kagi-search
Web search using Kagi Search API. Use when you need to search the web for current information, facts, or references. Requires KAGI_API_KEY in the environment.
Best use case
kagi-search is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Web search using Kagi Search API. Use when you need to search the web for current information, facts, or references. Requires KAGI_API_KEY in the environment.
Teams using kagi-search should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/kagi-search/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How kagi-search Compares
| Feature / Agent | kagi-search | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Web search using Kagi Search API. Use when you need to search the web for current information, facts, or references. Requires KAGI_API_KEY in the environment.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
> **Note:** The Kagi Search API is currently in beta. To request API access, email support@kagi.com. You must be a Kagi subscriber to use the API. --- # Kagi Search CLI Web search using the Kagi Search API with a clean, readable output format. ## Quick Start ```bash export KAGI_API_KEY="your_api_key" kagi-search "your search query" # or run directly: python3 scripts/kagi-search.py "your search query" ``` ## Features - **Clean output** - Title, URL, snippet, and metadata for each result - **Pagination support** - Control result count and offset - **JSON mode** - Raw JSON output for scripting - **Related searches** - Shows related queries (can be hidden) - **API balance** - Displays remaining API quota - **Fast & lightweight** - Pure Python, no dependencies ## Options | Flag | Description | |------|-------------| | `query` | Search terms (required) | | `-n, --limit` | Number of results (default: 10) | | `-s, --offset` | Offset for pagination (default: 0) | | `--json` | Output raw JSON | | `--no-related` | Hide related searches | | `-h, --help` | Show help | ## Examples ```bash # Basic search kagi-search "python async await tutorial" # Limit results kagi-search "AI news" --limit 5 # Pagination kagi-search "recipes" --offset 10 --limit 5 # JSON for scripting kagi-search "github stars" --json | jq '.data[].url' # Hide related searches kagi-search "rust programming" --no-related ``` ## Setup **Environment:** ```bash export KAGI_API_KEY="your_api_key" # Add to ~/.bashrc or ~/.zshrc for persistence ``` **PATH access:** ```bash # Make executable and add to PATH chmod +x scripts/kagi-search.py cp scripts/kagi-search.py ~/.local/bin/kagi-search ``` ## Requirements - Python 3.7+ - `KAGI_API_KEY` environment variable - Internet connection ## Output Format ``` [Query: search terms] [Results: 5] [API Balance: $0.123] [Time: 45ms] ---------------------------------------- === Result Title === https://example.com Snippet text here... [2024-01-15] --- Related: related query 1, related query 2 ```
Related Skills
npm-search
Search npm packages. Use for finding Node.js/JavaScript packages, libraries, and tools.
moltresearch
Molt Research 🦞 - AI research collaboration platform. Verify you're not human, propose research, contribute analysis, peer review, earn bounties, and build collective intelligence. Use when doing research, collaborating on papers, or exploring what AI agents are studying together.
macos-spm-app-packaging
Scaffold, build, and package SwiftPM-based macOS apps without an Xcode project. Use when you need a from-scratch macOS app layout, SwiftPM targets/resources, a custom .app bundle assembly script, or signing/notarization/appcast steps outside Xcode.
local-rag-search
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of RAG-based web search with DuckDuckGo, Google, and multi-engine deep research capabilities.
grok-search
Search the web or X/Twitter using xAI Grok server-side tools (web_search, x_search) via the xAI Responses API. Use when you need tweets/threads/users from X, want Grok as an alternative to Brave, or you need structured JSON + citations.
google-search
Search the web using Google Custom Search Engine (PSE). Use this when you need live information, documentation, or to research topics and the built-in web_search is unavailable.
gemini-deep-research
Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis.
exa-web-search-free
Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API key needed.
deep-research
Deep Research Agent specializes in complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files by we-crafted.com/agents/deep-research
ddg-search
Perform web searches using DuckDuckGo. Use when web search is needed and no API key is available or Brave Search is not preferred.
competitive-intelligence-market-research
B2B SaaS competitive intelligence with 24 scenarios across Sales/HR/Fintech/Ops Tech
brave-search
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.