← Back to Skills Marketplace
274
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install pure-search
Description
A lightweight, API-key-free web search skill based on DuckDuckGo and Trafilatura. Returns highly relevant URLs and clean markdown content.
Usage Guidance
This skill appears to do what it says: scrape DuckDuckGo HTML for result links and run trafilatura to extract page bodies as markdown. Before installing, consider: (1) run it in a sandboxed environment since it fetches arbitrary web pages you query; fetched pages can contain malicious or sensitive content; (2) audit or pin dependency versions (trafilatura) before installing via pip; (3) be aware the SKILL.md suggests installing 'duckduckgo-search' but the script doesn't use that package — the doc mismatch is not malicious but you may omit that install; (4) if you will run this unattended or let an agent invoke it autonomously, limit queries to safe domains and monitor network usage. If you need higher assurance, review the script (scripts/search.py) yourself or run it with network restrictions.
Capability Analysis
Type: OpenClaw Skill
Name: pure-search
Version: 1.0.0
The 'pure-search' skill is a legitimate utility for performing web searches and extracting clean markdown content. The primary script, `scripts/search.py`, implements a custom HTML parser to scrape DuckDuckGo's non-JS interface and uses the well-known `trafilatura` library for content extraction. The code and instructions in `SKILL.md` align with the stated purpose, and there are no indicators of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
The name/description say it uses DuckDuckGo + trafilatura and returns cleaned markdown — the included script implements exactly that by requesting html.duckduckgo.com and using trafilatura.extract. Minor mismatch: SKILL.md suggests installing the 'duckduckgo-search' package, but the script scrapes DuckDuckGo HTML directly rather than importing that library; this appears to be a benign inconsistency (documentation vs implementation), not a capability mismatch.
Instruction Scope
SKILL.md is explicit: install trafilatura and use the script. The runtime instructions and script perform network requests to DuckDuckGo and to the target webpages and return the extracted markdown. This is within the stated purpose, but note that the skill will fetch arbitrary third-party pages and return their content (expected for a search/ extraction tool) — users should be aware it may download content from sites they query (including potentially private or malicious pages if given such URLs).
Install Mechanism
No install spec is embedded in the registry (instruction-only), so nothing is written to disk by the platform. SKILL.md asks the user to pip install dependencies (standard practice). The pip recommendation includes 'duckduckgo-search' even though the script does not use that package — a minor documentation mismatch but not an install-time risk from the registry itself.
Credentials
The skill requests no environment variables, no credentials, and no config paths. The operations (HTTP GET to DuckDuckGo and to result URLs) do not require secrets; the requested privileges are proportional to the described functionality.
Persistence & Privilege
The skill is not configured as always: true and does not request persistent or cross-skill configuration. It can be invoked by the agent normally. Nothing here indicates elevated platform privileges or unexpected persistence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pure-search - After installation, invoke the skill by name or use
/pure-search - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Pure Search:
- Lightweight web search tool using DuckDuckGo and Trafilatura.
- No API keys required; zero configuration needed.
- Returns highly relevant URLs with main content extracted as clean Markdown.
- Outputs structured JSON with titles, URLs, and markdown bodies.
- Simple setup and usage with a single Python script.
Metadata
Frequently Asked Questions
What is Pure Search?
A lightweight, API-key-free web search skill based on DuckDuckGo and Trafilatura. Returns highly relevant URLs and clean markdown content. It is an AI Agent Skill for Claude Code / OpenClaw, with 274 downloads so far.
How do I install Pure Search?
Run "/install pure-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pure Search free?
Yes, Pure Search is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Pure Search support?
Pure Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pure Search?
It is built and maintained by cyecho-io (@cyecho-io); the current version is v1.0.0.
More Skills