agentleFS
InfiniteInsightInfiniteInsight/PortersValueChain-ClaudeSkill/skills/porters-value-chain/SKILL.md

porters-value-chain

Skill0 starsChanged 5 months agoMITView on GitHub

Use when analyzing where competitive advantage or margin comes from — running a Porter's Value Chain breakdown of a company OR one of the user's own software/app projects. Triggers on "value chain", "competitive advantage", "where's the margin", "strategy breakdown", or mapping a product's activities to find strengths/threats.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. tupe12334/instinct★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Follow these steps in order.

    line 14
  2. Distinctive:

    External company: ask the user for what they know.

    line 21
  3. Distinctive:

    Ask the user which lens to use:

    line 26
  4. Distinctive:

    Do not assume — ask, even for an obviously-software target, because the user wanted to choose each time.

    line 32
  5. Distinctive:

    If the user is asking to *learn* the framework rather than analyze a specific target (e.g.

    line 76
  6. Distinctive:

    Keep it concise — this is an explainer, not a full mapping.

    line 85

≈ “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

Porter's Value Chain Analysis

Apply Michael Porter's Value Chain framework to find where competitive advantage and margin are created — for an external company or one of the user's own software projects.

How to run an analysis

Follow these steps in order. Announce: "Using the Porter's Value Chain skill."

Step 1 — Identify the target

Determine what is being analyzed.

  • User's own project: gather context from the repo and conversation (README, product docs, recent commits, known collaborators). Do not ask the user for facts you can read yourself.
  • External company: ask the user for what they know. Do NOT fetch financials or invent figures — work only from provided/known information, and flag assumptions explicitly.

Step 2 — Pick the mode (ask up front)

Ask the user which lens to use:

  • Classic — the literal nine Porter activities, force-fitting the target and marking any activity N/A where it does not apply.
  • Software-adapted — Porter's structure translated for software/app/indie projects. Use the translation table in references/translation-table.md.

Do not assume — ask, even for an obviously-software target, because the user wanted to choose each time.

Step 3 — Map the activities into a matrix

Produce a Markdown table with one row per activity (primary first, then support), columns:

ActivityCost driversCurrent stateCompetitive-advantage potential

Fill every cell. Use "N/A — <reason>" rather than leaving blanks.

Step 4 — Render the value-chain diagram

Draw the classic shape inline as ASCII/Markdown: support activities as horizontal bands across the top, primary activities as the left-to-right arrow of boxes, and Margin on the right. Use this template, relabeling the primary boxes for Software-adapted mode:

┌─────────────────────────────────────────────────────────────┐
│ Firm Infrastructure                                          │\
│ Human Resource Management                                    │ \
│ Technology Development                                       │  >  M
│ Procurement                                                  │ /   A
├──────────┬──────────┬──────────┬──────────────┬─────────────┤/    R
│ Inbound  │Operations│ Outbound │  Marketing   │  Service    │  >  G
│Logistics │          │ Logistics│   & Sales    │             │ /   I
└──────────┴──────────┴──────────┴──────────────┴─────────────┘     N

Offer an HTML/SVG version only if the user asks.

Step 5 — Strategic synthesis

Identify the 2-3 activities that are the real source of, or biggest threat to, competitive advantage / margin. For each, give a one-line rationale and a concrete, prioritized next action. This is the payoff — never skip it.

Deliverable

By default, print matrix + diagram + synthesis in chat. Then offer to save a Markdown artifact, suggesting a consistent path like docs/strategy/<target>-value-chain.md. Save only if the user agrees.

Teaching mode

If the user is asking to learn the framework rather than analyze a specific target (e.g. "explain Porter's value chain", "what is the value chain"), skip the workflow above. Instead:

  1. Explain primary vs. support activities and the concept of margin.
  2. Walk one short worked example (pick a familiar company or, if the user has an active project, theirs) through 2-3 activities.
  3. Offer to run a full analysis next.

Keep it concise — this is an explainer, not a full mapping.

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.