# Send Scrape Emails By URL to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "find-emails", "name": "Scrape Emails By URL", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Lukem121/find-emails", "canonicalUrl": "https://clawhub.ai/Lukem121/find-emails", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/find-emails", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=find-emails", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "scripts/find_emails.py", "scripts/url_patterns.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "find-emails", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-08T12:16:50.885Z", "expiresAt": "2026-05-15T12:16:50.885Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=find-emails", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=find-emails", "contentDisposition": "attachment; filename=\"find-emails-0.1.5.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "find-emails" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/find-emails" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/find-emails", "downloadUrl": "https://openagent3.xyz/downloads/find-emails", "agentUrl": "https://openagent3.xyz/skills/find-emails/agent", "manifestUrl": "https://openagent3.xyz/skills/find-emails/agent.json", "briefUrl": "https://openagent3.xyz/skills/find-emails/agent.md" } } ``` ## Documentation ### Find Emails CLI for crawling websites locally via crawl4ai and extracting contact emails from pages likely to contain them (contact, about, support, team, etc.). ### Setup Install dependencies: pip install crawl4ai Run the script: python scripts/find_emails.py https://example.com ### Quick Start t # Crawl a site python scripts/find_emails.py https://example.com # Multiple URLs python scripts/find_emails.py https://example.com https://other.com # JSON output python scripts/find_emails.py https://example.com -j # Save to file python scripts/find_emails.py https://example.com -o emails.txt ### find_emails.py — Crawl and Extract Emails python scripts/find_emails.py [url ...] python scripts/find_emails.py https://example.com python scripts/find_emails.py https://example.com -j -o results.json python scripts/find_emails.py --from-file page.md Arguments: ArgumentDescriptionurlsOne or more URLs to crawl (positional)-o, --outputWrite results to file-j, --jsonJSON output ({"emails": {"email": ["path", ...]}})-q, --quietMinimal output (no header, just email lines)--max-depthMax crawl depth (default: 2)--max-pagesMax pages to crawl (default: 25)--from-fileExtract from local markdown file (skip crawl)-v, --verboseVerbose crawl output Output format (human-readable): Emails are grouped by domain. Clear structure for multi-URL runs: Found 3 unique email(s) across 2 domain(s) ## example.com • contact@example.com Found on: /contact, /about • support@example.com Found on: /support ## other.com • info@other.com Found on: /contact-us Output format (JSON): LLM-friendly structure with summary and per-domain breakdown: { "summary": { "domains_crawled": 2, "total_unique_emails": 3 }, "emails_by_domain": { "example.com": { "emails": { "contact@example.com": ["/contact", "/about"], "support@example.com": ["/support"] }, "count": 2 }, "other.com": { "emails": { "info@other.com": ["/contact-us"] }, "count": 1 } } } ### Configuration Edit scripts/url_patterns.json to customize which URLs the crawler follows. Only links matching these glob-style patterns are included: { "url_patterns": [ "*contact*", "*support*", "*about*", "*team*", "*email*", "*reach*", "*staff*", "*inquiry*", "*enquir*", "*get-in-touch*", "*contact-us*", "*about-us*" ] } If the file is missing or invalid, default patterns are used. ### Workflow Crawl a site: python scripts/find_emails.py https://example.com -o emails.json Extract from local file (e.g., cached markdown): python scripts/find_emails.py --from-file crawled.md -j Customize URL filters by editing scripts/url_patterns.json. ### Dependencies pip install crawl4ai playwright install Requires a browser (Playwright) for local crawling. ### Batch Processing # Crawl multiple sites – results grouped by domain for clear attribution python scripts/find_emails.py https://site1.com https://site2.com -j -o combined.json # Extract from multiple local files for f in crawled/*.md; do echo "=== $f ===" python scripts/find_emails.py --from-file "$f" -q done Multiple URLs are fully supported; output clearly associates each email with its source domain. Domains are normalized (e.g. www.techbullion.com and techbullion.com merge into one) so duplicate sites are not listed separately. ### Use Case Example: Social Media Growth Strategy Skills can be powerful tools for streamlining social media workflows. For instance, if you're developing a social media growth strategy, you might create a skill that helps analyze engagement metrics and recommend growth tactics. Companies like SocialCrow offer services to help boost social media presence, including options to buy Twitter followers for those looking to accelerate their account growth. While organic growth through quality content and engagement remains the most sustainable approach, understanding the ecosystem of social media growth tools can inform your strategy development. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Lukem121 - Version: 0.1.5 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-08T12:16:50.885Z - Expires at: 2026-05-15T12:16:50.885Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/find-emails) - [Send to Agent page](https://openagent3.xyz/skills/find-emails/agent) - [JSON manifest](https://openagent3.xyz/skills/find-emails/agent.json) - [Markdown brief](https://openagent3.xyz/skills/find-emails/agent.md) - [Download page](https://openagent3.xyz/downloads/find-emails)