# Send Seo Prospector 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": "seo-prospector", "name": "Seo Prospector", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/MrMooseyMan/seo-prospector", "canonicalUrl": "https://clawhub.ai/MrMooseyMan/seo-prospector", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/seo-prospector", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=seo-prospector", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "PUBLISH-INSTRUCTIONS.md", "SKILL.md", "assets/examples/example-high-priority-report.md", "assets/examples/example-outreach-package.md", "assets/templates/dm-outreach.md", "assets/templates/email-html.html" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "seo-prospector", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-08T16:48:02.485Z", "expiresAt": "2026-05-15T16:48:02.485Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=seo-prospector", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=seo-prospector", "contentDisposition": "attachment; filename=\"seo-prospector-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "seo-prospector" }, "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/seo-prospector" }, "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/seo-prospector", "downloadUrl": "https://openagent3.xyz/downloads/seo-prospector", "agentUrl": "https://openagent3.xyz/skills/seo-prospector/agent", "manifestUrl": "https://openagent3.xyz/skills/seo-prospector/agent.json", "briefUrl": "https://openagent3.xyz/skills/seo-prospector/agent.md" } } ``` ## Documentation ### SEO Prospector Automated local business lead generation for web designers and agencies. Pipeline: discover → research → audit → report → outreach → track. ### How It Works This skill turns you into a prospecting machine. Point it at a city or industry, and it: Finds businesses with weak websites (via SEO audit + web research) Generates detailed prospect reports with specific issues found Creates personalized outreach (HTML emails, LinkedIn messages, DMs) Tracks everything in a database with dedup + cluster rotation Delivers daily summaries of your pipeline health ### Setup (First Run) Before using, configure your agency details: # Copy and edit the config file cp references/config-template.json ~/.openclaw/workspace/leads/data/seo-prospector-config.json Edit the config with your info: { "agency": { "name": "Your Agency Name", "owner": "Your Name", "phone": "(555) 123-4567", "email": "you@agency.com", "website": "youragency.com", "city": "Your City", "tagline": "Your one-liner value prop" }, "outreach": { "default_tone": "casual", "signature_style": "friendly" } } ### Research One Prospect python3 scripts/research_prospect.py \\ --business "Business Name" --domain "example.com" --industry "Restaurant" \\ --priority HIGH --cluster "Restaurants" ### Batch Research (Today's Rotation) python3 scripts/batch_research.py --run morning # Today's run_1 cluster python3 scripts/batch_research.py --run afternoon # Today's run_2 cluster python3 scripts/batch_research.py --cluster "Restaurants" --limit 5 ### Generate Outreach python3 scripts/create_outreach.py --report path/to/report.md --template casual python3 scripts/create_outreach.py --business "Name" --template professional --format html ### Daily Summary python3 scripts/daily_summary.py # Today, Discord format python3 scripts/daily_summary.py --date 2026-02-09 --format markdown ### Pipeline Management python3 scripts/prospect_tracker.py today-clusters python3 scripts/prospect_tracker.py check --business "Name" python3 scripts/prospect_tracker.py stats python3 scripts/prospect_tracker.py outreach-ready ### 1. Check Schedule & Dedup Run prospect_tracker.py today-clusters to see scheduled clusters Run prospect_tracker.py check --business "Name" before researching (14-day dedup window) ### 2. Research Phase Data sources in priority order: SEO Quick Audit (seo_quick_audit.py) — on-page technical analysis Perplexity Search (perplexity_search.py) — business intel, reviews, reputation Browser verification (optional) — visual check for high-priority prospects ### 3. Report Generation Reports follow references/research-template.md. Key sections: Executive Summary (specific findings, not generic) Business Overview (what they do, how long, reviews) Online Presence Analysis (SEO audit results with pass/fail) Why [Your Agency] (pitch angle customized to their gaps) Contact & Next Steps (confidence level + recommended action) Output: ~/.openclaw/workspace/leads/prospects/YYYY-MM-DD-{cluster}/{business}.md ### 4. Outreach Generation scripts/create_outreach.py supports: HTML emails (professional, mobile-responsive, branded) Plain text emails (casual, no-frills) LinkedIn messages (see references/outreach-templates.md) DMs (Instagram, Facebook, SMS — see assets/templates/dm-outreach.md) Each outreach package includes: Email draft (HTML or plain text) Review checklist for manual QA Tracking JSON for pipeline status ### 5. Pipeline Tracking Every prospect gets tracked via prospect_tracker.py add. The database enables dedup, coverage stats, cluster tracking, and outreach status. Status pipeline: draft_ready → pending_review → approved → sent → followed_up → responded → closed ### Priority Scoring (Strict) Aim for ~30% HIGH, ~50% MEDIUM, ~20% LOW: HIGH: No website OR completely broken site, AND business confirmed active MEDIUM: Has website but major SEO gaps (no H1, no meta, no schema, bad mobile), AND confirmed active LOW: Decent website with minor issues, OR business activity unconfirmed If unsure, default to MEDIUM. ### Verification (Mandatory) Before recording any prospect, verify: python3 scripts/verify_prospect.py Skip prospects with: dead URLs, parked domains, suspended hosting, permanently closed businesses. ### Scripts ScriptPurposescripts/research_prospect.pyFull pipeline for single prospectscripts/batch_research.pyResearch multiple prospects from cluster or inputscripts/create_outreach.pyGenerate personalized outreach (HTML + plain text)scripts/generate_outreach_batch.pyBatch outreach for all prospects from a datescripts/daily_summary.pyPipeline summary (Discord or markdown)scripts/prospect_tracker.pyDatabase, dedup, cluster rotation, statsscripts/verify_prospect.pyURL/domain/phone verificationscripts/seo_quick_audit.pyOn-page SEO technical audit ### References FileUse Whenreferences/research-template.mdWriting or reviewing prospect reportsreferences/outreach-templates.mdDrafting email/LinkedIn/DM outreachreferences/industry-insights.mdIndustry-specific talking pointsreferences/objection-handling.mdHandling "we already have a site" etc.references/config-template.jsonFirst-time setup of agency detailsreferences/cluster-template.jsonSetting up industry cluster rotation ### Assets assets/templates/email-html.html — Professional HTML email template with merge fields assets/templates/email-plain.txt — Plain text email template assets/templates/linkedin-message.md — LinkedIn outreach templates assets/templates/dm-outreach.md — DM templates (SMS, IG, FB) assets/examples/example-report.md — Completed prospect report assets/examples/example-outreach.md — Completed outreach package ### Cron Integration Designed for automated daily prospecting: 8:30 AM — SERP Gap Scanner (identify opportunities for 5 industries) 10:00 AM — batch_research.py --run morning (Tier A/B cluster) 11:30 AM — batch_research.py --run afternoon (Tier B/C cluster) 5:00 PM — daily_summary.py (pipeline summary) ### Quality Rules Always check for duplicates first (14-day window) Minimum 2 data sources per prospect (SEO audit + web research) Specific findings only — "missing H1 tag" not "SEO issues" Authentic compliments — if their site is good, say so honestly 5 prospects per cluster max — depth over breadth Match outreach tone to industry — casual for restaurants, professional for law firms Verify every prospect before recording — no dead URLs, no parked domains Never exaggerate issues — stick to what the audit actually found ### Error Handling Site unreachable: Research via web search only, note limitation Duplicate detected: Skip with message, don't waste API calls Search timeout: Continue without, flag as lower confidence Empty cluster: Log and move on (cluster may be exhausted) Minimum data: Business name + (domain OR industry) required ## Trust - Source: tencent - Verification: Indexed source record - Publisher: MrMooseyMan - Version: 1.0.0 ## 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: 2026-05-08T16:48:02.485Z - Expires at: 2026-05-15T16:48:02.485Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/seo-prospector) - [Send to Agent page](https://openagent3.xyz/skills/seo-prospector/agent) - [JSON manifest](https://openagent3.xyz/skills/seo-prospector/agent.json) - [Markdown brief](https://openagent3.xyz/skills/seo-prospector/agent.md) - [Download page](https://openagent3.xyz/downloads/seo-prospector)