# Send Lead Scorer 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": "lead-scorer-free",
    "name": "Lead Scorer",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/psyduckler/lead-scorer-free",
    "canonicalUrl": "https://clawhub.ai/psyduckler/lead-scorer-free",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/lead-scorer-free",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lead-scorer-free",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "scripts/profiles/clearscope.json",
      "scripts/profiles/default.json",
      "scripts/score_lead.py"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "lead-scorer-free",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T04:36:01.773Z",
      "expiresAt": "2026-05-09T04:36:01.773Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lead-scorer-free",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lead-scorer-free",
        "contentDisposition": "attachment; filename=\"lead-scorer-free-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "lead-scorer-free"
      },
      "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/lead-scorer-free"
    },
    "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/lead-scorer-free",
    "downloadUrl": "https://openagent3.xyz/downloads/lead-scorer-free",
    "agentUrl": "https://openagent3.xyz/skills/lead-scorer-free/agent",
    "manifestUrl": "https://openagent3.xyz/skills/lead-scorer-free/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/lead-scorer-free/agent.md"
  }
}
```
## Documentation

### Lead Scorer

Analyze a domain and return a 0-100 lead score with detailed breakdown. The key feature is customizable scoring profiles — JSON configs that define which signals matter and their weights.

### How It Works

DNS Analysis — MX records (Google Workspace/M365 = real business), SPF/DMARC
Sitemap Parsing — URL count, last modified dates, content volume
Website Scraping — Blog detection, tech stack, meta tags, social links, contact info
Signal Scoring — Each signal scored against the profile weights
Grade Assignment — A (80-100), B (60-79), C (40-59), D (20-39), F (0-19)

### Dependencies

pip3 install dnspython

### Single domain (default profile)

python3 scripts/score_lead.py example.com

### With custom profile

python3 scripts/score_lead.py example.com --profile clearscope.json

### Multiple domains

python3 scripts/score_lead.py domain1.com domain2.com domain3.com

### Batch from CSV

python3 scripts/score_lead.py --csv leads.csv --domain-column "Website"

### Options

--profile FILE — Scoring profile JSON (default: default.json, resolved from scripts/profiles/)
--csv FILE — CSV file with domains
--domain-column NAME — Column name for domains in CSV (default: domain)
--scrape-delay SECONDS — Delay between HTTP requests (default: 0.5)
--output FILE — Write results to file instead of stdout

### Output

JSON to stdout with overall score, per-signal breakdown, raw data, and summary:

{
  "domain": "example.com",
  "score": 72,
  "grade": "B",
  "profile": "default",
  "signals": {
    "has_blog": {"score": 20, "max": 20, "evidence": "Blog found at /blog; 234 URLs in sitemap"},
    "business_legitimacy": {"score": 15, "max": 20, "evidence": "MX: Google Workspace; SPF configured"}
  },
  "raw_data": {
    "sitemap_urls": 234,
    "mx_provider": "Google Workspace",
    "tech_stack": ["WordPress", "Cloudflare"]
  },
  "summary": "Strong in: has blog, business legitimacy. Good lead, worth pursuing."
}

### Scoring Profiles

Profiles are the key differentiator. They let you define what matters for YOUR use case.

### Profile format

{
  "name": "my-profile",
  "description": "What this profile scores for",
  "signals": {
    "signal_name": {
      "weight": 25,
      "description": "What this signal measures",
      "keywords": ["optional", "keyword", "list"]
    }
  }
}

### Built-in signals

SignalWhat it checkshas_blogBlog/content section existence + sitemap volumebusiness_legitimacyMX provider, SPF/DMARC, about page, meta tagscontent_velocitySitemap dates — recency and frequency of updatestech_stackCMS, analytics, chat tools detected in page sourceaudience_sizeSocial media links (Twitter, LinkedIn, YouTube, Facebook)contact_findabilityContact page, emails on site, LinkedIn linkseo_toolsKeyword matching in homepage text (requires keywords array)

### Custom keyword signals

Any signal with a keywords array will match those terms against the homepage text. This is how you detect competitors, tools, or industry terms:

{
  "name": "crm-seller",
  "signals": {
    "uses_crm": {
      "weight": 30,
      "description": "Already uses a CRM",
      "keywords": ["salesforce", "hubspot", "pipedrive", "zoho crm", "close.io"]
    },
    "has_sales_team": {
      "weight": 25,
      "description": "Mentions sales roles or team",
      "keywords": ["sales team", "account executive", "sdr", "business development"]
    }
  }
}

### Shipped profiles

default.json — Generic scoring for any SaaS/content company
clearscope.json — Example profile for SEO tool partnership leads

Create your own in scripts/profiles/ or pass any path with --profile.

### Rate Limiting

The script is polite by default:

--scrape-delay 0.5 — 500ms between HTTP requests (default)
Each domain makes ~5-8 requests (homepage, blog, about, contact, sitemap, DNS)
For batch mode, there's an additional delay between domains
Increase delay for large batches: --scrape-delay 2
All requests use a generic User-Agent string

### Recommended delays

Batch sizeDelayEst. time1-100.5s (default)~30s-2min10-501.0s~5-15min50+2.0s~30min+

### Error Handling

If a signal can't be gathered (site down, DNS timeout, etc.), it scores 0 with an explanation in the evidence field. The script never crashes on a single domain failure — it logs the issue to stderr and continues.

### Tips

Start with default profile, review results, then customize
Weights should sum to 100 for intuitive scoring (not required — auto-normalizes)
Keywords are powerful — add competitor names, industry terms, technology mentions
Pipe to jq for quick filtering: python3 scripts/score_lead.py domain.com | jq '.score'
Batch + sort: Score a CSV, then sort by score to prioritize outreach
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: psyduckler
- 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: 2026-05-02T04:36:01.773Z
- Expires at: 2026-05-09T04:36:01.773Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/lead-scorer-free)
- [Send to Agent page](https://openagent3.xyz/skills/lead-scorer-free/agent)
- [JSON manifest](https://openagent3.xyz/skills/lead-scorer-free/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/lead-scorer-free/agent.md)
- [Download page](https://openagent3.xyz/downloads/lead-scorer-free)