Persistent intelligence layer that accumulates deal knowledge, competitive intel, product context, and team patterns over time — making every other skill smarter with use. This skill should ALWAYS be checked at the start of any GTM-related task. It reads from and writes to a structured knowledge base so that insights from one conversation carry into the next. Use this skill on every interaction that involves sales, marketing, CS, partnerships, or RevOps context. Also trigger proactively when the user shares deal outcomes, competitive intel, product updates, rep feedback, or customer insights — capture it even if they didn't ask you to.
Accumulates and applies sales, marketing, and competitive intelligence across all GTM interactions to build institutional knowledge.
/plugin marketplace add https://www.claudepluginhub.com/api/plugins/jbalbu01-sales-enablement-2/marketplace.json/plugin install jbalbu01-sales-enablement-2@cpd-jbalbu01-sales-enablement-2This skill inherits all available tools. When active, it can use any tool Claude has access to.
The intelligence backbone of the sales enablement system. Every other skill reads from this memory and writes back to it, creating a compounding loop where the system gets smarter with every deal, call, and interaction.
Traditional enablement creates content and hopes people use it. This system learns from what actually happens in the field — which talk tracks win deals, which discovery questions reveal the most, which objections trip reps up, which competitors keep winning in specific segments — and feeds those insights back into every future interaction.
The result: a plugin that's meaningfully better on day 90 than day 1.
┌─────────────────────────────────────────────────────────────────┐
│ GTM MEMORY │
├─────────────────────────────────────────────────────────────────┤
│ KNOWLEDGE STORE (persists across sessions) │
│ 📁 memory/ │
│ ├── product.md — Product details, features, pricing │
│ ├── competitors.md — Competitive landscape + intel log │
│ ├── icp.md — ICP definition + refinements over time │
│ ├── deal-patterns.md — Win/loss patterns, what works │
│ ├── objections.md — Objection library with effectiveness │
│ ├── team.md — Rep profiles, strengths, development │
│ ├── content-registry.md — All enablement assets + freshness │
│ └── changelog.md — All updates with timestamps │
├─────────────────────────────────────────────────────────────────┤
│ WORKING MEMORY (CLAUDE.md — always in context) │
│ • Current priorities and focus areas │
│ • Recent insights not yet integrated │
│ • Active deals requiring attention │
│ • Stale content flags │
│ • Cross-references to memory/ files │
├─────────────────────────────────────────────────────────────────┤
│ SUPERCHARGED (when you connect your tools) │
│ + ~~CRM: Deal outcomes auto-seeding win/loss patterns │
│ + ~~CRM: Contact roles populating buyer committee knowledge │
│ + ~~CRM: Company profiles enriching ICP definitions │
│ + ~~conversation intelligence (Gong): Call patterns & talk tracks│
│ + ~~conversation intelligence (Gong): Objection frequency data │
│ + ~~conversation intelligence (Gong): Discovery question library│
│ + ~~competitive intel (ZoomInfo): Competitor profiles & updates │
│ + ~~competitive intel (ZoomInfo): Tech stack intelligence │
│ + ~~data enrichment (Clay): Company signals & enrichment │
│ + ~~data enrichment (LinkedIn): Stakeholder career movements │
│ + ~~chat: Field feedback and tribal knowledge capture │
│ + ~~calendar/email: Engagement patterns and correspondence │
└─────────────────────────────────────────────────────────────────┘
CRITICAL: GTM Memory is dramatically more valuable when seeded from real data. Before relying solely on user-provided context, pull from connected tools to populate memory files with evidence-based intelligence.
Check if you have access to CRM tools (look for tools containing search_crm_objects, get_crm_objects, or similar).
If CRM tools ARE available:
dealname, amount, dealstage, closedate, createdate, pipeline, hubspot_owner_id, dealtype, description, closed_lost_reason, closed_won_reasonname, industry, numberofemployees, annualrevenue, descriptionsearch_owners to list all reps.
firstname, lastname, jobtitleCheck if you have access to Gong tools (look for tools prefixed with gong_).
If Gong tools ARE available:
gong_search_calls with common objection keywords.
gong_get_call_stats for top performers.
gong_get_transcript on won-deal calls.
ZoomInfo (if available):
zoominfo_search_company on known competitors.
zoominfo_search_company on best customer profiles.
Clay (if available):
clay_enrich_company on competitors.
LinkedIn (if available):
linkedin_get_profile for known champions and buyers.
linkedin_search_companies for competitor updates.
If chat tools are available (slack_search_public, slack_search_public_and_private):
If calendar/email tools are available:
"Memory seed/refresh complete. Auto-populated from connected tools: [If CRM:] [N] deals analyzed — [X]% win rate, $[X] avg deal size, top loss reasons: [reasons]. ICP: [profile]. [N] reps profiled. [If Gong:] [N] objections catalogued from [N] calls. Top-performer patterns identified. [If ZoomInfo:] [N] competitor profiles enriched. [If Slack:] [N] tribal knowledge items captured. Memory files updated — the system is now [X]% richer than last session."
After the auto-pull, capture what tools can't provide:
Write ALL new intelligence into the appropriate memory files. Use structured formats defined in the Memory File Formats section below. Always append new data with timestamps — never overwrite historical entries. Cite sources: "Per CRM ([N] deals):", "Per Gong:", "Per ZoomInfo:", "Per Slack:", "User reported:"
memory/changelog.md documenting all updatesCLAUDE.md working memory with current priorities and fresh insightsBefore generating any enablement content, check relevant memory files:
competitors.md + deal-patterns.md + objections.mdicp.md + deal-patterns.md + team.md (for rep's skill level)team.md (rep profile) + deal-patterns.mdproduct.md + icp.md + competitors.mdCLAUDE.md for current context and prioritiesThis means a battle card built on day 90 incorporates 90 days of deal outcomes, competitive encounters, and field feedback — not just what the user told you in this one conversation.
After completing any GTM task, capture new intelligence:
Did we learn something new about:
✓ A competitor? → Update competitors.md
✓ What works in deals? → Update deal-patterns.md
✓ An objection and what beats it? → Update objections.md
✓ A rep's skill gap or strength? → Update team.md
✓ The product or pricing? → Update product.md
✓ The ICP or personas? → Update icp.md
✓ A new content asset was created? → Update content-registry.md
Always → Add timestamped entry to changelog.md
When the user shares information casually — "we lost the Acme deal to Competitor X because of their API" — capture it even if they didn't ask you to. Say: "Got it — I've logged that competitive loss pattern. This will inform future battle cards and deal reviews."
# Product Knowledge
**Last Updated:** [Date]
## Product Overview
[What we sell, in one paragraph]
## Key Features
| Feature | Description | Differentiator? |
|---------|-------------|----------------|
| ... | ... | Yes/No |
## Pricing
[Current pricing model and tiers]
## Recent Changes
| Date | Change | Impact on Selling |
|------|--------|------------------|
| ... | ... | ... |
## Value Propositions (Ranked by Effectiveness)
1. [VP that wins most often] — Win rate: [X]%
2. [VP2] — Win rate: [X]%
# Competitive Intelligence
**Last Updated:** [Date]
## [Competitor A]
**Last Intel:** [Date]
**Win Rate Against:** [X]%
**Key Differentiators:** [Theirs vs ours]
### Recent Intel
| Date | Source | Intel | Impact |
|------|--------|-------|--------|
| ... | Deal: [Name] | [What we learned] | [Updated battle card?] |
### What Beats Them
[Patterns from won deals]
### Where They Beat Us
[Patterns from lost deals]
# Deal Patterns
**Last Updated:** [Date]
**Deals Analyzed:** [N]
## Win Patterns
1. [Pattern] — Confidence: [High/Med] — Evidence: [N] deals
2. ...
## Loss Patterns
1. [Pattern] — Confidence: [High/Med] — Evidence: [N] deals
2. ...
## Stage Conversion Insights
| Stage Transition | Success Factor | Failure Factor |
|-----------------|----------------|----------------|
| Discovery → Demo | [What works] | [What fails] |
| Demo → Proposal | ... | ... |
## Emerging Trends
[New patterns not yet confirmed]
# Content Registry
All enablement assets with freshness tracking.
| Asset | Type | Created | Last Updated | Freshness | Trigger for Refresh |
|-------|------|---------|-------------|-----------|-------------------|
| [Battle Card: CompA] | battle-card | [Date] | [Date] | 🟢🟡🔴 | [Competitor news, lost deal] |
| [Playbook: Enterprise] | playbook | [Date] | [Date] | 🟢🟡🔴 | [Process change, win rate drop] |
When used for the first time:
memory/ directory and seed each file with initial contextCLAUDE.md with working memory summarychangelog.mdOn subsequent uses:
CLAUDE.md first (always in context)User interaction
↓
Read relevant memory → Better context → Higher quality output
↓
Capture new insights from the interaction
↓
Update memory files
↓
Next interaction starts with richer context
↓
Repeat (system gets smarter with every use)
This is what Matthew means by "infrastructure that compounds" — the plugin isn't just generating content, it's building an institutional knowledge base that makes every future interaction better.
Every other skill in this plugin reads from and writes to GTM Memory:
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.