Skip to main content
One global context file per company. Every other GTM skill reads from this file for voice, value prop, ICP, win cases, proof points, and campaign learnings.

​
Trigger Phrases

“company context”, “update context”, “build context”, “ICP”, “win cases”, “campaign history”, “call recording”, “feedback loop”, “DNC list”

​
Context File Location

claude-code-gtm/context/{company}_context.md
Single file per company, not per-campaign. All skills reference this path.

​
Modes

​
Mode 1: Create

Use when no context file exists yet. Walk the user through each section.
1

Check for existing context

Check if claude-code-gtm/context/{company}_context.md exists.
2

Gather sections

If not, ask the user for each section (one at a time or in bulk):
SectionWhat to askExample
What We DoProduct one-liner, core value prop, email-safe value prop, key lingo, key numbersProduct description + quantifiable claims
VoiceSender name, tone, language level, hard constraints, scope boundariesWho emails come from, how they sound
ICPCustomer profiles, company sizes, roles, geographiesTarget profiles with size ranges and regions
Win CasesPast customers, why they bought, what workedConcrete outcomes with metrics
Proof LibraryPre-written PS sentences for emails, mapped to audience and hypothesisReady-to-paste proof points
Campaign HistoryPast campaigns: vertical, list size, reply rate, learnings(empty on first run)
Active HypothesesCurrent working hypotheses about what resonatesPain points validated by campaign data
Do Not ContactDomains to skip in all future listsCompetitors, partners, opt-outs
3

Write the file

Write the file using the context schema structure.

​
Key sections to get right

What We Do - must include:
  • Product one-liner
  • Core value prop (internal version, can use any language)
  • Email-safe value prop (outreach-friendly version of the value prop)
  • Key numbers (quantifiable claims - database size, speed benchmarks, coverage stats)
  • Key lingo (internal terms and definitions)
Voice - must include:
  • Sender name and company (who emails come from)
  • Tone (1 sentence)
  • Language level
  • Hard constraints (numbered list of rules)
  • Scope boundaries (what the product IS and ISN’T)
Proof Library - must include:
  • Full PS sentences ready to paste into emails
  • Each mapped to: best audience, best hypothesis, source win case
  • Every proof point must trace back to a real win case
  • Write the sentence as it would appear in the email (including “PS.”)

​
Mode 2: Update

Use when context file exists and user wants to add or modify a section.
1

Read existing context

Read the existing context file.
2

Ask what to update

Common updates:
  • Add a new win case
  • Add a campaign result
  • Update ICP based on new learnings
  • Add domains to DNC
  • Revise or add hypotheses
  • Add or update proof points in the Proof Library
  • Update voice rules
  • Update key numbers (e.g., database size grew)
3

Append to section

Append to the relevant section. Never overwrite existing entries - add new rows to tables, new bullets to lists.

​
Mode 3: Call Recording Capture

Use when the user pastes a call transcript or meeting notes.
1

Read the transcript

Read the transcript or meeting notes.
2

Extract and categorize signals

  • ICP signals - who was on the call, their role, company size, what they care about
  • Win case data - what resonated, what they said about their current workflow, pain points confirmed
  • Proof point candidates - specific results or quotes that could become Proof Library entries
  • DNC signals - any companies or domains mentioned as off-limits
  • Hypothesis validation - which existing hypotheses were confirmed or refuted
  • Voice feedback - any reaction to tone, language, or positioning that should update Voice rules
3

Present extracted signals

Present extracted signals to the user for confirmation.
4

Update context file

Update the context file with confirmed signals.

​
Mode 4: Feedback Loop

Use when importing campaign results from your email sequencer (e.g. Instantly) or manual tracking.
1

Read campaign results

Read campaign results (CSV, pasted data, or email sequencer export e.g. Instantly).
2

Extract metrics

  • Campaign name, vertical, list size
  • Open rate, reply rate, positive reply rate
  • Top-performing hypotheses (which P1 angles got replies)
  • Patterns in positive vs negative replies
3

Add to Campaign History

Add a new row to the ## Campaign History table.
4

Update Active Hypotheses

Update based on results:
  • Promote hypotheses with high reply rates to Validated
  • Demote hypotheses that didn’t resonate to Retired
  • Note any new hypotheses suggested by reply patterns
5

Update Proof Library

Update if campaign results surfaced new proof points:
  • New win cases → write new PS sentences
  • Existing proof points that didn’t resonate → add notes or remove

​
Cross-Skill References

This context file is consumed by:
  • hypothesis-building - reads ICP, Win Cases, and product value prop to generate pain hypotheses
  • email-prompt-building - reads Voice, What We Do, Proof Library, and Active Hypotheses to build prompt templates
  • email-generation - reads the prompt template (which was built from this file)
  • list-building - reads ICP and Win Cases for seed companies
  • market-research - reads ICP and hypotheses for research scope
  • enrichment-design - reads hypotheses for segmentation column design
  • list-segmentation - reads hypotheses for tiering logic
  • email-response-simulation - reads Voice rules to constrain rewrites
  • campaign-sending - reads DNC list for exclusions

​
DNC List Population

When building the Do Not Contact section, offer to:
  1. Run an Extruct search for competitors to auto-populate
  2. Accept a CSV of existing customers/partners

​
Example Context Structure

# Company Context: [Company Name]

## What We Do

**One-liner:** [Product description in one sentence]

**Core value prop:** [Internal version]

**Email-safe value prop:** [Outreach-friendly version]

**Key numbers:**
- [Metric 1]: [Value]
- [Metric 2]: [Value]

**Key lingo:**
- [Term]: [Definition]

## Voice

**Sender:** [Name, Company]

**Tone:** [One sentence]

**Language level:** [Technical/Business/Casual]

**Hard constraints:**
1. [Rule 1]
2. [Rule 2]

**Scope boundaries:**
- IS: [What the product does]
- ISN'T: [What it doesn't do]

## ICP

| Profile | Company Size | Roles | Geography |
|---------|-------------|-------|----------|
| [Profile 1] | [Range] | [Roles] | [Regions] |

## Win Cases

| Company | Why They Bought | Outcome |
|---------|----------------|----------|
| [Company] | [Trigger] | [Result] |

## Proof Library

| PS Sentence | Best Audience | Best Hypothesis | Source Win Case |
|------------|--------------|----------------|----------------|
| PS. [Sentence] | [Audience] | [Hypothesis] | [Company] |

## Campaign History

| Campaign | Vertical | List Size | Reply Rate | Learnings |
|---------|---------|----------|-----------|----------|
| [Name] | [Vertical] | [Count] | [%] | [Notes] |

## Active Hypotheses

| Hypothesis | Status | Evidence |
|-----------|--------|----------|
| [Name] | [Validated/Testing/Retired] | [Data] |

## Do Not Contact

- competitor1.com
- partner1.com

Build docs developers (and LLMs) love

Get started for freeTalk to us