Voice of Customer Agent Skill

When the user wants to know what customers are actually telling them — turning NPS, CSAT, CES, support tickets, call transcripts, churn…

Context cost
37k tokensestimated from the bundle, loaded when it triggers
Bundle
10 files · 172.9 kB1 script among them — read before you run
Licence
MITthe author’s own terms
Last change
—v1.0.0
Servers it uses
Noneruns standalone

What it does

When the user wants to know what customers are actually telling them — turning NPS, CSAT, CES, support tickets, call transcripts, churn reasons, feature requests and sales-loss notes into ranked themes with ARR attached and an owner on each. Also use when the user mentions 'across surveys and tickets', 'nps feedback', 'into themes', 'what are customers telling us', 'VoC readout', 'our NPS came back', 'NPS dropped', 'analyse our survey results', 'top complaints', 'customer feedback summary', 'feature request themes', 'why are customers unhappy', 'churn reasons', 'exit interview', 'win/loss…

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

analytics

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md39.3 kB · preview
--- name: voice-of-customer license: MIT metadata: version: 1.0.0 role: VP CS | CCO | CS Ops | Product Ops | CSM cadence: quarterly (readout) · monthly (pulse) · ad-hoc (theme deep-dive) ---
11# Voice of Customer
12
13You are running the feedback programme for a company where every theme you publish either gets
14funded or gets ignored, and both outcomes are your fault. The standard is not "summarise the
15survey". It is **a ranked register of what customers are telling you, with dollars attached to
16each theme, an accountable owner on each, and an honest statement of whose voice is missing** —
17handed to an exec staff that will spend money against it.
18
19The rookie version is recognisable in four seconds. It opens with an NPS number and no response
20rate, quotes the customer who emailed the CEO, and lists themes with no revenue on any of them —
21so Product ranks them by whichever CSM lobbied hardest, and a theme raised by 200 SMB trial users
22outranks one raised by $4M of Enterprise ARR three months from its opt-out deadline. Then it runs
23a survey nobody has capacity to act on, which is not neutral: it spends customer goodwill, returns
24nothing, and the response rate falls the next time you ask.
25
26The elite version treats **every channel as a biased instrument** and states the direction of each
27bias before quoting a number from it; codes free text against a **closed, versioned taxonomy** with
28a measured inter-coder check; attaches **ARR, segment and health band** to every theme so priority
29is a revenue argument, not a volume argument; **cross-references what customers say against what
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md6,261 words
Files10
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈310
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
36,715
on trigger
The instruction body and 9 supporting files, read only when the skill fires.
18.5%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

37k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

10 files, 172.9 kB on disk. Mostly text — the instructions the model reads — with 1 script in it that your client would run only if the instructions tell it to.

  • SKILL.md39.3 kB
  • assets/loop-close-note.md7.7 kB
  • assets/routing-brief.md4.6 kB
  • assets/theme-card.md3.7 kB
  • evals/evals.json5.4 kB
  • references/attribution.md19.3 kB
  • references/readout-structure.md17.3 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 1 script beside the text, so the bundle is 10 files you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Voice of Customer · 37k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/voice-of-customer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/voice-of-customer" ] && { [ ! -e .claude/skills/voice-of-customer ] || { mv .claude/skills/voice-of-customer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/voice-of-customer" .claude/skills/ && echo "Installed .claude/skills/voice-of-customer"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add gaintrace/voice-of-customer

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/voice-of-customer/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/voice-of-customer/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/voice-of-customer" ] && { [ ! -e ~/.claude/skills/voice-of-customer ] || { mv ~/.claude/skills/voice-of-customer "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/voice-of-customer" ~/.claude/skills/ && echo "Installed ~/.claude/skills/voice-of-customer" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/voice-of-customer/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0.0
Publishedno release date on file
PriceFree
Referencegaintrace/voice-of-customer

Versions

v1.0.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill