Skills qryma-search
🔍

qryma-search

Safe 🔑 Env variables🌐 Network access

Search the Web with Multiple Output Formats

Get fast, LLM-optimized web search results with Qryma API. This skill provides structured search responses in Markdown, JSON, or Brave-style formats for seamless integration into your AI workflows.

Supports: Claude Codex Code(CC)
🥈 78 Silver
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Test it

Using "qryma-search". Search for 'Python async await tutorial' with 3 results in Markdown format

Expected outcome:

1. Async IO in Python: A Complete Walkthrough
https://docs.python.org/3/library/asyncio.html
- Comprehensive guide to asyncio library with examples

2. Understanding Async/Await in Python
https://realpython.com/async-io-python/
- Detailed tutorial covering coroutines, event loops, and practical examples

3. Python Asyncio Tutorial
https://realpython.com/python-concurrency/
- Explains async programming patterns with real-world use cases

Using "qryma-search". Search for 'machine learning trends 2024' in JSON format

Expected outcome:

Query results returned as structured JSON with title, url, and content fields for each result, enabling programmatic processing and integration into workflows.

Security Audit

Safe
v4 • 4/2/2026

Static analysis detected 136 potential security issues across 12 files. After evaluation, all findings are false positives related to legitimate skill functionality: environment variable access for API key authentication, network requests to official Qryma API endpoints, shell commands in documentation examples, and configuration file reading. No evidence of malicious intent, credential exfiltration, or data theft. The skill follows standard patterns for API-based search tools with proper error handling.

12
Files scanned
770
Lines analyzed
3
findings
4
Total audits
Low Risk Issues (1)
Shell Commands in Documentation
Static scanner detected shell backtick patterns in README.md and SKILL.md files. These are documentation code examples within markdown code blocks, not executable code. Lines 10-72 in README.md and lines 17-67 in SKILL.md contain example commands for users to run manually.
Audited by: claude View Audit History →

Quality Score

59
Architecture
100
Maintainability
87
Content
34
Community
100
Security
100
Spec Compliance

What You Can Build

Research Assistant

Find current information, articles, and resources for research topics. Use when you need to verify facts, gather recent data, or find authoritative sources on any subject.

Developer Documentation Search

Quickly find technical documentation, tutorials, and code examples. Search for specific programming problems, libraries, or frameworks to get accurate technical results.

Content Verification

Fact-check information and find corroborating sources. Use to verify claims, find multiple perspectives on topics, or gather supporting evidence for content creation.

Try These Prompts

Basic Web Search
Search the web for "[your query here]" and return the results in Markdown format with 5 results.
Technical Documentation Search
Search for "[programming language or library] documentation [specific topic]" with 10 results in JSON format. Include both fulltext and snippet modes if possible.
Multi-perspective Research
Search the web for "[topic]" with 10 results, then search for "[topic] controversy debate" with 5 results. Return both in Markdown format.
Deep Dive with Pagination
Search for "[detailed research topic]" with 5 results starting at offset 0. If results are relevant, continue searching with start offset 5 to get more results.

Best Practices

  • Always provide specific, well-focused search queries rather than broad terms to get the most relevant results
  • Start with the default 5 results and increase max_results only if needed for comprehensive research
  • Use Markdown format for human-readable results, JSON format for data processing, and Brave format for compatibility with existing tools
  • Set the QRYMA_API_KEY as an environment variable for security and convenience instead of passing it with each command

Avoid

  • Don't use very general queries like 'python' or 'javascript' - instead be specific like 'python async await best practices'
  • Don't request excessive max_results (above 20) unless truly necessary, as this may slow down responses and hit rate limits
  • Don't ignore the language parameter - setting it correctly improves result relevance for non-English searches
  • Don't hardcode API keys in scripts or configuration files committed to version control

Frequently Asked Questions

How do I get a QRYMA_API_KEY?
Visit qryma.com to sign up for a free API key. The key will start with 'ak-' and can be set as an environment variable QRYMA_API_KEY or passed via the --api-key parameter.
What output formats are available?
Three formats are supported: 'md' for human-readable Markdown, 'raw' for structured JSON data, and 'brave' for Brave search-style JSON output with title/url/content fields.
What is the difference between fulltext and snippet modes?
Fulltext mode provides detailed search results with longer content excerpts, while snippet mode returns concise results with brief descriptions. Use fulltext for research and snippet for quick overviews.
Can I use this skill without an API key?
No, a valid QRYMA_API_KEY is required for all search operations. The API key authenticates your requests to the Qryma search service.
How do I search in languages other than English?
Use the --lang parameter with your language code (e.g., 'en' for English, 'es' for Spanish, 'zh' for Chinese). The API will return results optimized for that language.
What does the start offset parameter do?
The start parameter enables pagination. Setting start=0 returns the first page of results, start=5 returns the second page (skipping first 5), and so on. Use this to navigate through many results.

Developer Details

Author

qryma-ai

License

MIT

Ref

main