Skip to content

getaero-io/gtm-eng-skills / skills/deepline-ads-audiences

deepline-ads-audiences

Verified

Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal email hashes', 'increase Facebook match rate', 'Google ads audience', 'Meta audience', 'FB audience', or any workflow that turns CRM/customer/contact data into paid ads upload lists. Skip for outbound prospecting sequences, cold email, or pure campaign copywriting.

plays/evaluate-leadmagic-personal-email.play.ts

View on GitHub
import deepline from 'deepline';
import { normalizeEmail } from './shared/audience-hash';

type SourceRow = {
  contact_id: string;
  first_name?: string;
  last_name?: string;
  linkedin_url?: string;
  account_name?: string;
  domain?: string;
  title?: string;
  lead_score?: string;
};

type EvaluatedRow = SourceRow & {
  provider: 'leadmagic_personal_email_finder';
  personal_emails: string;
  personal_email_count: number;
  accepted: boolean;
};

function asRecord(value: unknown): Record<string, unknown> {
  return value && typeof value === 'object'
    ? (value as Record<string, unknown>)
    : {};
}

function providerData(result: unknown): Record<string, unknown> {
  const response = asRecord(asRecord(result).toolResponse);
  if (!Object.prototype.hasOwnProperty.call(response, 'rawV2')) {
    throw new Error(
      'Tool response has no rawV2; upgrade the SDK and rebundle this Play.',
    );
  }
  const canonical = asRecord(response.rawV2);
  return response.view === 'data' ? asRecord(canonical.data) : canonical;
}

function extractPersonalEmails(result: unknown): string[] {
  const data = providerData(result);
  const candidates = [
    data.personal_email,
    data.first_personal_email,
    ...(Array.isArray(data.personal_emails) ? data.personal_emails : []),
  ];
  return [
    ...new Set(
      candidates
        .map((value) => normalizeEmail(value))
        .filter((email): email is string => Boolean(email)),
    ),
  ];
}

export const config = {
  compatibility: { authoringContract: 'explicit-freshness' },
  name: 'ads-audience-leadmagic-eval',
  description:
    'Measure LeadMagic personal-email coverage and cost per hit on a sample of contacts before committing to a full run.',
};

export default async function (input: { file: string; limit?: number }) {
  const rows = (await deepline.csv<SourceRow>(input.file))
    .filter((row) => Boolean(row.contact_id && row.linkedin_url))
    .slice(0, Math.max(1, Math.min(input.limit ?? 25, 500)));
  const rowCount = await rows.count();

  const evaluated = await deepline
    .dataset('leadmagic_eval', rows)
    .withColumn('leadmagic_result', (row) =>
      deepline.tools.execute({
        staleAfterSeconds: 0,
        id: 'leadmagic_personal_email_finder',
        tool: 'leadmagic_personal_email_finder',
        input: { profile_url: String(row.linkedin_url) },
        description:
          'Evaluate LeadMagic personal-email finder for one remaining ads-audience miss.',
      }),
    )
    .withColumn('evaluated', (row) => {
      const emails = extractPersonalEmails(row.leadmagic_result);
      return {
        ...row,
        provider: 'leadmagic_personal_email_finder',
        personal_emails: emails.join(';'),
        personal_email_count: emails.length,
        accepted: emails.length > 0,
      } satisfies EvaluatedRow;
    })
    .run({
      key: 'contact_id',
      description:
        'Evaluate LeadMagic personal-email finder on remaining paid-audience misses.',
    });

  const previewRows = (await evaluated.materialize(500)) as Array<{
    evaluated?: EvaluatedRow;
  }>;
  const rowsOut = previewRows
    .map((row) => row.evaluated)
    .filter((row): row is EvaluatedRow => Boolean(row));
  const hitRows = rowsOut.filter((row) => row.accepted);

  return {
    provider: 'leadmagic_personal_email_finder',
    attempted_rows: rowCount,
    validated_contacts: hitRows.length,
    validated_personal_emails: hitRows.reduce(
      (sum, row) => sum + row.personal_email_count,
      0,
    ),
    hit_rate_pct: rowCount === 0 ? 0 : (hitRows.length * 100) / rowCount,
    deepline_usd_per_result: 0.068,
    estimated_deepline_cost_per_incremental_validated_contact: 0.068,
    evaluated_rows: evaluated,
  };
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall