grok-search
Real-time web research/search with sources (outputs JSON).
Best use case
grok-search is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Real-time web research/search with sources (outputs JSON).
Teams using grok-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.
How grok-search Compares
| Feature / Agent | grok-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?
Real-time web research/search with sources (outputs JSON).
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
## When to use (aggressive)
- Default to using this skill before answering anything that might be outdated, ambiguous, or requires external confirmation (APIs, versions, errors, docs, releases).
- If you feel even slightly unsure, search first, then answer with evidence.
## Quick start
### Configure (recommended)
Run once to write config:
```powershell
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.codex\skills\grok-search\configure.ps1"
```
Default config path (recommended): `C:\Users\<you>\.codex\skills\grok-search\config.json` (override with `--config` or `GROK_CONFIG_PATH`).
Write to user-level config instead (optional):
```powershell
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.codex\skills\grok-search\configure.ps1" -Global
```
### Configure (env vars)
If you prefer env vars:
```powershell
$env:GROK_BASE_URL="https://your-grok-endpoint.example"
$env:GROK_API_KEY="YOUR_API_KEY"
$env:GROK_MODEL="grok-2-latest"
```
### Run
```bash
python scripts/grok_search.py --query "What changed in X recently?"
```
## Output
Prints JSON to stdout:
- `content`: the synthesized answer
- `sources`: best-effort list of URLs (and optional titles/snippets)
- `raw`: raw assistant content (if parsing failed)
## Notes
- Endpoint: `POST {GROK_BASE_URL}/v1/chat/completions` (also supports `{GROK_BASE_URL}/chat/completions` if you set `GROK_BASE_URL` ending with `/v1`).
- You can override model via `--model` or `GROK_MODEL`.
- If your 2api requires custom flags to enable web search, pass them via `--extra-body-json` / `GROK_EXTRA_BODY_JSON`.Related Skills
search-first
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Systematizes the "search for existing solutions before implementing" approach. Use when starting new features or adding functionality.
market-research
Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
exa-search
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
deep-research
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
hig-components-search
Apple HIG guidance for navigation-related components including search fields, page controls, and path controls.
exa-search
Semantic search, similar content discovery, and structured research using Exa API. Use when you need semantic/embeddings-based search, finding similar content, or searching by category (company, people, research papers, etc.).
deep-research
Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.
context7-auto-research
Automatically fetch latest library/framework documentation for Claude Code via Context7 API. Use when you need up-to-date documentation for libraries and frameworks or asking about React, Next.js, Prisma, or any other popular library.
azure-search-documents-ts
Build search applications with vector, hybrid, and semantic search capabilities.
azure-search-documents-py
Azure AI Search SDK for Python. Use for vector search, hybrid search, semantic ranking, indexing, and skillsets.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search.