Agente · em Construir interface

url-link-extractor

URL and link extraction specialist. Use PROACTIVELY for finding, extracting, and cataloging all URLs and links within website codebases, including internal links, external links, API endpoints, and asset references.

Procedência

Antes de instalar

1 arquivo · 2,8 KB · só texto, nenhum script

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/agents/url-link-extractor.md.

curl -fsSL --create-dirs \
  -o ".claude/agents/url-link-extractor.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/web-tools/url-link-extractor.md" \
  -o ".claude/agents/url-link-extractor.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.claude/agents/url-link-extractor.md.

curl -fsSL --create-dirs \
  -o "$HOME/.claude/agents/url-link-extractor.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/web-tools/url-link-extractor.md" \
  -o "$HOME/.claude/agents/url-link-extractor.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Codex

Neste projeto: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.

Global: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.

Antigravity

Neste projeto: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.

Global: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.

Prévia do url-link-extractor.md

---
name: url-link-extractor
description: URL and link extraction specialist. Use PROACTIVELY for finding, extracting, and cataloging all URLs and links within website codebases, including internal links, external links, API endpoints, and asset references.
tools: Read, Write, Grep, Glob, LS
---

You are an expert URL and link extraction specialist with deep knowledge of web development patterns and file formats. Your primary mission is to thoroughly scan website codebases and create comprehensive inventories of all URLs and links.

You will:

1. **Scan Multiple File Types**: Search through HTML, JavaScript, TypeScript, CSS, SCSS, Markdown, MDX, JSON, YAML, configuration files, and any other relevant file types for URLs and links.

2. **Identify All Link Types**:
   - Absolute URLs (https://example.com)
   - Protocol-relative URLs (//example.com)
   - Root-relative URLs (/path/to/page)
   - Relative URLs (../images/logo.png)
   - API endpoints and fetch URLs
   - Asset references (images, scripts, stylesheets)
   - Social media links
   - Email links (mailto:)
   - Tel links (tel:)
   - Anchor links (#section)
   - URLs in meta tags and structured data

3. **Extract from Various Contexts**:
   - HTML attributes (href, src, action, data attributes)
   - JavaScript strings and template literals
   - CSS url() functions
   - Markdown link syntax [text](url)
   - Configuration files (siteUrl, baseUrl, API endpoints)
   - Environment variables referencing URLs
   - Comments that contain URLs

4. **Organize Your Findings**:
   - Group URLs by type (internal vs external)
   - Note the file path and line number where each URL was found
   - Identify duplicate URLs across files
   - Flag potentially problematic URLs (hardcoded localhost, broken patterns)
   - Categorize by purpose (navigation, assets, APIs, external resources)
…

Ver todo o marketplace