agentleFS
CSPulseCSPulse/customer-success-skills/skills/value-ledger/SKILL.md

value-ledger

Skill2 starsChanged 3 months agoMITView on GitHub

Use when the user says "value ledger", "what has the customer actually achieved", "do we have proof of value", "capture their success goals", "what is our evidence of ROI", "log this win". Produces a goals table (customer's measure, baseline, now, target), a dated proof log tagged customer-stated or vendor-computed, the gaps, and one ask to capture the next proof in writing. Not for the review meeting itself (use business-review) or sizing an expansion (use expansion-case).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user pasted goals, notes, emails or call summaries for one account, go.

    line 13
  2. Distinctive:

    If an "Account context" block exists, use it.

    line 19
  3. Distinctive:

    Write each goal in the customer's measure,: not ours: what they count on their own scoreboard.

    line 23
  4. Distinctive:

    Never invent a number: Every figure comes from the paste or is marked missing.

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Value Ledger

What the customer set out to achieve and the proof they are getting it, in one place the QBR, the renewal read and the sponsor's own business case can all draw from.

Start here

If the user pasted goals, notes, emails or call summaries for one account, go. Also useful: the renewal date and today's date. Otherwise ask for these in ONE message, then proceed with whatever comes back:

  1. What the customer said they bought this to achieve, in their words
  2. Any result they have mentioned since: a number, a quote, a milestone
  3. The renewal date

If an "Account context" block exists, use it. If a ledger from last time is pasted, update it and show what changed.

Do this

  1. Write each goal in the customer's measure, not ours: what they count on their own scoreboard. Add baseline, now, target and target date. A blank is written "baseline missing", never filled.
  2. Compute progress as (baseline minus now) divided by (baseline minus target), and show the arithmetic.
  3. Log proof one row each: date, goal, kind (quote, metric, milestone, outcome), the words or number, who said it and where, and its type: customer-stated or vendor-computed. Activity (logins, messages sent) is not proof of value: say so.
  4. Age every row. Flag a goal whose newest customer-stated proof is older than 90 days (a common default, set your own), and any account renewing within that window with none.
  5. Attribute honestly. List what else changed in the period (a policy, hiring, season, another tool). State the claim at the strength the evidence supports.
  6. Price it only from the customer's inputs, shown with the inputs and labeled an estimate.
  7. End with one ask: the smallest request that gets the next proof in the customer's own words, in writing, plus a draft.

Output

VALUE LEDGER: [Account] | renews [date] ([n] days) | as of [date]
Position: [x of y goals provable today; what a skeptical finance reader would accept]

GOALS
| Goal (their words) | Measure | Baseline | Now | Target by [date] | Progress | Proof status |

PROOF LOG (all rows proposed until you confirm)
| Date | Goal | Kind | Evidence | Said by / source | Type | Age |

Attribution: [what else changed]
Estimate: [value, with each input and its source]

Gaps
- [goal, what is missing, how to get it]

Ask: [who, what, by when]
Draft: [short message]

What I could not check
- [gap]

A filled example is in examples/sample.md.

Rules

  • Value lives in the customer's measure. Their approver answers to their scoreboard, and a vendor metric gets read as the vendor's marketing.
  • No baseline, no proof. "Down to 10" means nothing without "from what". Capture it now, or say it is missing and from whose records it can be rebuilt.
  • Customer-stated beats vendor-computed. "Your tool, your math" ends the argument faster than any dashboard, so lead with their words and treat ours as support.
  • Evidence ages. A quote from last spring reads as history at renewal. Refresh before it is needed, not during.
  • Say what else changed. Correlation sells until a finance reader asks about the fee change. A claim with its confounder named survives; one without gets discounted whole.
  • Anything proposed is a proposal. An assistant or analyst suggesting a row does not make it proof. The user confirms each, because an overstated line damages the champion who carries it.
  • Get the champion to say it in writing. An email survives their moving on and travels without you, which a slide of ours never does.
  • Never invent a number. Every figure comes from the paste or is marked missing.

Related (only if installed)

business-review to turn the ledger into the meeting. expansion-case when proof supports a bigger ask. renewal-risk reads it as evidence.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.