tavily-crawl
tavily-crawl is an agent skill published by tavily-ai, listed under writing & docs. It lives in the tavily-ai/skills repository, which has 491 GitHub stars and is licensed under MIT; we last read it on 2026-09-16.
Crawl websites and extract content from multiple pages. Requires no credentials. Supports depth/breadth control, path filtering, and semantic instructions, saving each page as a local markdown file.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads tavily-ai/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add tavily-ai/skills
Maintenance
Crawl websites and extract content from multiple pages via the Tavily CLI. Use this skill when the user wants to crawl a site, download documentation, extract an entire docs section, bulk-extract pages, save a site as local markdown files, or says "crawl", "get all the pages", "download the docs", "extract everything under /docs", "bulk extract", or needs content from many pages on the same domain. Supports depth/breadth control, path filtering, semantic instructions, and saving each page as a local markdown file.
tavily-crawl compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| tavily-crawl (this page) | tavily-ai | Crawl websites and extract content from multiple pages via the Tavily CLI. Use this skill when the user wants… | 491 | 2026-10-23 |
| academy-guide | anthropic | Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude produc… | 183,845 | 2026-10-09 |
| doc-coauthoring | anthropic | Guide users through a structured workflow for co-authoring documentation. Use when user wants to write docume… | 183,845 | 2026-10-09 |
| documentation-and-adrs | addyosmani | Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reas… | 110,611 | 2026-10-13 |
| git-workflow-and-versioning | addyosmani | Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving… | 110,611 | 2026-10-13 |
| source-driven-development | addyosmani | Grounds every implementation decision in official documentation. Use when you want to verify an approach agai… | 110,611 | 2026-10-13 |
| developing-genkit-dart | Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents… | 21,580 | 2026-10-25 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about tavily-crawl
- What does tavily-crawl do?
- Crawl websites and extract content from multiple pages. Requires no credentials. Supports depth/breadth control, path filtering, and semantic instructions, saving each page as a local markdown file.
- How do I install tavily-crawl?
- Run npx skills add tavily-ai/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes tavily-crawl?
- tavily-ai.
- Is tavily-crawl maintained, and what licence does it use?
- Its repository has 491 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-23. The repository declares the MIT licence.
More agent skills for writing & docs
- technical-blog-writingby 101-skills
- documentation-and-adrsby addyosmani
- git-workflow-and-versioningby addyosmani
- source-driven-developmentby addyosmani
- vitepressby antfu
- academy-guideby anthropic