enrich-and-score-lead — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited enrich-and-score-lead (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Enrich a single prospect using any available identifier and produce a structured profile with an ICP fit score and recommended next actions.
When a user provides a LinkedIn URL, email address, or name + company combination, enrich the person and their company, then synthesize the data into a scored profile.
linkedin.com/in/username)[email protected])mcp__claude_ai_Amplemarket__enrich_person with the available identifiers:linkedin_url if providedemail if providedname + company_name or company_domain if providedreveal_email to true and reveal_phone_numbers to true to get full contact details.reveal_email and reveal_phone_numbers consumes additional Amplemarket credits per reveal. Factor this in when enriching large batches.mcp__claude_ai_Amplemarket__enrich_company with:domain from the person enrichment result, orlinkedin_url of the company if the domain is not available.If the user has previously stated their ICP criteria, adjust the scoring weights to match their specific requirements.
Contact Card:
Company Card:
ICP Fit Score:
Recommended Next Steps:
User prompt: "Enrich this lead: linkedin.com/in/johndoe-vpsales"
What the skill does:
mcp__claude_ai_Amplemarket__enrich_person with linkedin_url: "https://linkedin.com/in/johndoe-vpsales", reveal_email: true, reveal_phone_numbers: true.mcp__claude_ai_Amplemarket__enrich_company with the extracted domain.Example output:
Contact Card
| Field | Value |
|---|---|
| Name | John Doe |
| Title | VP of Sales |
| Seniority | VP |
| Department | Revenue |
| [email protected] | |
| Phone | +1 (555) 123-4567 |
| linkedin.com/in/johndoe-vpsales | |
| Location | San Francisco, CA |
Company Card
| Field | Value |
|---|---|
| Company | TechCorp |
| Domain | techcorp.com |
| Industry | Computer Software |
| Size | 201-500 employees |
| Type | Privately Held |
| HQ | San Francisco, CA |
| Description | AI-powered sales automation platform |
ICP Fit Score: 82/100 (A)
| Factor | Score | Reasoning |
|---|---|---|
| Seniority | 27/30 | VP-level is a key decision maker |
| Company Size | 22/25 | 201-500 is ideal for B2B SaaS |
| Industry | 18/20 | Software/Tech is a core ICP industry |
| Data Completeness | 15/15 | Both email and phone found |
| Company Signals | 0/10 | No specific growth signals detected |
Recommended Next Steps:
User prompt: "Score this prospect: [email protected]"
What the skill does:
mcp__claude_ai_Amplemarket__enrich_person with email: "[email protected]", reveal_phone_numbers: true.mcp__claude_ai_Amplemarket__enrich_company with domain: "finova.io".User prompt: "What can you tell me about David Kim at Stripe?"
What the skill does:
mcp__claude_ai_Amplemarket__enrich_person with name: "David Kim", company_name: "Stripe", reveal_email: true, reveal_phone_numbers: true.mcp__claude_ai_Amplemarket__enrich_company with domain: "stripe.com".The default scoring weights (Seniority 30%, Company Size 25%, Industry 20%, Data Completeness 15%, Company Signals 10%) work well for mid-market B2B SaaS. Adjust them when your ICP differs:
Tell the user: "I'm using default ICP scoring weights. Want me to adjust for your specific selling motion?"
| Problem | Solution |
|---|---|
| Person not found | Fallback chain: 1) Try LinkedIn URL if not already used. 2) Try company domain + full name. 3) Try search_people with company_domains + person_titles as a fuzzy match. 4) If still not found, inform user with suggestions: "Could not find this person. Try providing their LinkedIn URL or exact company domain." |
| Company enrichment fails | Fallback chain: 1) Try the company domain instead of name (or vice versa). 2) Try the LinkedIn company URL. 3) Try the parent company domain if this is a subsidiary. 4) If still failing, use whatever company data was returned in person enrichment and flag the gap. |
| Person enrichment succeeds but company enrichment fails | Use whatever company data was returned in the person enrichment (company name, domain). Present the person profile and note that company details are limited. Score with available data and flag the gap. |
| Company enrichment succeeds but person enrichment fails | Present the company profile and suggest alternative identifiers. Try searching for the person via search_people with company domain + title as a fallback. |
| Multiple people match the same name + company | Present all matches with titles and ask the user to confirm which person they mean. If LinkedIn URLs are available, show those for disambiguation. |
| Email not revealed | The contact may not have a verified business email. Suggest LinkedIn outreach instead. |
| Low data completeness | Combine multiple identifiers in the enrichment call for better match rates. If email is missing, suggest LinkedIn outreach. If phone is missing, note it in the profile and suggest email as primary channel. Always score with available data and flag which factors were impacted by missing data. |
| Score seems off | Ask the user to define their specific ICP criteria so scoring weights can be adjusted. |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.