grok-search

Real-time web research/search with sources (outputs JSON).

148 stars

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 / Agentgrok-searchStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/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- Default to using this skill before answering anything that might be outdated, ambiguous, or requires external confirmation (APIs, versions, errors, docs, releases).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

144923
from affaan-m/everything-claude-code

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.

DevelopmentClaude

market-research

144923
from affaan-m/everything-claude-code

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.

Business Intelligence & AnalyticsClaude

exa-search

144923
from affaan-m/everything-claude-code

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.

ResearchClaude

deep-research

144923
from affaan-m/everything-claude-code

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.

ResearchClaude

hybrid-search-implementation

31392
from sickn33/antigravity-awesome-skills

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Information RetrievalClaude

hig-components-search

31392
from sickn33/antigravity-awesome-skills

Apple HIG guidance for navigation-related components including search fields, page controls, and path controls.

exa-search

31392
from sickn33/antigravity-awesome-skills

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.).

Information RetrievalClaude

deep-research

31392
from sickn33/antigravity-awesome-skills

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

ResearchClaudeGemini

context7-auto-research

31392
from sickn33/antigravity-awesome-skills

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.

Developer ToolsClaude

azure-search-documents-ts

31392
from sickn33/antigravity-awesome-skills

Build search applications with vector, hybrid, and semantic search capabilities.

Search and RetrievalClaude

azure-search-documents-py

31392
from sickn33/antigravity-awesome-skills

Azure AI Search SDK for Python. Use for vector search, hybrid search, semantic ranking, indexing, and skillsets.

Text AnalysisClaude

azure-search-documents-dotnet

31392
from sickn33/antigravity-awesome-skills

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search.

Information RetrievalClaude