pravidhi-ddgs-internet-search
About pravidhi-ddgs-internet-search
pravidhi-ddgs-internet-search is an agent skill for searching the web through the DuckDuckGo Search library. It provides a safe mode for timeouts and returns structured JSON errors for agents to handle.
Key features
- 01Search with DuckDuckGo Search
- 02Limit the number of results
- 03Use safe mode with added delay
- 04Return JSON on soft failures
Use cases
- 01Search the web for current topics
- 02Retry searches that encounter timeouts
- 03Handle search errors in an agent
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ pravidhi-net/ skills --skill pravidhi-ddgs-internet-searchAfter installing, type/pravidhi-ddgs-internet-searchin Claude Code to confirm it loaded.
Bundled filesreferences/CLI_OPTIONS.mdscripts/search.py
Details
From the project READMEInternet Search Skill (DDGS)
Developed and maintained by Pravidhi
This skill performs internet searches using the DuckDuckGo Search library. It is designed to be low-friction and context-safe for AI agents.
Prerequisite: Installation
This skill requires the duckduckgo-search library. Install it in your agent's active Python environment.
pip install duckduckgo-search
Usage
Standard Search: Execute the script using your active Python interpreter.
# Syntax: python scripts/search.py -q "QUERY" -m MAX_RESULTS
python scripts/search.py -q "AI funding 2026" -m 3
Safe Mode (Use if getting timeouts):
The script includes a --safe flag that adds extra delay (3s) and disables aggressive backends.
python scripts/search.py -q "latest linux kernel features" -m 5 --safe
Known Limitations & Troubleshooting
Warning: This skill relies on scraping DuckDuckGo. It is not an official API.
-
Rate Limiting / IP Blocking:
- Symptom:
429 Too Many RequestsorRatelimiterrors. - Cause: Cloud/Datacenter IPs (AWS, GCP) are often flagged by DuckDuckGo.
- Fix: Wait 60 seconds. Try the
--safeflag. If persistent, use a residential proxy or switch to an API-based skill.
- Symptom:
-
Soft Failures:
- The script is designed to "soft fail". Instead of crashing with a non-zero exit code, it will return a JSON object with
status: error. Agents should parse the JSON output to handle errors gracefully.
- The script is designed to "soft fail". Instead of crashing with a non-zero exit code, it will return a JSON object with
References
- CLI_OPTIONS.md - Script argument reference.