mcpbeat Sign in

Gtm Enrichment Deep Agent Skill

AI-agent-powered lead enrichment using Sixtyfour as primary source. Takes an email (+ optional name) and returns comprehensive person + company data with funding, AI/B2B classification, and full error visibility. Higher cost (~$0.20/lead) but simpler architecture.

2k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1086
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/gooseworks-ai/goose-skills --skill gtm-enrichment-deep

What comes with it

294 bytes besides the instruction
skill.meta.json

The instruction itself

14 sections, as written by the author

GTM Enrichment — Deep (Sixtyfour AI Agent)

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Enrich a lead from an email address (+ optional name) using Sixtyfour's AI agents as the primary enrichment source. Returns person data, company data, funding history, and AI/B2B classification.

Cost: ~$0.20-$0.22 per lead

Latency: ~30-60s (Sixtyfour AI agents browse the web)

Input

Required:

Optional:

  • name — full name if known (improves match rate)

Workflow

Step 1: Extract Domain

Extract the domain from the email address. Example: [email protected] -> domain: acme.com

Step 2: Run Sixtyfour Enrichment (parallel)

Fire both calls simultaneously. These are the primary data sources.

Enrich Lead ($0.10):

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"sixtyfour","path":"/enrich-lead"}'
  "lead_info": {
    "email": "{email}",
    "first_name": "{first_name_if_known}",
    "last_name": "{last_name_if_known}",
    "company": "{company_name_if_known}",
    "domain": "{domain}"
  },
  "struct": {
    "full_name": "Full legal name of this person",
    "first_name": "First name",
    "last_name": "Last name",
    "title": "Current job title at their company",
    "linkedin_url": "LinkedIn profile URL (full URL starting with https://linkedin.com/in/)",
    "city": "City where the person is located",
    "state": "State or region where the person is located",
    "country": "Country where the person is located"
  }
}'

Enrich Company ($0.10):

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"sixtyfour","path":"/enrich-company"}'
  "target_company": {
    "domain": "{domain}"
  },
  "struct": {
    "company_name": "Official company name",
    "description": "One-paragraph description of what the company does",
    "linkedin_url": "LinkedIn company page URL (full URL starting with https://linkedin.com/company/)",
    "hq_city": "Headquarters city",
    "hq_state": "Headquarters state or region",
    "hq_country": "Headquarters country",
    "employee_count": "Approximate number of employees (number only)",
    "founded_year": "Year the company was founded (number only)",
    "total_funding_amount_usd": "Total funding raised in USD (number only, no $ sign)",
    "latest_funding_date": "Date of most recent funding round (YYYY-MM-DD format)",
    "latest_funding_stage": "Stage of most recent funding round (e.g., Series A, Series B, Seed)",
    "latest_funding_amount_usd": "Amount raised in most recent round in USD (number only)",
    "is_ai_company": "true or false - does this company build or primarily use AI/ML technology?",
    "ai_evidence": "Brief explanation of why this is or is not an AI company",
    "is_b2b_saas": "true or false - is this a B2B SaaS company?",
    "b2b_evidence": "Brief explanation of why this is or is not B2B SaaS"
  }
}'

Record the status, latency, and any errors for both calls.

Step 3: Fallback — Apollo Person Match (conditional)

ONLY run if Sixtyfour /enrich-lead did NOT return a LinkedIn URL.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"apollo","path":"/api/v1/people/match"}'
  "email": "{email}",
  "reveal_personal_emails": true
}'

Cost: $0.01. Extract linkedin_url, and also grab name, title, organization as cross-reference data.

Step 4: Fallback — Apollo Organization Enrich (conditional)

ONLY run if Sixtyfour /enrich-company did NOT return funding data (total_funding_amount_usd is null/empty).

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"apollo","path":"/api/v1/organizations/enrich","query":{"domain":"{domain}"}}'

Cost: $0.01. Extract funding events, total funding, latest funding stage, and latest funding amount.

Step 5: Compile Results

Merge all data into the output format below. Apply these rules:

  • Sixtyfour is primary — use its data first for all fields
  • Apollo is fallback — only used to fill gaps Sixtyfour missed
  • Source tracking — for each field, note whether it came from sixtyfour or apollo
  • Confidence:
  • high — Sixtyfour returned the field directly
  • medium — Apollo fallback provided the field
  • low — field was inferred or partially matched

Output Format

Present the results as a JSON code block:

{
  "person": {
    "full_name": "string",
    "title": "string",
    "linkedin_url": "string",
    "location": {"city": "string", "state": "string", "country": "string"},
    "email_verified": "unknown",
    "confidence": "high | medium | low",
    "source": "sixtyfour | apollo"
  },
  "company": {
    "name": "string",
    "domain": "string",
    "linkedin_url": "string",
    "description": "string",
    "geo": {"city": "string", "state": "string", "country": "string"},
    "employee_count": "number | null",
    "founded_year": "number | null",
    "funding": {
      "total_amount": "number | null",
      "total_amount_printed": "string | null",
      "latest_round_date": "string | null",
      "latest_round_stage": "string | null",
      "latest_round_amount": "number | null",
      "rounds": [],
      "confidence": "high | medium | low"
    },
    "classification": {
      "is_ai": {"value": true, "confidence": "high | medium | low", "evidence": ["string"]},
      "is_b2b_saas": {"value": true, "confidence": "high | medium | low", "evidence": ["string"]}
    },
    "buying_signals": {
      "has_enterprise_plan": null,
      "has_self_serve": null,
      "hiring_enterprise_reps": null,
      "website_traffic_rank": null,
      "github_stars": null,
      "tech_stack": null
    },
    "confidence": "high | medium | low",
    "source": "sixtyfour | apollo | merged"
  },
  "meta": {
    "total_cost": "$0.XX",
    "api_calls": [],
    "phases_run": [1, 2],
    "enrichment_timestamp": "ISO datetime"
  }
}

Error Visibility

Track EVERY API call in the meta.api_calls array:

{
  "api": "sixtyfour",
  "endpoint": "/enrich-lead",
  "status": "success | partial | error",
  "cost": "$0.10",
  "latency_ms": 35000,
  "fields_returned": ["full_name", "title", "linkedin_url"],
  "fields_missing": ["city"],
  "error": null
}

If an API call fails, returns empty data, or times out, include it in the api_calls array with status='error' and a clear error message. Never silently skip failures.

Cost Tracking

Sum all API call costs and report in meta.total_cost:

  • Sixtyfour /enrich-lead: $0.10
  • Sixtyfour /enrich-company: $0.10
  • Apollo /api/v1/people/match: $0.01 (only if used)
  • Apollo /api/v1/organizations/enrich: $0.01 (only if used)

Example

Input: [email protected]

Expected flow:

  • Extract domain: acme.com
  • Fire Sixtyfour /enrich-lead and /enrich-company in parallel
  • Check if LinkedIn URL returned — if not, call Apollo /people/match
  • Check if funding data returned — if not, call Apollo /organizations/enrich
  • Compile and output JSON with all fields, error visibility, and cost

Tips

  • Sixtyfour takes 30-60s per call — be patient, do NOT timeout early
  • If Sixtyfour returns partial data, still use what it returned and fill gaps with Apollo
  • AI/B2B classification comes from Sixtyfour's web research — it reads the company website
  • The struct field in Sixtyfour tells the AI agent exactly what to research — modify fields there if you need different data points

Other skills for the same job

different authors, same section of the catalogue
Meeting Insights Analyzer
by frostant
×8

Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.

3k tokens
Slack Gif Creator
by JayZeeDesign
×7

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".

53k tokens scripts
Developer Growth Analysis
by frostant
×6

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

4k tokens
Slack Gif Creator
by anthropics
vendor ×5

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.

11k tokens scripts
Skill Share
by frostant
×4

A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.

728 tokens
Electron
by vercel-labs
vendor ×2

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

2k tokens
Notion Meeting Intelligence
by openai
vendor ×2

Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

18k tokens
Daily Meeting Update
by softaworks
×2

Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare for meeting', 'morning update', or 'team sync'. Pulls activity from GitHub, Jira, and Claude Code session history. Conducts 4-question interview (yesterday, today, blockers, discussion topics) and generates formatted Markdown update.

8k tokens scripts

How to use it

Copy the folder

Take gooseworks-ai/gtm-enrichment-deep from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference npx. Without those the skill loads but fails at the first command.