mece-framework
Skill6 starsChanged 4 months agoApache-2.0View on GitHub
Use when a problem, issue tree, option set, segmentation, workplan, hypothesis set, risk list, or recommendation structure must be mutually exclusive and collectively exhaustive. Use when applying MECE, no-overlap/no-gap structuring, consulting issue decomposition, taxonomy cleanup, or structured problem solving.
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
- cost-benefit-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
- 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
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- Distinctive: line 9
Use this skill to check and improve whether a structure is clear, non-overlapping, and complete enough for decision work.
- Very specific: line 28
If an input is missing, do not block automatically.
- Very specific: line 32
Do not use MECE when the user is still exploring raw ideas and premature structure would hide weak signals.
- Distinctive: line 79
Do not confuse MECE with excessive completeness.
- Distinctive: line 80
Keep items at the same logical level whenever possible.
- Distinctive: line 81
Avoid mixing causes, symptoms, actions, owners, and metrics in the same branch set unless that is the deliberate design.
- Distinctive: line 83
If full MECE is impossible, state the practical boundary and remaining ambiguity.
≈ “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
MECE Framework
Use this skill to check and improve whether a structure is clear, non-overlapping, and complete enough for decision work.
Method Notes
- MECE means Mutually Exclusive and Collectively Exhaustive.
- Mutually exclusive means categories do not overlap in a way that creates double counting or unclear ownership.
- Collectively exhaustive means the structure covers all material parts of the question within the chosen scope.
- MECE is a discipline, not a slogan. Use it to improve clarity, not to make every real-world situation artificially neat.
Required Inputs
Collect or infer these inputs before execution:
- core question or decision
- current structure, list, tree, segmentation, options, hypotheses, or workplan
- scope boundary
- intended use of the structure
- known exclusions, constraints, or edge cases
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 MECE when the user is still exploring raw ideas and premature structure would hide weak signals. Use affinity-diagram or mind-map-analysis first.
Step-by-Step Execution
| Step | Required input | How to execute | Output |
| State the scope | Core question, intended use, boundary. | Define what the structure must cover and what it deliberately excludes. | Scope statement. |
| List current branches | Existing list, tree, segments, options, hypotheses, or actions. | Put all current items at the same logical level when possible. | Current structure. |
| Test mutual exclusivity | Current branches, definitions. | Check whether two items overlap, duplicate, mix levels, or create ambiguous ownership. | Overlap diagnosis. |
| Test collective exhaustiveness | Scope, edge cases, known exclusions. | Ask what important case, stakeholder, cause, option, segment, or risk is missing. | Gap diagnosis. |
| Fix level and logic | Overlaps, gaps, mixed levels. | Rename, split, merge, move, or add branches so each item has one clear place. | Revised structure. |
| Define inclusion rules | Revised structure. | Write a short rule for what belongs in each branch and what does not. | Category rules. |
| Stress test with examples | Edge cases, sample facts, known scenarios. | Place sample items into the structure and check if any item fits nowhere or fits multiple places. | Stress-test result. |
Output Template
### 1. Scope
- Core question:
- Structure being tested:
- In scope:
- Out of scope:
### 2. Current Structure
| Branch / item | Current definition | Level | Issue detected |
|---|---|---|---|
| | | same level / mixed level | overlap / gap / unclear / ok |
### 3. MECE Diagnosis
| Problem | Where it appears | Why it matters | Fix |
|---|---|---|---|
| overlap / duplicate / mixed level / missing branch / unclear boundary | | | |
### 4. Revised MECE Structure
| Branch | Inclusion rule | Exclusion rule | Example items |
|---|---|---|---|
| | | | |
### 5. Stress Test
- Item that fits clearly:
- Edge case:
- Remaining ambiguity:
- Next refinement:Quality Gate
- Do not confuse MECE with excessive completeness. The structure only needs to be complete for the current decision scope.
- Keep items at the same logical level whenever possible.
- Avoid mixing causes, symptoms, actions, owners, and metrics in the same branch set unless that is the deliberate design.
- Define inclusion and exclusion rules for ambiguous branches.
- If full MECE is impossible, state the practical boundary and remaining ambiguity.
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.

