Value Case & ROI Measurement Agent Skill

When the user has to prove, measure or defend what a customer actually got for their money — the impact hypothesis, the baseline, the…

Context cost
30.9k tokensestimated from the bundle, loaded when it triggers
Bundle
11 files · 141.3 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 has to prove, measure or defend what a customer actually got for their money — the impact hypothesis, the baseline, the KPIs, the arithmetic, and the one-page value case. Also use when the user mentions 'prove the roi', 'roi to their finance team', 'show the value we delivered', 'build the value case', 'ROI model', 'we never captured a baseline', 'capture the baseline', 'there is no baseline', 'what did we actually save them', 'quantify the impact', 'justify the spend', 'is it worth what they pay', 'the number has to survive finance', 'measure the outcome we promised', 'impact…

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.md38.3 kB · preview
--- name: value-case license: MIT metadata: version: 1.0.0 role: CSM | AM | FDE | VP CS | CCO cadence: per-account (built at kickoff) · quarterly refresh · per-renewal ---
11# Value Case & ROI Measurement
12
13You are running the measurement programme that decides whether this customer can answer their own
14CFO in November. Not the slide — the programme: an impact hypothesis agreed before deployment, a
15baseline captured while the pre-period still exists, one to three KPIs instrumented in a system,
16arithmetic a finance team can audit, and a number the **customer** states rather than one you assert.
17
18The rookie failure happens at the same moment every time. At T-60 someone opens the analytics tool
19and builds an ROI slide out of logins and a loaded cost they invented — no baseline, attribution a
20silent 100%, inputs their finance team has never seen. It gets one question, *"where does 47% come
21from?"*, and every other number in the deck dies with it. **The baseline is the unrecoverable
22step:** once the product is live the pre-period is gone unless the customer's own system retained
23it. Hence kickoff, not renewal.
24
25The elite version is quieter and harder to argue with. The hypothesis was written before go-live
26and they agreed it. The baseline sits in a dated record naming who supplied it. Attribution is a
27number **they** set, never 1.0. The headline is the conservative scenario, the sensitivity line is
28published before anyone asks, and a short list of benefits is deliberately not counted — which is
29what makes the counted ones believable. Read ../cs-context/references/evidence-standard.md
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md6,343 words
Files11
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.

≈300
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
30,625
on trigger
The instruction body and 10 supporting files, read only when the skill fires.
15.5%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

30.9k 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

11 files, 141.3 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.md38.3 kB
  • assets/baseline-record.md2.9 kB
  • assets/impact-hypothesis.md2.8 kB
  • assets/value-one-pager.md5.1 kB
  • evals/evals.json6.3 kB
  • references/attribution.md13.7 kB
  • references/baseline-methods.md19.7 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 11 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.

# Value Case & ROI Measurement · 30.9k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/value-case-roi-measurement/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/value-case-roi-measurement" ] && { [ ! -e .claude/skills/value-case-roi-measurement ] || { mv .claude/skills/value-case-roi-measurement "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/value-case-roi-measurement" .claude/skills/ && echo "Installed .claude/skills/value-case-roi-measurement"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add gaintrace/value-case-roi-measurement

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/value-case-roi-measurement/ 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/value-case-roi-measurement/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/value-case-roi-measurement" ] && { [ ! -e ~/.claude/skills/value-case-roi-measurement ] || { mv ~/.claude/skills/value-case-roi-measurement "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/value-case-roi-measurement" ~/.claude/skills/ && echo "Installed ~/.claude/skills/value-case-roi-measurement" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/value-case-roi-measurement/ 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. It appears as value-case in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, value-case-roi-measurement.

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/value-case-roi-measurement

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