
pm-determine
Product strategy and market analysis skills that set outcomes and map competitors, finance, and customers.
- GitHub stars
- 8.1K
What it does
- Adds 24 skills grouped as Direct, Diagnose, Detect, and Describe, plus 5 shared helper skills for the rest of the set
- Covers strategy and finance through
product-strategy-session,business-health-diagnostic, and SaaS revenue and efficiency metrics - Provides strategic lenses such as
swot-analysis,porters-five-forces,ansoff-matrix,pestel-analysis, andtam-sam-som-calculator - Designed for product managers who need structured market research and customer insight before setting outcomes
Set outcomes and read the terrain: strategy, finance, market, customers. 24 skills (Direct, Diagnose, Detect, Describe); shared helper skills included.
Add marketplace
/plugin marketplace add deanpeters/Product-Manager-SkillsRun it inside Claude Code once, then install the plugin below.
Install
/plugin install pm-determine@pm-skillsRun it inside Claude Code after adding the marketplace.
Files
Discovered from sourceAnsoff Matrix (Evidence-Backed)
Purpose
Map a company's growth options across the Ansoff Matrix with evidence per quadrant: use or gather evidence → four quadrants with signals → risk-rated sequence → next-step options. The four quadrants — market penetration, market development, product development, diversification — organize one question: where does the next tranche of growth come from, and at what risk? This is a research instrument, not wishful whiteboarding: every candidate move must answer "what documented signal says this demand exists?" And the close is a sequence, because growth options compound — penetration funds development, and diversification bets the funding.
Input
Works best with: the company or product line seeking growth, its current core (who is served,
with what, at what scale — the matrix's axes are defined relative to it), and the growth outcome and
horizon on the table.
Also useful: constraints (capital, capability, risk appetite), and any research in session — a
landscape scan, five-forces read, or company-intel output lets the
matrix organize evidence instead of gathering it.
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 (core, outcome and horizon, constraints) and proceeds on labeled assumptions if they go unanswered.
Example invocation: Ansoff growth options for our field-service product line — core: dispatch software for mid-market HVAC firms, US. Outcome: +40% ARR in 24 months. Constraint: no acquisitions.
Key Concepts
- Governing protocol: honors the
autonomous-investigationcontract — question budget of 3, search-plan gate, Fact/Inference/Assumption labels, Just Enough Mode (2-3 moves per quadrant), stable schema, 4-option Final Step. - The framework (Ansoff, 1957): growth options plotted on two axes — existing vs. new products, existing vs. new markets. Penetration (existing/existing) is the lowest-risk quadrant; diversification (new/new) the highest, because it abandons both anchors of proven demand at once.
- The risk gradient is law. Penetration < market development ≈ product development < diversification. A diversification move rated "low risk" needs extraordinary evidence — and the gradient teaches why diversification proposals deserve the heaviest evidence burden and usually arrive with the lightest.
- Signals, not wishes. Candidate moves come from documented signals: underserved-segment data,
expressed demand (
voice-of-customer-minerthemes), competitor precedent, capability evidence. An empty diversification quadrant is an acceptable answer; an invented one is not. - Coaching vs. investigation — same map, different jobs:
organic-growth-advisoris the Interactive sibling that diagnoses your growth constraint through questions (its Growth Path Matrix shares Ansoff's axes); this skill researches the evidence for each quadrant's options. Diagnose there, evidence here — they pair deliberately. - When NOT to use: feature-level prioritization (this is portfolio altitude — use
feature-investment-advisorfor a single build decision); no growth mandate or capacity — an options map without an owner is a poster. - Do-not-invent list: market sizes, adoption data, competitor results, demand claims. Where
sizing matters, flag it for
tam-sam-som-calculatorrather than guessing.
Application
- Check session for existing evidence (landscape scan, five forces, company intel, VoC). Present → the matrix organizes it; search only gaps.
- Credit inline context, then ask only the unanswered questions (max 3):
- Which company or product line, and what is its current core?
- What growth outcome and horizon is on the table?
- Any constraints — capital, capability, risk appetite?
- If researching fresh, show the 3-bullet search plan — what you'll search per quadrant (segment data, expressed demand, competitor precedents, capability signals), source types, fact/inference separation. Continue unless revised.
- Populate the quadrants and emit the schema below exactly.
Output schema (do not reorder)
# Ansoff Growth Options: [Company / Product Line]
**As-of date:** | **Current core:** | **Growth outcome sought:**
## 1. Market Penetration (existing product, existing market — lowest risk)
- **[Candidate move]** — signal: [evidence, URL, label] — risk: [low/med/high, why]
- [2-3 moves]
## 2. Market Development (existing product, new market)
- **[Candidate move: segment, geography, or channel]** — signal: [evidence of underserved demand, URL, label] — risk: [rating, why]
- [2-3 moves]
## 3. Product Development (new product, existing market)
- **[Candidate move]** — signal: [expressed demand, VoC theme, competitor precedent, URL, label] — risk: [rating, why]
- [2-3 moves]
## 4. Diversification (new product, new market — highest risk)
- **[Candidate move]** — signal: [the extraordinary evidence this quadrant requires, URL, label] — risk: [rating, why]
- [1-2 moves; an empty quadrant is an acceptable answer]
## 5. Recommended Sequence (the "so what")
- **First:** [move] — because [evidence strength + funding logic]
- **Then:** [move] — funded/de-risked by the first
- **Not yet:** [the tempting move and why the evidence says wait]
- **The assumption that breaks this sequence:** [one line]
### 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)
- Size the top move with TAM/SAM/SOM (
tam-sam-som-calculator) (Recommended) - Pressure-test the sequence with a premortem
- Deep-dive the diversification quadrant's evidence
- Convert the first move into an opportunity solution tree (
opportunity-solution-tree)
Accept 1, 2, 3, 4, 1 and 2, Verbose Mode, or a custom path.
Examples
A quadrant entry earning its place (fictional):
2. Market Development
- Adjacent trade: plumbing contractors, same size band — signal: plumbing firms appear unprompted in 14% of our category's review-site mentions asking "does this work for plumbing?" — Fact ([review threads, URLs]); the two incumbents serving plumbing both gate scheduling behind enterprise tiers — Fact ([pricing pages]) — risk: medium — demand signal is real but second-hand; sales motion transfers, integrations don't fully.
The sequence close doing its job:
- First: win-back campaign into the churned-but-reachable base (penetration) — strongest evidence, funds everything else, 1-quarter payback
- Then: plumbing-contractor entry (market development) — de-risked by the penetration win's cash and case studies
- Not yet: the IoT hardware bundle (diversification) — one analyst mention and founder enthusiasm is not extraordinary evidence
- The assumption that breaks this sequence: churned customers left for fixable reasons; if win-loss shows they left the category, penetration is a dead first move and development leads.
See examples/sample.md for a complete worked matrix (fictional FSM-software
market) with an honestly empty diversification quadrant and a sequence whose breaking assumption is
named. examples/sample-industrial.md shows the opposite lesson: a
populated diversification quadrant whose entry fails the evidence bar in writing.
Common Pitfalls
- The brainstorm grid. Four quadrants of unsourced ambition. Every move answers "what signal says this demand exists?" or it doesn't ship — that single rule converts Ansoff from wall art into an instrument.
- Risk-gradient denial. A diversification move rated low-risk on enthusiasm. The gradient is the framework's whole teaching: new product and new market means both anchors are gone.
- Quadrant stuffing. Filling diversification because empty feels lazy. An honestly empty quadrant is a finding; a padded one is a liability with a deadline.
- Options without sequence. A menu with no first move, no funding logic, no breaking assumption. Growth options compound — order is the strategy.
- Sizing by vibe. Attaching invented market sizes to moves. The do-not-invent list routes sizing to the TAM/SAM/SOM calculator, where the math shows its work.
References
organic-growth-advisor(Interactive) — the coaching sibling: diagnoses which growth path fits your constraint; this skill evidences the optionsautonomous-investigation(Workflow) — the governing protocolintelligence-collection-disciplines(Component) — signal sources per quadrantporters-five-forces(Workflow) — the profit-pool read that feeds this analysistam-sam-som-calculator(Component) — sizes the movesvoice-of-customer-miner(Workflow) — expressed-demand signals for product developmentopportunity-solution-tree(Interactive) — structures the first move's execution- H. Igor Ansoff, "Strategies for Diversification" (Harvard Business Review, 1957)
- Adapted from
market-intelligence/ansoff-matrix-prompt.mdin thehttps://github.com/deanpeters/product-manager-promptsrepo.
Readme
PM Skills: Determine
Set outcomes and read the terrain: strategy, finance, market, customers.
Lifecycle phase: Context
Generated from pm-skills.config.yaml. Do not edit here: change the skill in skills/ and rebuild with python3 scripts/build-plugins.py.
Install
/plugin install pm-determine --marketplace deanpeters/Product-Manager-Skills
Skills by motion
Direct
Business and product outcomes, strategy, and the finance behind them
product-strategy-sessionorganic-growth-advisorbusiness-health-diagnosticfeature-investment-advisorfinance-metrics-quickrefsaas-economics-efficiency-metricssaas-revenue-growth-metrics
Diagnose
Strategic lenses: SWOT, Porter's, Ansoff, PESTEL, TAM/SAM/SOM
Detect
The market and competitor investigation chain
company-intelcompany-researchcompetitive-analysis-processcompetitive-intel-watchcompetitive-research-snapshotintel-discipline-advisorintelligence-collection-disciplinesmarket-landscape-scanpestel-delta-monitor
Describe
Who the customer is: jobs, personas, voice of customer
Also included (Core)
Shared helpers the skills above lean on:
workshop-facilitationpm-skills-navigatorautonomous-investigationpm-skill-creatorskill-authoring-workflow
License
CC BY-NC-SA 4.0. See LICENSING.md.
Details
- Marketplace
- deanpeters/Product-Manager-Skills
- Source
- plugins/pm-determine
- Category
- Lifecycle Bundle
More from deanpeters/Product-Manager-Skills
All 102- pm-develop
- pm-discover
- pm-drive
- pm-role-charter
- pm-skill-creator
- pm-skills-navigator
- pol-probe
- pol-probe-advisor
- porters-five-forces
- positioning-statement
- positioning-workshop
- prd-development
- press-release
- pricing-packaging-tracker
- prioritization-advisor
- problem-framing-canvas
- problem-statement
- product-lifecycle-plays
- product-manager-skills
- product-sense-interview-answer
- product-strategy-session
- proto-persona
- recommendation-canvas
- release-readiness
Similar to pm-determine
More Development Tools
reamorluto/rea466.8K starsReverse engineer anything with agents, from app behavior down to native binaries.
superpowersobra/superpowers319.5K starsCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
claude-apianthropics/skills196.9K starsClaude API and SDK documentation skill for building LLM-powered applications
prompts.chatf/prompts.chat178.2K starsAccess thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
agent-sdk-devanthropics/claude-code156.1K starsDevelopment kit for working with the Claude Agent SDK
ui-ux-pro-maxnextlevelbuilder/ui-ux-pro-max-skill152.6K starsProfessional UI/UX design intelligence for AI coding assistants. Includes searchable databases of styles, colors, typography, charts, and UX guidelines for Reac