Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add adam-lagerhausen/b2b-marketing-skills --skill voice-of-customer-synthesisgit clone --depth 1 https://github.com/adam-lagerhausen/b2b-marketing-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/adam-lagerhausen/b2b-marketing-skills/voice-of-customer-synthesis)<a href="https://agentmods.dev/skills/adam-lagerhausen/b2b-marketing-skills/voice-of-customer-synthesis"><img src="https://agentmods.dev/badge/skills/adam-lagerhausen/b2b-marketing-skills/voice-of-customer-synthesis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/adam-lagerhausen/b2b-marketing-skills/voice-of-customer-synthesis"><img src="https://agentmods.dev/badge/skills/adam-lagerhausen/b2b-marketing-skills/voice-of-customer-synthesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.01887 |
| Opus 5.5 | $0.00020 | $0.00755 |
| Sonnet 5.5 | $0.00010 | $0.00377 |
| Haiku 4.5 | $0.00005 | $0.00189 |
Grade A, and why
voice-of-customer-synthesis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
97% identical to voice-of-customer-synthesis — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 306 lines · 50 tokens per session scan A b12d73483859
voice-of-customer-synthesis is a skill published in the GitHub repository adam-lagerhausen/b2b-marketing-skills (6 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 1,887 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to voice-of-customer-synthesis, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
go-to-market-playbook
A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.
skill-catalog
Maintains the central registry of all skills with dependencies, trigger phrases, review gates, and chaining.
gbp-review-strategy
Analyzes review velocity, sentiment distribution, and competitor review patterns, then produces branded response.
design-reviewer
Reviews implemented React/Tailwind/CSS output for design quality across 5 dimensions scored 0-4: anti-patterns.
design-incident-response
Triage decision tree for design incidents flagged by /design-reviewer.
learn
Process raw source material (transcripts, docs, articles, competitor pages, meeting notes) into structured context.