cost-benefit-analysis
Skill6 starsChanged 4 months agoApache-2.0View on GitHub
Use when deciding whether an action is worth the resources, attention, or tradeoffs required. Use when applying the Cost Benefit Analysis consulting method and when a user asks for Cost Benefit Analysis, method execution, structured diagnosis, or action planning.
In this repository57 other files it gives its agents.
- 5w1h-analysisSkill
- abductive-reasoningSkill
- account-planSkill
- affinity-diagramSkill
- assumption-inventorySkill
- balanced-scorecardSkill
- break-even-analysisSkill
- business-model-canvasSkill
- change-event-timelineSkill
- change-impact-analysisSkill
- communications-planSkill
- competitive-positioningSkill
- constraint-analysisSkill
- critical-uncertaintiesSkill
- customer-segmentationSkill
- customer-success-health-scoreSkill
- deal-strategy-mapSkill
- decision-matrixSkill
- deductive-reasoningSkill
- effort-impact-matrixSkill
- empathy-mapSkill
- evidence-mapSkill
- fifteen-percent-solutionsSkill
- first-principles-thinkingSkill
- fishbone-diagramSkill
- five-whys-root-causeSkill
- force-field-analysisSkill
- go-to-market-diagnosisSkill
- hypothesis-treeSkill
- inductive-reasoningSkill
- issue-treeSkill
- jobs-to-be-doneSkill
- kano-modelSkill
- mece-frameworkSkill
- metrics-treeSkill
- mind-map-analysisSkill
- min-specsSkill
- north-star-metricSkill
- pestel-analysisSkill
- porter-five-forcesSkill
- power-interest-gridSkill
- pre-mortemSkill
- pricing-strategy-checkSkill
- raci-matrixSkill
- rice-scoringSkill
- risk-matrixSkill
- scenario-planningSkill
- service-blueprintSkill
- signal-vs-noise-filterSkill
- stakeholder-power-mapSkill
- swot-analysisSkill
- systems-thinkingSkill
- user-journey-mappingSkill
- validation-planSkill
- weighted-scorecardSkill
- win-loss-reviewSkill
- wsjf-prioritizationSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Very specific: line 9
Use this skill to run Cost Benefit Analysis as a practical consulting method, not as a generic framework explanation.
- Very specific: line 26
If an input is missing, do not block automatically.
- Distinctive: line 30
Do not use when material costs and benefits cannot be compared over a common time horizon.
- Distinctive: line 87
Keep wording professional and plain enough that a smart non-specialist can use the output directly.
≈ “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.
Files
Cost Benefit Analysis
Use this skill to run Cost Benefit Analysis as a practical consulting method, not as a generic framework explanation.
Method Notes
- Compare against a clear baseline.
- Include timing, confidence, opportunity cost, and downside case.
Required Inputs
Collect or infer these inputs before execution:
- option or investment
- benefit estimates
- cost estimates
- time horizon
- risk assumptions
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 when material costs and benefits cannot be compared over a common time horizon. Treat non-negotiable legal, safety, or policy constraints as gates rather than averaging them into a financial total.
Adjacent Methods
break-even-analysis: calculate the threshold volume, price, or time.decision-matrix: compare options across non-financial criteria as well as economics.
Step-by-Step Execution
| Step | Required input | How to execute | Output |
| Define baseline | Current state, proposed option, time horizon. | State what the option is compared against. | Baseline and option definition. |
| Estimate benefits | Revenue, savings, risk reduction, learning, strategic value. | List benefits by type, owner, timing, and confidence. | Benefit estimate table. |
| Estimate costs | Fixed cost, variable cost, time, coordination, opportunity cost. | List costs and timing, including hidden effort. | Cost estimate table. |
| Compare scenarios | Benefits, costs, assumptions. | Calculate or reason through base, upside, and downside cases. | Scenario comparison. |
| Recommend threshold | Scenario comparison and constraints. | Recommend go/no-go/test-first and assumptions to validate. | Cost-benefit recommendation. |
Output Template
### 1. Decision Baseline
Decision:
Baseline / do-nothing case:
Time horizon:
Discount / timing assumption:
### 2. Benefits And Costs
| Item | Type | Amount / range | Timing | Evidence | Confidence |
|---|---|---|---|---|---|
| | | | | | |
### 3. Scenarios
| Scenario | Net value | Key assumption | Downside |
|---|---|---|---|
| | | | |
### 4. Recommendation And Threshold
Recommendation:
Break condition:
Owner:
Validation action:
### 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 Decision Baseline, Benefits And Costs, Scenarios; 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.
- Keep wording professional and plain enough that a smart non-specialist can use the output directly.
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
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.

