convez.ai
SkillIntegração & APIsIntermediário
eruto-skills

Fetch Web

eruto-skills/fetch-web

Fetch de páginas web com Markdown e fallback automático

Ver no GitHub
InicialPluginScore · de 0 a 100

Skill que extrai conteúdo de páginas web como Markdown, com fallback inteligente entre r.jina.ai, Chrome headless e curl direto. Projetada como utilitário reutilizável para outras skills do ecossistema Eruto.

Instalação

$npx convez-ai eruto-skills/fetch-web

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
50%
Último commit
há 1 mês
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Extrair conteúdo de artigos e documentos web para processamento
  • Reutilizar em outras skills que precisem acessar conteúdo web
  • Converter HTML complexo para Markdown limpo com renderização JS

Veredito

Skill sólida e pragmática com arquitetura de fallback bem pensada. Resolve um problema real (fetch + rendering + conversão para Markdown) com flexibilidade para diferentes ambientes, embora demande dependências externas (Chrome, Node 22+).

README

A tradução para o português deste README ainda está na fila.

fetch-web

Claude Code skill — Fetch web page content as Markdown

Web ページのコンテンツを Markdown で取得する共通フェッチユーティリティ。他スキルから参照される共通戦略として設計されており、r.jina.ai → headless Chrome → direct curl の順でフォールバックする。

フェッチ戦略

  1. r.jina.ai(主)— curl -s 'https://r.jina.ai/<URL>'
  2. headless Chrome(フォールバック)— node scripts/fetch-page.js "<URL>"
  3. direct curl(最終手段)— JS レンダリング不要のシンプルな HTML のみ

Installation

/plugin install fetch-web@eruto-skills

Dependencies

  • curl — Windows 11 標準搭載
  • Google Chrome — fetch-page.js が標準パスで自動検出
  • puppeteer-core + turndown — npm install in scripts/(Node.js 22.12 以上)

License

MIT

Codex / Claude Code installation

This package supports both Codex and Claude Code. The plugin entry point is skills/fetch-web/SKILL.md; the root SKILL.md remains the standalone source.

For Codex, add the public eruto-skills marketplace in the plugin UI using https://github.com/eruto-skills/marketplace, then install fetch-web. To install as a standalone user skill instead:

mkdir -p ~/.agents/skills
git clone https://github.com/eruto-skills/fetch-web.git ~/.agents/skills/fetch-web

On Windows PowerShell:

New-Item -ItemType Directory -Force "$env:USERPROFILE/.agents/skills" | Out-Null
git clone https://github.com/eruto-skills/fetch-web.git "$env:USERPROFILE/.agents/skills/fetch-web"

In Codex, select the installed skill by name or invoke $fetch-web with a task. In Claude Code:

/plugin marketplace add eruto-skills/marketplace
/plugin install fetch-web@eruto-skills

The instructions use the tools available in the current host. Scripts are resolved from the actual skill directory, rather than a fixed author path. Additional browser, Python, or format-specific dependencies are described in SKILL.md and the references; installing the plugin alone does not install those external programs.

Maintaining the plugin package

Edit the root SKILL.md and its supporting resources, then run:

node scripts/package-plugin.mjs
node scripts/package-plugin.mjs --check

Commit the generated skills/ files with the source changes. CI checks that both layouts match, including the Claude manifest. Do not edit generated files directly.

Ver o original no GitHub

Bom para

Relacionados