agentleFS
teodstrteodstr/boardroom/skills/business-analysis/SKILL.md

business-analysis

Skill0 starsChanged 3 days agoMITView on GitHub

Structure any business question or case study like a strategy consultant: frame the decision, pick the right frameworks, back every point with evidence and end with a clear recommendation. Use this skill whenever a company, a founder or a student must choose between strategic options (open a new location, enter a city or a country, launch a product or a channel first, grow or cut), even when the question is short, as well as for case studies, "analyze this company" and business-school assignments. Triggers: "case study", "business case", "analyze this company", "what should X do", "should we open", "expand to", "étude de cas", "analyse stratégique", "faut-il ouvrir", "s'implanter", "recommandation stratégique", "caso práctico", "análisis estratégico", "qué debería hacer", "deberíamos abrir".

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    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:

    Not for a single named framework ("do a SWOT"): use that framework's skill directly.

    line 25
  2. Distinctive:

    If the question is too vague, ask at most two clarifying questions.

    line 33
  3. Distinctive:

    Every claim rests on the user's material, a cited source or an explicitly labeled assumption.

    line 89

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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

Business analysis

Turn an open business question into a structured, evidence-backed recommendation. This skill frames the problem and chooses the frameworks; the other skills in this pack do the detailed work.

When to use

  • Open questions: "Should a French bakery chain enter the UK?", "Why is this brand losing market share?", "Analyse ce cas".
  • A case study, annual report or company description to analyze.
  • Not for a single named framework ("do a SWOT"): use that framework's skill directly.

Inputs

  1. The decision to make and who makes it (CEO, investor, marketing team, a jury).
  2. The company, its industry and its geography.
  3. The material provided (case text, figures, links). Treat it as the primary source.

If the question is too vague, ask at most two clarifying questions. If the user wants you to proceed anyway, list your assumptions in a few lines and go.

Method

  1. Frame the decision. Rewrite the question as one decision with a scope and a horizon: "Should X do Y in market Z within N years?" State it in four lines with SCQA: Situation, Complication, Question, Answer (your starting hypothesis).
  2. Build an issue tree. Split the question into 2–4 sub-questions that are mutually exclusive and collectively exhaustive (MECE). For example: Is the market attractive? Can we win? Is it worth it financially? Can we execute?
  3. Pick 2–4 frameworks with the routing table below. More frameworks dilute the answer.
  4. Run each framework with its skill and keep only the findings that change the answer.
  5. Lead with the answer (Pyramid Principle): the recommendation first, then the three strongest arguments, then the risks and how to mitigate them.
  6. Make it actionable: next steps with an owner, a date and a success indicator.

Routing table

Sub-questionSkill
What is changing in the macro environment?pestel
Is the industry attractive? Who captures the profits?porter-five-forces
What are the company's real advantages?vrio, swot-tows
How does the company make money?business-model-canvas
Where should it grow?ansoff-matrix, bcg-matrix
How can it escape head-to-head competition?blue-ocean
How big is the opportunity?market-sizing
Does it make money on each customer?unit-economics
Who should it target, and how can it stand out?stp-positioning, marketing-mix
How should it source, make and deliver?supply-chain-strategy
Something went wrong publiclycrisis-communication
Luxury or premium brandluxury-brand-strategy

Output

## Recommendation
<One sentence: what to do, how, by when.>

## Why
1. <Argument + evidence>
2. <Argument + evidence>
3. <Argument + evidence>

## Analysis
<One short section per framework, each ending with "So what: …">

## Risks and mitigations
| Risk | Likelihood | Impact | Mitigation |
|---|---|---|---|

## Next steps
| Action | Owner | When | Success indicator |
|---|---|---|---|

## Assumptions and sources

Quality bar

  • The recommendation is a decision ("Enter Spain in 2027 through franchising"), not a summary ("Spain has potential").
  • Every claim rests on the user's material, a cited source or an explicitly labeled assumption. Never invent figures: give a reasoned estimate, or say which data would settle the point.
  • Each framework section ends with its consequence for the decision. Findings that change nothing are cut.
  • Written in the user's language, with the standard terms from each skill's terminology table.

Terminology

EnglishFrançaisEspañol
Case studyÉtude de casCaso práctico
Issue treeArbre des problèmesÁrbol de problemas
Key success factorsFacteurs clés de succès (FCS)Factores clave de éxito
RecommendationRecommandationRecomendación
Pyramid PrinciplePrincipe de la pyramide (Minto)Principio de la pirámide (Minto)

Sources

  • Minto, B. (1996). The Minto Pyramid Principle: Logic in Writing, Thinking and Problem Solving. Minto International.
  • Rasiel, E. M. (1999). The McKinsey Way. McGraw-Hill.

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.