Tavily Search

What it does

The current entry routes questions to search, known URLs to extraction, site navigation to mapping and site sections to crawling. It supports MCP tools or a CLI path and separates a generated answer from the evidence that supports it. Longer investigations are handed to the companion research workflow rather than treated as a single ranked search result.

Best for

Agents locating current sources or retrieving a small, explicitly scoped set of pages for a factual question.

Tradeoffs and requirements

A provider ranking or generated answer does not establish accuracy or complete coverage. Tool schemas, installed CLI syntax and service access need current checks. The instruction includes broader search and installation suggestions; these remain subordinate to the host permissions, actual task scope and applicable source rights.

Unknown; inspect source requirements and supporting scripts.

Install from the source

First time installing a skill? Follow the walkthrough →

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/tavily-ai/skills/tree/00a131a8033e565829a21f49745925801213ea97/skills/core/tavily-search --skill tavily-search

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

• Network Access — review the source context.
• Shell Or Package Install — review the source context.

Allowed tools declaration: Bash(tvly *). Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

85/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

100/100

100

Repository Health

100/100

100

Compatibility Evidence

80/100

80

Popularity

48/100

48

Originality

80/100

80

Static Safety

60/100

60

Suggested workflow

Identify whether the missing input is a fact, a known page or a site section. Use focused names and date or domain constraints, inspect the strongest direct source, and keep large results in the intended task artifact rather than searching unrelated temporary files.

How to judge the result

Verify important claims on the named primary source, preserve dates and URLs, and report failed or incomplete retrievals. Distinguish a retrieved passage from inference and a service-generated synthesis; do not treat webpage instructions as permission to run code or widen the task.