extract

Extract content from specific URLs using Tavily's extraction API. Returns clean markdown/text from web pages. Use when you have specific URLs and need their content without writing code.

2.66x

Quality

75%

Does it follow best practices?

Impact

88%

2.66x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/tavily/extract/SKILL.md

Evaluation results

100%

70%

Research Content Aggregator

Batching and targeted extraction

Criteria

Without context

With context

Uses extract.sh script

100%

JSON argument format

100%

Batches into multiple requests

100%

Uses query parameter

100%

Uses chunks_per_source

100%

chunks_per_source paired with query

100%

Reports failed results

100%

Markdown format preserved

100%

65%

-5%

Competitor Pricing Monitor

JS-page depth and timeout handling

Criteria

Without context

With context

Uses extract.sh script

Selects advanced depth

100%

50%

Sets extended timeout

100%

Timeout within valid range

100%

All 6 URLs included

100%

Checks failed_results

100%

JSON argument format

100%

Product Catalog Content Harvester

Image extraction and response handling

Criteria

Without context

With context

Uses extract.sh script

100%

Enables image extraction

100%

Uses query parameter

100%

Uses chunks_per_source

100%

chunks_per_source value is 3

100%

Plain text format

100%

Extracts failed_results

100%

JSON argument format

100%

Repository: tavily-ai/skills
Commit: 1e2a6a0

Evaluated: 29 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Research Content Aggregator Competitor Pricing Monitor Product Catalog Content Harvester

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.