Voice Of Customer Synthesis logo

Voice Of Customer Synthesis

Community
growthack88
voice-of-customer-synthesis

Turn customer notes, call transcripts, sales feedback, and research into PMM-ready voice-of-customer inputs: pains, triggers, status quo, JTBD, exact language, objections, proof, and messaging implications.

Overview

Publishergrowthack88
Repositorygrowth-marketing-os
Skill namevoice-of-customer-synthesis
Stars
125
Forks
25
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by growthack88 on GitHub. Read the source before you install it.

Installation

Install the Voice Of Customer Synthesis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/growthack88/growth-marketing-os/tree/main/skills/community/voice-of-customer-synthesis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/growthack88/growth-marketing-os.git /tmp/growth-marketing-os
mkdir -p .claude/skills
cp -r /tmp/growth-marketing-os/skills/community/voice-of-customer-synthesis .claude/skills/voice-of-customer-synthesis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Voice Of Customer Synthesis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Voice Of Customer Synthesis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Voice Of Customer Synthesis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Voice of Customer Synthesis

When to use

Use this skill when you have raw customer input and need to turn it into useful product marketing judgment.

Good inputs include:

  • Customer interview notes
  • Sales call transcripts
  • Win/loss notes
  • Support tickets or community threads
  • Customer advisory board notes
  • Gong/Zoom summaries
  • Survey verbatims
  • Founder or sales-team anecdotes that need structure

Use it before positioning, messaging, launch planning, customer stories, sales narratives, website copy, or enablement. Voice of customer is the currency for PMM. Without it you have opinion. With it you can say, "I talked to 10 customers and here's what they said."

Inputs

Ask for or infer the following:

  • Product or company context
  • Target audience or segment
  • Buyer, decision-maker, user, and influencer if known
  • Raw customer notes, transcript excerpts, survey responses, sales notes, or research
  • Business model, ACV, market, or GTM motion if relevant
  • The desired downstream use: positioning, messaging, launch, sales enablement, customer story, or research synthesis

If the input is thin, still synthesize it, but label conclusions by confidence:

  • High confidence: directly supported by multiple customer statements
  • Medium confidence: supported by one clear statement or repeated pattern in weaker notes
  • Low confidence: plausible inference that needs validation

Workflow

1. Separate customer truth from PMM interpretation

Do not blend quotes, facts, and strategy into one mush.

For each finding, distinguish:

  • What the customer actually said
  • What behavior or business reality it points to
  • What PMM should infer from it
  • What still needs validation

2. Identify the audience and buying roles

Clarify who is speaking and who matters in the deal.

Look for:

  • End user pain
  • Decision-maker pain
  • Economic buyer concerns
  • Admin or implementation concerns
  • Champion language
  • Procurement, security, IT, finance, or legal blockers

Do not assume the loudest user is the buyer. Do not assume the buyer is the daily user.

3. Extract the problem before the product

Start with fundamentals:

  • Who is the target audience?
  • What problem do they have?
  • How do they solve it today?
  • Why is the current way painful, risky, slow, expensive, or incomplete?
  • What event makes the problem urgent now?
  • How does the product solve it better?
  • What value is created?
  • How should GTM let the market know?

Do not jump straight to features.

4. Name the status quo

The real competition is often not another vendor. It is the make-do process customers already tolerate.

Look for current alternatives such as:

  • Spreadsheets
  • Email threads
  • Manual handoffs
  • Meetings
  • Internal tools
  • Consultants or agencies
  • Doing nothing
  • Waiting until the pain becomes urgent
  • A partial tool used outside its intended job

Explain why the status quo persists. Common reasons: no owner, low urgency, switching cost, habit, budget timing, fear of implementation, or the pain is invisible until something breaks.

5. Capture the buyer trigger

Find the specific event that made the customer act.

Use this pattern:

  • Situation: the old make-do process
  • Trigger: the specific event that made them act
  • Solution: how the product made the job better
  • Result: the tangible outcome

Triggers can be reactive or proactive.

Reactive buyer moments:

  • A failure, missed deadline, customer escalation, audit, outage, lost deal, cost spike, compliance issue, or executive complaint

Proactive buyer moments:

  • New team, new market, new regulation, growth target, platform change, strategic initiative, budget cycle, or leadership mandate

6. Translate into Jobs To Be Done

Write jobs in plain buyer language.

Format:

  • When [situation/trigger], I need to [job], so I can [desired outcome].

Separate:

  • Functional job: the task they need done
  • Emotional job: the anxiety, confidence, control, or peace of mind they seek
  • Social job: how they need to be perceived by leadership, peers, customers, or their team

7. Pull exact language

Capture short, useful phrases customers actually used.

Prioritize language that is:

  • Specific
  • Emotional
  • Repeated
  • Plain-English
  • A better alternative to internal jargon
  • Close to how a buyer would describe the problem to a peer

Never polish a customer quote until it becomes generic marketing copy. Preserve the edge.

8. Identify objections and proof requirements

Extract what could stop the deal or weaken belief.

Look for objections around:

  • Cost or budget
  • Urgency
  • Implementation effort
  • Trust, risk, security, or compliance
  • Integration fit
  • Data quality
  • Change management
  • Executive buy-in
  • Whether the pain is big enough to solve now

Map each objection to the proof needed:

  • Customer proof
  • Quantified outcome
  • Demo moment
  • Technical validation
  • Security documentation
  • ROI model
  • Before/after workflow
  • Executive narrative

9. Synthesize messaging implications

Turn the patterns into PMM direction.

Cover:

  • Primary message
  • Secondary messages
  • What to stop saying
  • What to say instead
  • Best-fit audience
  • Segment or persona nuance
  • Proof points to gather
  • Sales discovery questions
  • Content or campaign angles
  • Risks if the team overclaims

Messaging should come from customer reality, not clever copy.

Output format

Return a structured synthesis with these sections:

  1. Executive summary

    • 3-5 bullets on the strongest customer truths
  2. Audience and buying roles

    • User
    • Decision-maker
    • Economic buyer
    • Champion
    • Blockers or influencers
    • Confidence level
  3. Pains

    • Pain
    • Evidence from notes
    • Business impact
    • Confidence
  4. Triggers

    • Situation
    • Trigger
    • Reactive or proactive
    • Why now
    • Evidence
  5. Current workaround / status quo

    • What they do today
    • Why it persists
    • Where it breaks
    • Real competition
  6. Jobs To Be Done

    • Functional job
    • Emotional job
    • Social job
    • JTBD statement
  7. Exact customer language

    • Quote or phrase
    • Who said it, if known
    • Why it matters
    • Potential use in messaging or sales
  8. Objections and risks

    • Objection
    • Who holds it
    • Why it matters
    • Proof needed
  9. Proof and outcomes

    • Stated result
    • Quantified proof, if available
    • Anecdotal proof
    • Proof gaps
  10. Messaging implications

  • Recommended message
  • What to avoid
  • Sales discovery questions
  • Content, launch, or enablement angles
  • Follow-up research needed
  1. Unknowns and validation plan
  • Unknown
  • Why it matters
  • How to validate it

Quality bar

A strong synthesis:

  • Uses customer evidence, not PMM opinion, as the starting point
  • Names the status quo clearly
  • Distinguishes decision-maker pain from user pain
  • Identifies the moment that made the customer act
  • Shows whether the buyer is reactive or proactive
  • Pulls exact language that sounds like a real person
  • States what is known, inferred, and unknown
  • Connects pains to business impact
  • Connects objections to proof requirements
  • Produces messaging implications a sales or marketing team could use immediately
  • Avoids inventing claims, outcomes, or market patterns not supported by the input

Anti-patterns

Avoid:

  • Writing generic SaaS messaging from thin evidence
  • Treating every feature mention as a customer pain
  • Ignoring the current workaround
  • Assuming the competitor is only another vendor
  • Confusing user enthusiasm with budget authority
  • Turning quotes into sanitized marketing language
  • Claiming ROI, savings, or business impact not present in the notes
  • Averaging all personas into one vague buyer
  • Hiding uncertainty
  • Producing a summary that is interesting but not actionable for GTM

Related skills

  • positioning-messaging-framework: Use after this synthesis to define positioning, messaging pillars, and reasons to believe.
  • sales-narrative-deck: Use after positioning to turn customer truth into a first-call sales story.
  • customer-story-engine: Planned future skill for turning strong before/after stories into reusable proof assets.
  • launch-tier-framework: Planned future skill for using audience, narrative, and GTM priority to size launches.

Frequently asked questions

What does the Voice Of Customer Synthesis AI skill do?

Turn customer notes, call transcripts, sales feedback, and research into PMM-ready voice-of-customer inputs: pains, triggers, status quo, JTBD, exact language, objections, proof, and messaging implications.

Why use Voice Of Customer Synthesis on TypingMind?

Because you install it once and use it with any model. Voice Of Customer Synthesis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Voice Of Customer Synthesis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/growthack88/growth-marketing-os/tree/main/skills/community/voice-of-customer-synthesis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Voice Of Customer Synthesis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Voice Of Customer Synthesis?

As many as you like. As long as a model supports skills, you can use Voice Of Customer Synthesis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Voice Of Customer Synthesis AI skill free?

Yes. It is published on GitHub by growthack88 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇