agentleFS
fzfcleefzfclee/consulting-skills/skills/customer-success-health-score/SKILL.md

customer-success-health-score

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Use when assessing retention risk, expansion potential, account quality, or service intervention priority. Use when applying the Customer Success Health Score consulting method and when a user asks for Customer Success Health Score, method execution, structured diagnosis, or action planning.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to run Customer Success Health Score as a practical consulting method, not as a generic framework explanation.

    line 9
  2. Distinctive:

    Use adoption, realized value, relationship, support, commercial, and risk signals.

    line 14
  3. Very specific:

    If an input is missing, do not block automatically.

    line 25
  4. Distinctive:

    Do not use before customer outcomes, adoption signals, relationship signals, renewal risk, and data quality are defined.

    line 29
  5. Distinctive:

    Keep wording professional and plain enough that a smart non-specialist can use the output directly.

    line 88

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Customer Success Health Score

Use this skill to run Customer Success Health Score as a practical consulting method, not as a generic framework explanation.

Method Notes

  • Define healthy before scoring.
  • Use adoption, realized value, relationship, support, commercial, and risk signals.

Required Inputs

Collect or infer these inputs before execution:

  • customer or account list
  • usage/adoption signals
  • value realization evidence
  • relationship and support data

If an input is missing, do not block automatically. Mark it as missing, state the assumption used, and add a validation action.

When Not To Use

Do not use before customer outcomes, adoption signals, relationship signals, renewal risk, and data quality are defined. One aggregate score must not hide a critical failure condition.

Adjacent Methods

  • metrics-tree: design causal drivers and guardrails before building a score.
  • user-journey-mapping: diagnose where experience friction creates the risk signal.

Step-by-Step Execution

StepRequired inputHow to executeOutput
Define health outcomeRetention, expansion, value realization, satisfaction objective.State what healthy means for customer and business.Health definition.
Select signal categoriesAdoption, value, relationship, support, commercial, risk data.Choose candidate health signals and state their evidence; predictive value is unvalidated unless tested.Signal model.
Set weights and thresholdsSignal model, historical evidence, expert judgment.Specify how raw signals map to scores or grades and the combination rule: weighted aggregation or ordered qualitative rules. Define tier boundaries, missing-data handling and critical-failure overrides. Mark designed rules proposed / unvalidated unless evidence supports validation.Health scoring rubric.
Score accountsCustomer/account data.Calculate health tier and explain drivers.Health score table.
Assign interventionsHealth tier, owner capacity, account value.Define save, nurture, expand, or monitor actions.CS intervention plan.

Output Template

### 1. Health Definition
Desired customer outcome:
Risk event:
Prediction window:
Population:

### 2. Signals And Weights
Raw-to-score / grade mapping, combination rule, missing-data and critical-failure precedence:
Rubric status and validation evidence:
| Signal | Definition | Source | Weight | Threshold | Lag / leading |
|---|---|---|---|---|---|
|  |  |  |  |  |  |

### 3. Customer Scores
| Customer | Score | Tier | Evidence gap | Primary risk |
|---|---|---|---|---|
|  |  |  |  |  |

### 4. Intervention Rules
| Tier / trigger | Action | Owner | Timing | Recovery signal |
|---|---|---|---|---|
|  |  |  |  |  |

### Evidence And Next Decision
- Confirmed facts:
- Assumptions:
- Missing evidence:
- Next action, owner, and timing:
- Expected signal and decision threshold:

Quality Gate

  • Produce the method-specific outputs for Health Definition, Signals And Weights, Customer Scores; do not substitute a generic framework summary.
  • Tie every material score, causal claim, or stakeholder judgment to evidence or label it as an assumption.
  • Include at least one disconfirming check, sensitivity, alternative explanation, or failure condition appropriate to the method.
  • Convert the result into a named action or decision with an owner or stakeholder, timing, and observable signal.
  • State missing inputs and the smallest validation action instead of inventing precision.
  • Carry mapping, combination rules, missing-data effects and any critical-failure override into each result; do not let a healthy average hide a critical failure. Proposed / unvalidated rubric values do not establish predictive accuracy.
  • Keep wording professional and plain enough that a smart non-specialist can use the output directly.

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.