Dianel555/DSkills / skills/grok-search
grok-search
VerifiedEnhanced web search and real-time content retrieval via Grok API with forced tool routing. Use when: (1) Web search / information retrieval / fact-checking, (2) Webpage content extraction / URL parsing, (3) Breaking knowledge cutoff limits for current information, (4) Real-time news and technical documentation, (5) Multi-source information aggregation. Triggers: "search for", "find information about", "latest news", "current", "fetch webpage", "get content from URL". IMPORTANT: This skill REPLACES built-in WebSearch/WebFetch with Grok Search tools.
| File | Kind | Size |
|---|---|---|
| .env.example | other | 3.2 KB |
| README.md | markdown | 8.5 KB |
| SKILL.md | skill md | 6.6 KB |
| ruff.toml | config | 904 B |
| scripts/groksearch/__init__.py | script | 47 B |
| scripts/groksearch/cli.py | script | 5.0 KB |
| scripts/groksearch/commands.py | script | 9.1 KB |
| scripts/groksearch/config.py | script | 14.0 KB |
| scripts/groksearch/env.py | script | 1.4 KB |
| scripts/groksearch/formatting.py | script | 3.0 KB |
| scripts/groksearch/http.py | script | 2.9 KB |
| scripts/groksearch/prompts.py | script | 704 B |
| scripts/groksearch/provider.py | script | 5.7 KB |
| scripts/groksearch/tavily.py | script | 18.0 KB |
| scripts/groksearch_cli.py | script | 6.8 KB |
| scripts/tests/test_groksearch_cli.py | script | 62.8 KB |
| scripts/tests/test_retry_budget.py | script | 703 B |
.env.example
View on GitHub# GrokSearch CLI Configuration
# Copy this file to .env and fill in your values
# Required: Grok API endpoint (OpenAI-compatible format)
GROK_API_URL=https://your-api-endpoint.com/v1
# Required: Your API key
GROK_API_KEY=your-api-key-here
# Optional: Default model
GROK_MODEL=grok-4-1-fast
# Optional: Enable debug mode (true/false)
GROK_DEBUG=false
# Optional: Tavily API (for --extra-sources, --via tavily, web_map)
TAVILY_API_URL=https://api.tavily.com
TAVILY_API_KEY=
TAVILY_ENABLED=true
# Optional: Tavily search tuning
# search_depth: advanced(2 credits, highest relevance) | basic/fast/ultra-fast(1 credit)
# advanced = niche topics, very recent pages, multi-facet queries (recommended for grounding)
# basic = general-purpose lookups where lower latency matters
TAVILY_SEARCH_DEPTH=advanced
# Snippets per source (1-5); higher = more grounding evidence per URL
TAVILY_CHUNKS_PER_SOURCE=3
# topic: general | news | finance (news auto-adds published_date)
TAVILY_TOPIC=general
# time_range: day | week | month | year (blank = no date filter)
TAVILY_TIME_RANGE=
# Domain filters, comma-separated. include_domains_mode: filter | boost
# boost also searches the wide web, so trusted sources are prioritized without
# risking empty results. Requires TAVILY_INCLUDE_DOMAINS to be set.
TAVILY_INCLUDE_DOMAINS=
TAVILY_EXCLUDE_DOMAINS=
TAVILY_INCLUDE_DOMAINS_MODE=filter
# include_answer: false | basic | advanced (LLM answer; extra cost, off by default)
TAVILY_INCLUDE_ANSWER=false
# Log credit usage in each response (useful when auditing cost)
TAVILY_INCLUDE_USAGE=false
# Optional: Tavily extract tuning (web_fetch --via tavily)
# extract_depth: basic(faster) | advanced(tables, JS-heavy pages, higher success)
# Also applies to web_crawl extraction.
TAVILY_EXTRACT_DEPTH=basic
# Tavily-side timeout in seconds (API range 1.0-60.0)
TAVILY_EXTRACT_TIMEOUT=30
# Optional: Tavily crawl tuning (web_crawl)
# Crawl has its own rate limit: 100 RPM on both development and production keys.
# timeout: API range 10-150 seconds.
TAVILY_CRAWL_TIMEOUT=150
TAVILY_CRAWL_MAX_DEPTH=1
TAVILY_CRAWL_MAX_BREADTH=20
TAVILY_CRAWL_LIMIT=50
# Follow links to other domains (default true; set false to stay on one site)
TAVILY_CRAWL_ALLOW_EXTERNAL=true
# Path regexes, comma-separated (e.g. /docs/.*,/api/.*). Blank = no path filter.
TAVILY_CRAWL_SELECT_PATHS=
TAVILY_CRAWL_EXCLUDE_PATHS=
# Optional: Tavily research tuning (web_research)
# Research is async: the task is submitted, then polled until completed/failed.
# Its own rate limit is 20 RPM on both tiers — far tighter than search.
TAVILY_RESEARCH_MODEL=auto
TAVILY_RESEARCH_CITATION_FORMAT=numbered
TAVILY_RESEARCH_OUTPUT_LENGTH=standard
# Path to a JSON Schema file for structured output (blank = free-form text).
# Must have a non-empty "properties"; each property needs "type" + "description".
# Example:
# {"properties": {"company": {"type": "string", "description": "The company name"}},
# "required": ["company"]}
TAVILY_RESEARCH_OUTPUT_SCHEMA=
# Overall polling budget in seconds, and delay between status checks.
TAVILY_RESEARCH_TIMEOUT=300
TAVILY_RESEARCH_POLL_INTERVAL=5
# Optional: Retry tuning (applies to Grok and Tavily HTTP calls)
GROK_RETRY_MAX_ATTEMPTS=3
GROK_RETRY_MULTIPLIER=1
GROK_RETRY_MAX_WAIT=10
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |