Media name
    • news_posttime: Posting time
    • news_emotion: News emotion (positive/negative/neutral)
    • news_url: News URL
    • news_digest: News digest

Response Structure:

[
    {
        "news_title": "News title",
        "news_uuid": "123456789",
        "media_name": "Media name",
        "news_posttime": "2026-03-01 10:30:00",
        "news_emotion": "positive",
        "news_url": "https://example.com/news/123",
        "news_digest": "News digest..."
    }
]

Notes

  • Make sure you have valid project_id and sign credentials
  • The API has a timeout of 30 seconds
  • Results are returned as JSON data
Usage Guidance
This skill appears to do what it says: it sends your provided project_id and sign to projects-databus.gsdata.cn and returns selected fields from the response. Before installing/using it: (1) review and trust the API operator because you must supply credentials; (2) be aware the code uses HTTP (not HTTPS) to send project_id/sign — this can expose secrets on the network; avoid using sensitive credentials over unencrypted networks or ask the provider for a TLS endpoint; (3) note the minor packaging inconsistency (package.json present for a Python package) — not malicious but worth a quick sanity check; (4) if you want stronger assurance, run the included Python file locally with non-production credentials and inspect traffic (or add TLS) before giving real credentials.
Capability Analysis
Type: OpenClaw Skill Name: gsdata-search Version: 1.0.3 The skill is designed to interact with the `projects-databus.gsdata.cn` API for data searching, as described in `SKILL.md`. The `src/__init__.py` code makes a legitimate HTTP POST request to the specified API endpoint, passing `project_id` and `sign` credentials along with search parameters. There is no evidence of data exfiltration to unauthorized endpoints, unauthorized file system access, persistence mechanisms, or prompt injection attempts in `SKILL.md`. The code's behavior is fully aligned with its stated purpose.
Capability Assessment
Purpose & Capability
The name, description, SKILL.md, and src/__init__.py all align: the module issues a POST to the stated GS Data API with the provided project_id, sign, and search parameters and returns filtered JSON results. Minor oddity: repository includes a package.json (npm-style) even though the implementation is Python and requirements.txt is present; this is a packaging inconsistency but not a functional mismatch.
Instruction Scope
SKILL.md only instructs how to call the search function and how to provide project_id and sign. It does not ask the agent to read other files, environment variables, or send data to endpoints outside the declared API. One operational risk: the code posts credentials over HTTP (API URL uses http:// and port 7777), which can expose secrets in transit if the network is not trusted.
Install Mechanism
There is no install spec (instruction-only skill with included Python source). Dependencies are ordinary (requests in requirements.txt). The presence of package.json/plugin.json is redundant and slightly inconsistent for a Python skill but not an active install-time risk (no arbitrary download or extract steps).
Credentials
The skill does not request environment variables or other credentials up front; it expects project_id and sign to be provided when calling the function or CLI. This is proportionate. Note: because the API call uses plain HTTP, those provided credentials would be transmitted in cleartext over the network.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skill configurations. It only performs on-demand network requests to the stated API endpoint.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install gsdata-search
  3. After installation, invoke the skill by name or use /gsdata-search
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Updated API reference: the search function now returns a list of dictionaries with specific news-related fields instead of a generic dictionary. - Added a detailed response structure example for the search results. - Clarified which fields are included in each result item (news_title, news_uuid, media_name, news_posttime, news_emotion, news_url, news_digest). - General documentation improvements for API usage.
v1.0.2
- Added support for filtering search results by post time, with new parameters `posttime_start` and `posttime_end`. - Updated usage instructions and example to include the new post time parameters. - Revised API reference documentation to reflect the updated search function signature.
v1.0.1
- No changes detected—this version is functionally identical to the previous release.
v1.0.0
- Initial release of GS Data Search skill. - Provides a simple interface to search data via the projects-databus.gsdata.cn API. - Users can specify project ID, API signature, search keywords, and result limit. - Returns search results as a Python dictionary (JSON format). - Includes example usage and installation instructions.
Metadata
Slug gsdata-search
Version 1.0.3
License
All-time Installs 0
Active Installs 0
Total Versions 4
Frequently Asked Questions

What is gsdata-search?

Searches the projects-databus.gsdata.cn API for data using provided project ID, signature, keywords, and returns results as JSON with optional limit. It is an AI Agent Skill for Claude Code / OpenClaw, with 323 downloads so far.

How do I install gsdata-search?

Run "/install gsdata-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is gsdata-search free?

Yes, gsdata-search is completely free (open-source). You can download, install and use it at no cost.

Which platforms does gsdata-search support?

gsdata-search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created gsdata-search?

It is built and maintained by urhd528 (@urhd528); the current version is v1.0.3.

💬 Comments