Porters Five Forces logo

Porters Five Forces

CommunityPopular
deanpeters
porters-five-forces

Read an industry's structure through Porter's Five Forces with documented signals per rating, ending at the profit pool. Use when weighing market entry or when margins erode and nobody can say why.

Overview

Publisherdeanpeters
RepositoryProduct-Manager-Skills
Skill nameporters-five-forces
Stars
7K
Forks
831
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by deanpeters on GitHub. Read the source before you install it.

Installation

Install the Porters Five Forces AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/deanpeters/Product-Manager-Skills.git /tmp/Product-Manager-Skills
mkdir -p .claude/skills
cp -r /tmp/Product-Manager-Skills/skills/porters-five-forces .claude/skills/porters-five-forces
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Porters Five Forces in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Porters Five Forces on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Porters Five Forces is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Porter's Five Forces (Evidence-Cited)

Purpose

Read an industry's structure through Porter's Five Forces, with evidence: search plan → force-by-force ratings with signals → profit-pool implication → next-step options. Each force — competitive rivalry, threat of new entrants, threat of substitutes, buyer power, supplier power — is rated weak/moderate/strong and justified with documented signals, because a rating without signals is vibes. The analysis closes where it should have been aiming all along: where the profit pool sits and who is squeezing it. Five forces is an argument about where margin goes, not a diagram for slide four.

Input

Works best with: the industry or segment, named as precisely as you can ("clinical data management SaaS," not "healthcare"), and the decision this analysis should support. Also useful: a geographic boundary if the structure differs by region, and a market-landscape-scan in session — the forces read builds on it and searches only gaps.

Input supplied inline with the invocation — text after the skill name, a pasted context dump, or an appended ARGUMENTS: line — counts as answers already given. Use it against the question budget; don't re-ask.

Arriving empty-handed? That works too. The skill opens with at most 3 questions (segment, decision, boundary) and proceeds on labeled assumptions if they go unanswered.

Example invocation: Five forces on mid-market field-service management software, North America — decision: whether we enter or partner.

Key Concepts

  • Governing protocol: honors the autonomous-investigation contract — question budget of 3, search-plan gate, Fact/Inference/Assumption labels, Just Enough Mode (2-4 signals per force), stable schema, 4-option Final Step. Disciplines: FININT (concentration, margins, filings) + OSINT (analyst coverage, trade press) per intelligence-collection-disciplines.
  • The framework (Porter, 1979): industry profitability is determined by five structural forces, not by how hard incumbents work. Rivalry sets the intensity of margin competition; entry threat caps pricing; substitutes cap value; buyer power extracts margin downstream; supplier power extracts it upstream. Structure explains what negotiation skill cannot: pricing power is structural.
  • Ratings must survive "how do you know?" Each weak/moderate/strong rating stands on documented signals — concentration data, switching costs, entry examples and how they fared, substitute adoption curves, margin trends. Forces-with-signals is the difference between naming a framework and using one.
  • AI-driven substitution is a named candidate, always. In most knowledge industries it is now the substitute threat; assess it explicitly in the substitutes force rather than letting the analysis pretend it's 2015. Supplier power gets the same modern read: cloud, model, and platform dependencies are supplier concentration.
  • Industry, not player: this reads what the structure does to everyone who plays. swot-analysis reads one company's position within it.
  • When NOT to use: nascent categories with no stable structure — the forces are still forming; run the landscape scan and revisit.
  • Do-not-invent list: market share, margin data, entrant names, funding rounds, adoption figures.

Application

  1. Credit inline context, then ask only the unanswered questions (max 3):
    1. Which industry or segment, precisely?
    2. What decision should this support?
    3. Any geographic boundary?
  2. Show the 3-bullet search plan — what you'll search per force, source types (filings, analyst coverage, trade press, pricing pages, funding databases), fact/inference separation. Continue unless revised. If a landscape scan is in session, build on it; search only gaps.
  3. Rate each force with signals, then emit the schema below exactly.

Output schema (do not reorder)

markdown
# Five Forces: [Industry / Segment]
**As-of date:** | **Boundary:** | **Decision supported:**

## 1. Competitive Rivalry — [weak / moderate / strong]
- Signals: [concentration, growth rate, differentiation, exit barriers — each with URL + label]
- What it means here: [one sentence]

## 2. Threat of New Entrants — [weak / moderate / strong]
- Signals: [entry barriers, capital needs, recent entrants and how they fared, regulation — each with URL + label]
- What it means here: [one sentence]

## 3. Threat of Substitutes — [weak / moderate / strong]
- Signals: [substitute adoption, price-performance trajectory, switching evidence — each with URL + label]
- AI-driven substitution, named and assessed: [labeled]
- What it means here: [one sentence]

## 4. Buyer Power — [weak / moderate / strong]
- Signals: [buyer concentration, switching costs, price transparency, backward-integration examples — URL + label]
- What it means here: [one sentence]

## 5. Supplier Power — [weak / moderate / strong]
- Signals: [supplier concentration (including cloud/model/platform dependencies), input differentiation — URL + label]
- What it means here: [one sentence]

## 6. The Profit Pool (the "so what")
- Where margin sits today, and the force squeezing it: [labeled]
- Structure trend: [tightening / loosening, on what evidence]
- For your decision: [2 sentences tying structure to the decision named above]

### Assumptions to Validate
- [Assumption 1] / [Assumption 2] / [Assumption 3]

A copy/paste fill-in version of this schema, with quality checks, lives in template.md.

Final Step (offer exactly 4 options)

  1. Trace the strongest force into your strategy's exposed assumptions
  2. Run market-landscape-scan to name the players behind each force
  3. Feed the profit-pool read into an Ansoff growth-options analysis (ansoff-matrix)
  4. Schedule-ready version: which force signals should a re-run watch?

Accept 1, 2, 3, 4, 1 and 3, Verbose Mode, or a custom path.

Examples

A rating that survives "how do you know?" (fictional):

4. Buyer Power — strong

  • Signals: top 10 buyers account for ~60% of segment spend — Fact ([trade association data, URL]); three publicized incumbent-to-rival switches in 18 months with no reported penalty — Fact ([press coverage, URLs]); public rate cards make pricing fully transparent — Fact ([vendor pricing pages]); one major buyer built the capability in-house — Fact ([their engineering blog, URL])
  • What it means here: buyers can credibly threaten to leave or build, so list-price integrity is an illusion in this segment — discounting pressure is structural, not a sales-discipline problem.

The profit-pool close doing its job: rivalry moderate, entrants weak, substitutes strong (AI agents absorbing the low-complexity tier), buyers strong, suppliers moderate. The pool sits in the regulated high-complexity tier — the only place two strong forces don't reach — Inference. For the entry decision: enter only via the regulated tier; the volume tier's margin is already spoken for by buyers below and AI substitution above.

See examples/sample.md for a complete worked five-forces read (fictional FSM-software market) that builds on the market-landscape-scan example and lands at a profit-pool close that changes the decision. examples/sample-industrial.md shows the forces inverting in an industrial market — read both to see the framework adapt instead of recite.

Common Pitfalls

  • Ratings as vibes. "Rivalry: strong" because it feels crowded. Every rating stands on signals with URLs, or the whole exercise is a diagram.
  • Skipping the AI substitute. Assessing substitutes as adjacent products while an AI workflow eats the category's low end. Name it and rate it, even when the rating is "weak — for now."
  • Confusing competitors with structure. Listing who plays (that's the landscape scan) instead of what the structure does to everyone who plays. The forces are about margin physics, not rosters.
  • No profit-pool close. Five rated forces and no answer to "where does margin go?" The close is the analysis; everything above it is evidence assembly.
  • Forcing structure onto a nascent category. Rating forces that haven't formed yet produces confident noise. Say "still forming," scan the landscape, revisit in two quarters.

References

  • autonomous-investigation (Workflow) — the governing protocol
  • intelligence-collection-disciplines (Component) — FININT/OSINT sources behind the signals
  • market-landscape-scan (Workflow) — who plays; this skill asks what the structure does to them
  • swot-analysis (Workflow) — one company's position within the structure
  • ansoff-matrix (Workflow) — growth options informed by the profit-pool read
  • Michael E. Porter, "How Competitive Forces Shape Strategy" (Harvard Business Review, 1979)
  • Adapted from market-intelligence/porters-five-forces-prompt.md in the https://github.com/deanpeters/product-manager-prompts repo.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Porters Five Forces AI skill do?

Read an industry's structure through Porter's Five Forces with documented signals per rating, ending at the profit pool. Use when weighing market entry or when margins erode and nobody can say why.

Why use Porters Five Forces on TypingMind?

Because you install it once and use it with any model. Porters Five Forces is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Porters Five Forces in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/deanpeters/Product-Manager-Skills/tree/main/skills/porters-five-forces. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Porters Five Forces?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Porters Five Forces?

As many as you like. As long as a model supports skills, you can use Porters Five Forces with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Porters Five Forces AI skill free?

It is published on GitHub by deanpeters. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇