mcpField
T
tavily-hikari-research

tavily-hikari-research

github.com/ivanli-cnProductivity36858 installsUpdated 2d ago
Repository

About tavily-hikari-research

tavily-hikari-research is an Agent skill for multi-step research through Tavily Hikari. It guides question scoping, result saving, and checking or polling asynchronous research requests.

Key features

  1. 01Scoped research questions
  2. 02JSON research results
  3. 03Save research output
  4. 04Check and poll async requests

Use cases

  1. 01Research a topic across multiple steps
  2. 02Save results for a longer investigation
  3. 03Retrieve an asynchronous research result

Install

Copy the command and run it in a terminal.

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

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

Details

From the project README

Tavily Hikari Research

Use this skill when the task needs multi-step Tavily research through Tavily Hikari.

Workflow

  1. Write a concise research question with scope, date, geography, and source constraints.

  2. Run:

    tvly-hikari research "Compare Tavily CLI, Agent Skills, and MCP for AI agents" --json

  3. Save the response for longer investigations:

    tvly-hikari research "Compare Tavily CLI, Agent Skills, and MCP for AI agents" --json -o tavily-research.json

  4. If the official CLI returns an async request id, inspect or wait for the result through the official follow-up commands exposed by the wrapper:

    tvly-hikari research status <request-id> --json
tvly-hikari research poll <request-id> --json -o tavily-research.json

Hikari Notes

  • Requests go to the configured Hikari /api/tavily/research facade.
  • Hikari token quota applies to research calls.
  • Hikari audit logs retain the downstream token context while upstream keys remain private.

Comments

Markdown supported