mcpField
T
tavily-hikari-crawl

tavily-hikari-crawl

github.com/ivanli-cnData & databases36856 installsUpdated 2d ago
Repository

About tavily-hikari-crawl

A skill for using Tavily Hikari to run bounded website crawls and save results for later analysis. It guides agents through setting crawl scope and using the `tvly-hikari` CLI.

Key features

  1. 01Bounded site and path crawling
  2. 02JSON-formatted crawl output
  3. 03Save results to an output directory
  4. 04Guidance on crawl scope

Use cases

  1. 01Crawling a documentation path
  2. 02Saving crawl data for follow-up analysis

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ivanli-cn/tavily-hikari --skill tavily-hikari-crawl

After installing, type/tavily-hikari-crawlin Claude Code to confirm it loaded.

Details

From the project README

Tavily Hikari Crawl

Use this skill when a task needs to crawl a site or path through Tavily Hikari.

Workflow

  1. Define the start URL and crawl bounds before running the command.

  2. Run a bounded crawl:

    tvly-hikari crawl https://example.com/docs --json

  3. Save crawl results for follow-up analysis:

    tvly-hikari crawl https://example.com/docs --json --output-dir tavily-crawl

  4. Prefer narrow crawl scope over broad site-wide crawling.

Hikari Notes

  • Requests go to the configured Hikari /api/tavily/crawl facade.
  • Hikari token quota and audit logs apply to the crawl.
  • The upstream Tavily key remains inside Hikari's key pool.

Comments

Markdown supported