# Deep Research Tavily

> Use Tavily Search API for bounded deep research retrieval, RAG-ready snippets, and low-cost web search. Use when a workflow needs search grounding, source discovery, or benchmarkable retrieval rather than full report-writing.

- Skill: `closedloop-technologies/deep-research-tavily` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add closedloop-technologies/deep-research-tavily`
- Raw SKILL.md: https://api.skillmd.com/api/skills/closedloop-technologies/deep-research-tavily/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- Author: closedloop-technologies (https://skillmd.com/u/closedloop-technologies)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/closedloop-technologies/deep-research-tavily

---


# Tavily Search

Use this skill for low-cost search/retrieval steps inside a deep research
workflow. Tavily is usually a retriever, not a full report-writing agent.

## Environment

```bash
op run --env-file .env.climbhill -- python .agents/skills/deep-research-tavily/scripts/tavily_search.py \
  --query "deepresearch the deepresearchers" \
  --search-depth basic \
  --max-results 5
```

Required 1Password-backed variable:

- `TAVILY_API_KEY`

## Cost Controls

- Use `basic`, `fast`, or `ultra-fast` search depth for benchmark tasks.
- Use `advanced` only when the task explicitly needs deeper retrieval.
- Keep `max_results` small and avoid raw content unless needed.

## Current Source Links

- https://docs.tavily.com/documentation/api-reference/endpoint/search
- https://docs.tavily.com/documentation/api-credits