pravidhi-ddgs-internet-search
Internet 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.
More from pravidhi-net/skills
pravidhi-commit-protocol
A complete, opinionated development workflow skill for agents. Triggers when the user asks to implement a feature, fix a bug, or refactor code in a Git repo. Enforces hygiene, security, quality, and atomic commits.
5pravidhi-bug-review-pipeline
Run a structured, adversarial multi-agent bug review pipeline on a codebase. Use this skill whenever the user wants to find bugs, audit code quality, review a codebase for issues, or run any kind of bug-finding or code analysis workflow. Also trigger when the user asks to 'review my code for bugs', 'find all issues in this repo', 'audit this codebase', or any similar request. The pipeline uses three sequential phases: a Bug Finder that maximizes issue discovery, a Bug Adversary that challenges false positives, and an Arbiter that issues final verdicts — producing a clean, high-confidence bug report.
4pravidhi-yc-oss
Robust tool to fetch and analyze Y Combinator company data. Use this skill to find companies by batch, industry, or tag, and to identify trends or specific startups without guessing URLs or crashing memory.
3