Agent skill

CRM Automation

by aAAaqwq in aAAaqwq/AGI-Super-Team

CRM workflow automation for HubSpot, Salesforce, Pipedrive - lead management, deal tracking, and multi-CRM synchronization

MITAuto-check passedSales & Support

Install CRM Automation

skills CLI
$ npx skills add aAAaqwq/AGI-Super-Team --skill crm-automation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aAAaqwq/AGI-Super-Team crm-automation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/crm-automation .claude/skills/crm-automation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
crm-automation
GitHub stars
105
Used in
1 other repo
Token cost
~2.9k tokens
SKILL.md length
113 words
Files
1
Skills in repo
167
Repo updated
First seen
Licence
MIT

At a glance

CRM workflow automation for HubSpot, Salesforce, Pipedrive - lead management, deal tracking, and multi-CRM synchronization

  • Works in 3 steps: Lead Capture → Enrichment → Assignment → Deal Stage Automation → Multi-CRM Synchronization
  • Tasks that involve CRM management
  • SKILL.md covers Overview, Core Workflow Patterns, Lead Scoring Model and Automated Sequences, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

CRM Automation is an agent skill from aAAaqwq/AGI-Super-Team. CRM workflow automation for HubSpot, Salesforce, Pipedrive - lead management, deal tracking, and multi-CRM synchronization

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support, covering CRM management. It works with HubSpot, Salesforce and n8n. The repository describes itself as: An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters. The licence is MIT.

When your agent uses it

  • Tasks that involve CRM management

Example prompts

  • “/crm-automation”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Lead Capture → Enrichment → Assignment
  2. Deal Stage Automation
  3. Multi-CRM Synchronization

What it can do on your machine

Read from SKILL.md and the folder at commit 7cefd81. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml, javascript and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CRM Automation loads about 2.9k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 113 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aAAaqwq/AGI-Super-Team at commit 7cefd81, republished under its MIT licence (© aAAaqwq). 113 words, ~2,944 tokens.

Download SKILL.mdSave it as .claude/skills/crm-automation/SKILL.md (or your agent's skills folder).
name
crm-automation
description
CRM workflow automation for HubSpot, Salesforce, Pipedrive - lead management, deal tracking, and multi-CRM synchronization
version
1.0.0
author
claude-office-skills
license
MIT
category
sales
tags
crm, hubspot, salesforce, automation, lead-management
department
Sales
models.recommended
claude-sonnet-4, claude-opus-4
models.compatible
gpt-4, gpt-4o
mcp.server
crm-mcp
mcp.tools
hubspot_create_contact, hubspot_update_deal, salesforce_query, pipedrive_sync, enrichment_api

CRM Automation

Automate CRM workflows for HubSpot, Salesforce, and Pipedrive including lead management, deal tracking, pipeline automation, and multi-CRM synchronization. Based on n8n workflow templates.

Overview

This skill covers:

  • Lead capture and enrichment automation
  • Deal stage progression workflows
  • Multi-CRM data synchronization
  • Automated follow-up sequences
  • Sales analytics and reporting

Core Workflow Patterns

1. Lead Capture → Enrichment → Assignment
┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│ Lead Source │───▶│ Enrich Data │───▶│ Score Lead  │───▶│ Route to    │
│ (Form/API)  │    │ (Clearbit)  │    │ (AI/Rules)  │    │ Sales Rep   │
└─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘
                                                                │
                         ┌─────────────┐    ┌─────────────┐    │
                         │ Start       │◀───│ Create in   │◀───┘
                         │ Sequence    │    │ CRM         │
                         └─────────────┘    └─────────────┘

n8n Configuration:

yaml
workflow: "Lead Capture to CRM"

trigger:
  - type: webhook
    event: form_submission
    source: [website, landing_page, calendly]

steps:
  1. capture_lead:
      fields: [email, name, company, phone, source]
  
  2. enrich_data:
      provider: clearbit
      lookup_by: email
      append: [company_size, industry, title, linkedin]
  
  3. score_lead:
      model: ai_scoring  # or rule-based
      factors:
        - company_size: {1-50: 10, 51-200: 20, 201+: 30}
        - industry_fit: {high: 30, medium: 20, low: 10}
        - title_seniority: {c-level: 30, director: 20, manager: 10}
      threshold: 50  # MQL threshold
  
  4. route_lead:
      rules:
        - if: score >= 80 AND industry == "tech"
          assign_to: "Enterprise Team"
        - if: score >= 50
          assign_to: "SMB Team"
        - else:
          assign_to: "Marketing Nurture"
  
  5. create_in_crm:
      platform: hubspot
      object: contact
      properties:
        email: "{email}"
        firstname: "{first_name}"
        company: "{company}"
        lead_score: "{score}"
        lead_source: "{source}"
  
  6. start_sequence:
      if: score >= 50
      sequence: "New Lead Welcome"
      delay: 1_hour

2. Deal Stage Automation
yaml
workflow: "Deal Stage Progression"

trigger:
  - type: hubspot_deal_updated
    property: dealstage

stages:
  appointment_scheduled:
    actions:
      - create_task: "Prepare for meeting"
        due: 1_day_before_meeting
      - notify_slack: "#sales-pipeline"
      - update_property: last_activity_date
  
  qualified_to_buy:
    actions:
      - create_task: "Send proposal"
        due: 3_days
      - notify_manager: true
      - add_to_forecast: true
  
  presentation_scheduled:
    actions:
      - create_task: "Prepare demo environment"
      - send_reminder: 1_hour_before
      - log_activity: "Presentation scheduled"
  
  contract_sent:
    actions:
      - set_close_date: 14_days_from_now
      - create_task: "Follow up on contract"
        due: 7_days
      - notify_legal: if amount > 50000
  
  closed_won:
    actions:
      - notify_slack: "#wins"
      - trigger_onboarding: true
      - update_forecast: remove
      - celebrate: confetti  # Slack celebration
  
  closed_lost:
    actions:
      - log_loss_reason: required
      - add_to_nurture: true
      - schedule_reengagement: 90_days

3. Multi-CRM Synchronization
yaml
workflow: "HubSpot + Salesforce + Pipedrive Sync"

sync_rules:
  contacts:
    master: hubspot
    sync_to: [salesforce, pipedrive]
    frequency: real_time
    fields:
      - email (unique_key)
      - name
      - company
      - phone
      - owner
    conflict_resolution: most_recent_wins
    deduplication: 
      provider: openai
      similarity_threshold: 0.85
  
  deals:
    master: salesforce
    sync_to: [hubspot, pipedrive]
    frequency: every_15_minutes
    field_mapping:
      salesforce.Opportunity.Amount → hubspot.deal.amount
      salesforce.Opportunity.CloseDate → hubspot.deal.closedate
      salesforce.Opportunity.StageName → hubspot.deal.dealstage
  
  activities:
    aggregate_to: google_sheets
    types: [calls, emails, meetings, notes]
    columns: [date, contact, type, summary, outcome]

n8n Implementation:

javascript
// Multi-CRM Sync Node
{
  "nodes": [
    {
      "name": "Get HubSpot Contacts",
      "type": "n8n-nodes-base.hubspot",
      "parameters": {
        "operation": "getAll",
        "limit": 100,
        "additionalFields": {
          "propertiesToInclude": ["email", "firstname", "lastname", "company"]
        }
      }
    },
    {
      "name": "Get Salesforce Contacts",
      "type": "n8n-nodes-base.salesforce",
      "parameters": {
        "operation": "getAll",
        "sobject": "Contact"
      }
    },
    {
      "name": "Deduplicate with OpenAI",
      "type": "n8n-nodes-base.openAi",
      "parameters": {
        "operation": "message",
        "model": "gpt-4",
        "prompt": "Compare these contacts and identify duplicates: {{$json}}"
      }
    },
    {
      "name": "Sync to Master Sheet",
      "type": "n8n-nodes-base.googleSheets",
      "parameters": {
        "operation": "append",
        "sheetId": "your-sheet-id"
      }
    }
  ]
}

Lead Scoring Model

Rule-Based Scoring
yaml
lead_score_rules:
  demographic:
    job_title:
      - C-Level|VP|Director: +30
      - Manager|Head: +20
      - Individual Contributor: +10
    
    company_size:
      - 1-50: +10
      - 51-200: +20
      - 201-1000: +25
      - 1000+: +30
    
    industry:
      - Technology|SaaS: +30
      - Finance|Healthcare: +25
      - Manufacturing|Retail: +15
  
  behavioral:
    website_visits:
      - 1-2: +5
      - 3-5: +10
      - 6+: +20
    
    content_downloads:
      - Whitepaper: +15
      - Case Study: +20
      - Pricing Page: +25
    
    email_engagement:
      - Opened: +5
      - Clicked: +10
      - Replied: +20

thresholds:
  - MQL: 50
  - SQL: 75
  - Hot Lead: 90
AI-Based Scoring
yaml
ai_scoring_model:
  provider: openai
  prompt: |
    Score this lead from 0-100 based on:
    - Fit with our ICP (ideal customer profile)
    - Buying intent signals
    - Budget authority
    - Timeline urgency
    
    Lead Data: {lead_data}
    ICP: B2B SaaS companies, 50-500 employees, Series A+
    
    Return JSON: {"score": X, "reasoning": "...", "next_action": "..."}

Automated Sequences

Sequence 1: New Lead Welcome
yaml
sequence: "New Lead Welcome"
trigger: lead_created AND score >= 50

steps:
  - day_0:
      type: email
      template: "welcome_intro"
      subject: "Welcome to {Company} - Here's what's next"
  
  - day_2:
      type: email
      template: "value_prop"
      subject: "How {Similar_Company} achieved {Result}"
      condition: not_replied
  
  - day_4:
      type: task
      action: "LinkedIn connection request"
      assign_to: owner
  
  - day_7:
      type: email
      template: "case_study"
      subject: "Quick case study for {Lead_Company}"
      condition: not_replied
  
  - day_10:
      type: email
      template: "meeting_request"
      subject: "15 min to discuss {Pain_Point}?"
      include: calendly_link
  
  - day_14:
      type: task
      action: "Phone call attempt"
      assign_to: owner
      condition: not_responded
Sequence 2: Deal Follow-Up
yaml
sequence: "Proposal Follow-Up"
trigger: deal_stage == "contract_sent"

steps:
  - day_3:
      type: email
      template: "contract_check_in"
      subject: "Any questions about the proposal?"
  
  - day_7:
      type: task
      action: "Phone call - contract follow-up"
  
  - day_10:
      type: email
      template: "deadline_reminder"
      subject: "Pricing valid until {deadline}"
      condition: not_responded
  
  - day_14:
      type: alert
      notify: sales_manager
      message: "Deal stuck in contract stage"

Integration Recipes

Recipe 1: Calendly → HubSpot
yaml
trigger: calendly.booking_created

actions:
  1. search_contact:
      hubspot.search: email == calendly.invitee_email
  
  2. create_or_update:
      if: contact_exists
        hubspot.update_contact:
          last_meeting_booked: calendly.start_time
      else:
        hubspot.create_contact:
          email: calendly.invitee_email
          firstname: calendly.invitee_name
          lifecycle_stage: "salesqualifiedlead"
  
  3. create_meeting:
      hubspot.create_engagement:
        type: MEETING
        scheduled_time: calendly.start_time
        title: calendly.event_name
  
  4. notify:
      slack.send:
        channel: "#sales"
        message: "Meeting booked: {name} at {time}"
Recipe 2: LinkedIn → HubSpot
yaml
trigger: linkedin.connection_accepted

actions:
  1. enrich:
      linkedin.get_profile: connection_id
  
  2. create_contact:
      hubspot.create:
        email: linkedin.email
        firstname: linkedin.first_name
        lastname: linkedin.last_name
        jobtitle: linkedin.title
        company: linkedin.company
        linkedin_url: linkedin.profile_url
        lead_source: "LinkedIn"
  
  3. add_to_sequence:
      if: title contains ["CEO", "CTO", "VP"]
      sequence: "LinkedIn C-Level Outreach"

Reporting Templates

Weekly Sales Report
markdown
# Sales Pipeline Report - Week {week_number}

## Pipeline Summary
| Stage | Deals | Value | Change |
|-------|-------|-------|--------|
| New | 15 | $150K | +5 |
| Qualified | 8 | $120K | +2 |
| Proposal | 5 | $85K | -1 |
| Negotiation | 3 | $45K | +1 |
| **Total Pipeline** | **31** | **$400K** | **+7** |

## This Week's Activity
- New leads: 45
- Meetings held: 12
- Proposals sent: 4
- Deals closed: 2 ($35K)

## Team Performance
| Rep | Meetings | Proposals | Closed |
|-----|----------|-----------|--------|
| Alice | 5 | 2 | 1 |
| Bob | 4 | 1 | 1 |
| Carol | 3 | 1 | 0 |

## Forecast
- Commit: $45K (3 deals)
- Best Case: $85K (5 deals)
- Pipeline: $400K (31 deals)

## Actions Needed
- [ ] Follow up on 3 stale deals (>14 days no activity)
- [ ] Schedule demo for Enterprise Lead X
- [ ] Send revised proposal to Company Y

Best Practices

Data Hygiene
yaml
data_hygiene_rules:
  - deduplicate: weekly
    method: email_match + company_fuzzy_match
  
  - validate_emails: on_create
    action: remove_invalid
  
  - enrich_missing: daily
    fields: [company, title, linkedin]
  
  - archive_stale: monthly
    criteria: no_activity > 180_days
    action: move_to_archive
Security
yaml
security_practices:
  - api_keys: rotate_quarterly
  - access_control: role_based
  - audit_log: all_changes
  - pii_handling: encrypt_at_rest
  - gdpr_compliance: consent_tracking

CRM Automation Skill - Part of Claude Office Skills

© aAAaqwq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/crm-automation of aAAaqwq/AGI-Super-Team.

Open the folder on GitHubat commit 7cefd81

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in aAAaqwq/AGI-Super-Team, which our catalogue first saw on October 7, 2026.

Compare with similar skills

CRM Automation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

CRM Automation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CRM Automation this skillaAAaqwq/AGI-Super-Team1051 repos~2.9kAutomated safety check: PassMIT
Google Maps Exportgmapsscraper/google-maps-agent-skills132—~1.2kAutomated safety check: PassMIT
Pipeline Reviewgooseworks-ai/goose-skills1.2k1 repos~6.9kAutomated safety check: PassMIT
Hubspot Bulk Migrationjeremylongshore/tons-of-skills-marketplace2.8k—~3.9kAutomated safety check: PassMIT
CRM Integrationmanojbajaj95/claude-gtm-plugin105—~3.8kAutomated safety check: PassMIT
CRMmagnus919/agent-skills115—~2.1kAutomated safety check: PassMIT

Similar skills

  • Google Maps Export

    gmapsscraper/google-maps-agent-skills

    Export Google Maps business data to CSV, JSON, or CRM format (HubSpot, Pipedrive, Salesforce).

    132 GitHub stars~1.2k tokensUpdated 4 mo ago
    Sales & SupportAuto-check passed
  • Pipeline Review

    gooseworks-ai/goose-skills

    Pipeline analysis composite. An agent skill from gooseworks-ai/goose-skills.

    1.2k GitHub starsUsed in 1 repo~6.9k tokens
    Sales & SupportAuto-check passed
  • Hubspot Bulk Migration

    jeremylongshore/tons-of-skills-marketplace

    Bulk-migrate CRM data into HubSpot from Salesforce, Pipedrive, or Copper — or export off HubSpot — with field mapping, ID continuity, association re-linking, dedup safety, rate-limit budgeting, and…

    2.8k GitHub stars~3.9k tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • CRM Integration

    manojbajaj95/claude-gtm-plugin

    CRM integration patterns for Close CRM, HubSpot, and Salesforce.

    105 GitHub stars~3.8k tokensUpdated 23 days ago
    Sales & SupportAuto-check passed
  • CRM

    magnus919/agent-skills

    Operate HubSpot CRM from a terminal or agent: list and search contact records, view deal pipeline stages, and — with explicit confirmation — move deals between stages, backed by a bundled crm-cli…

    115 GitHub stars~2.1k tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Fathom Core Workflow B

    jeremylongshore/tons-of-skills-marketplace

    Sync Fathom meeting data to CRM and build automated follow-up workflows.

    2.8k GitHub stars~871 tokensUpdated yesterday
    Sales & SupportAuto-check passed

More from aAAaqwq/AGI-Super-Team

All 167 skills in this repo
  • Content Creator

    aAAaqwq/AGI-Super-Team

    Create SEO-optimized marketing content with consistent brand voice.

    105 GitHub starsUsed in 3 repos~1.9k tokens
    Auto-check passed
  • Financial Calculator

    aAAaqwq/AGI-Super-Team

    Advanced financial calculator with future value tables, present value, discount calculations, markup pricing, and compound interest.

    105 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • Bankr Signals

    aAAaqwq/AGI-Super-Team

    Transaction-verified trading signals on Base blockchain. An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub starsUsed in 2 repos~3.3k tokens
    Auto-check passed
  • Erc 8004

    aAAaqwq/AGI-Super-Team

    Register AI agents on Ethereum mainnet using ERC-8004 (Trustless Agents).

    105 GitHub starsUsed in 2 repos~1.2k tokens
    Auto-check passed
  • Frontend Design Ultimate

    aAAaqwq/AGI-Super-Team

    Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed.

    105 GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed
  • Zsxq Smart Publish

    aAAaqwq/AGI-Super-Team

    Publish and manage content on 知识星球 (zsxq.com). An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about CRM Automation

What does CRM Automation do?

CRM workflow automation for HubSpot, Salesforce, Pipedrive - lead management, deal tracking, and multi-CRM synchronization. CRM Automation is an agent skill from aAAaqwq/AGI-Super-Team.

When should I use CRM Automation?

CRM Automation fits situations like: tasks that involve CRM management.

How do I install CRM Automation in Claude Code?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill crm-automation -a claude-code`. Or copy the skill folder (skills/crm-automation in aAAaqwq/AGI-Super-Team) into .claude/skills/crm-automation in your project. Claude Code loads it when a task matches its description.

How do I install CRM Automation in Codex?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill crm-automation -a codex`. Or copy the skill folder (skills/crm-automation in aAAaqwq/AGI-Super-Team) into .agents/skills/crm-automation in your project. Codex loads it when a task matches its description.

Can I use CRM Automation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aAAaqwq/AGI-Super-Team --skill crm-automation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/crm-automation, .gemini/skills/crm-automation, .github/skills/crm-automation and .opencode/skills/crm-automation in your project.

What does CRM Automation need to run?

SKILL.md names no scripts, command-line tools or credentials: CRM Automation is instructions for the agent only.

Does CRM Automation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is CRM Automation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does CRM Automation use?

CRM Automation is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CRM Automation use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to CRM Automation?

Skills that share tags, products or a category with CRM Automation: Google Maps Export (gmapsscraper/google-maps-agent-skills, 132 stars), Pipeline Review (gooseworks-ai/goose-skills, 1.2k stars), Hubspot Bulk Migration (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and CRM Integration (manojbajaj95/claude-gtm-plugin, 105 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CRM Automation?

aAAaqwq (a GitHub user) maintains it in aAAaqwq/AGI-Super-Team, which has 105 GitHub stars. The repository holds 167 skills in this directory. The repository was last updated on October 8, 2026.

Source: aAAaqwq/AGI-Super-Team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.