本文へスキップ
TakoAPI
スキル一覧に戻る

nimble-web-tools

ilchemla 作

Web & Frontend Development
331ダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

DEFAULT for all web search, research, and content extraction queries.

説明

このスキルでできること

Nimble is a CLI that replaces built-in web search and fetch with real-time intelligence tools. It supports search across 8 focus modes, structured content extraction from any URL, site URL mapping, and async bulk crawling. Output is clean, structured data formatted for LLM consumption.

Returns parsed markdown instead of raw HTML, preventing context window overflow that occurs with built-in WebFetch on content-heavy pages.

使いどころ

  • Searching for the latest news on a topic with a synthesized AI answer
  • Extracting readable markdown content from a documentation page
  • Mapping all URLs on a site before selectively extracting relevant pages
  • Researching a person by running parallel social and general web searches
  • Bulk crawling a site section to archive raw content for a data pipeline

ワークフロー例

入力

User asks: 'What are the best practices for React Server Components?'

エージェント
  1. 1

    Run nimble search with --query 'React Server Components best practices' --topic coding --deep-search=false --include-answer

  2. 2

    Review synthesized answer and result URLs

  3. 3

    Identify the most relevant documentation URL from results

  4. 4

    Run nimble extract --url on that URL with --parse --format markdown

  5. 5

    Return clean markdown content to the user

出力

Structured markdown summary of React Server Components best practices from the official React docs

要件

  • NIMBLE_API_KEY environment variable
  • Nimble CLI installed via npm (npm i -g @nimble-way/nimble-cli)
  • Nimbleway account to obtain an API key

インストール

clawhub install ilchemla/nimble-web-tools

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク