agentleFS
patonkikhpatonkikh/APES/skills/product/product-vision-builder/skill.md

product-vision-builder

Skill3 starsChanged 4 months agoMITView on GitHub

Define a product vision that connects user problems, strategic direction, and measurable north star using the Product Vision Canvas. Use when working on product discovery, PRDs, user stories, OKRs, or backlog planning.

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Keep to 2–3 sentences maximum.

    line 39
  2. Distinctive:

    Keep realistic given stated constraints.

    line 73
  3. Distinctive:

    Keep vision stable; tactics change, vision should not shift weekly.

    line 121

≈ “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

Product Vision Builder

Purpose

Define a product vision that connects user problems, strategic direction, and measurable north star using the Product Vision Canvas.

Input: Problem statement, persona (optional), business context (optional)
Output: Product Vision document with vision statement, principles, and north star metric candidate Examples: See examples.md for worked input/output.


Workflow

Step 1: Synthesize inputs

Consolidate:

  • Core problem being solved (from problem statement or user input)
  • Primary persona and their success definition
  • Business constraints (market, timeline, resources)
  • Competitive landscape (if provided)

Step 2: Draft vision statement

Format:

For [target user] who [need/problem], [product name] is a [category] that [key benefit]. Unlike [alternatives], we [differentiation].

Keep to 2–3 sentences maximum.

Step 3: Define product principles

Establish 3–5 guiding principles:

  • Decision-making rules for the team
  • Trade-off preferences (speed vs quality, breadth vs depth)
  • Non-negotiables (security, accessibility, etc.)

Each principle must be actionable, not aspirational slogans.

Step 4: Identify north star metric

Select one metric that:

  • Reflects core value delivered to users
  • Is measurable and trackable
  • Correlates with long-term business success

Document:

  • North star metric definition
  • Input metrics that drive it (3–5 leading indicators)
  • Anti-metrics (what you will NOT optimize at expense of vision)

Step 5: Define 3-year direction

Outline:

  • Year 1: foundation (what must be true)
  • Year 2: expansion (what grows)
  • Year 3: maturity (what scales)

Keep realistic given stated constraints.

Step 6: Validate

Run Validation checklist.


Decision Rules

ConditionAction
No problem statement or equivalentStop; request problem context or run problem-statement-builder
Vision statement includes feature listReframe to outcome and differentiation, not features
Multiple north star metrics proposedForce selection of one primary; others become input metrics
Principles are generic ("user first")Rewrite as actionable decision rules
3-year plan ignores stated constraintsRevise to match resources and timeline

Validation

  • Vision statement follows For/Who/Is/That/Unlike/We format
  • 3–5 actionable product principles defined
  • Exactly one north star metric with definition
  • 3–5 input metrics linked to north star
  • Anti-metrics documented
  • 3-year direction is realistic given constraints
  • No feature laundry list in vision statement

Anti-patterns

  • Feature vision — listing capabilities instead of user outcome.
  • Multiple north stars — diluting focus across competing metrics.
  • Slogan principles — "innovate", "delight users" without decision guidance.
  • Ignoring constraints — 3-year unicorn plan for a 2-person team.
  • Copying competitor vision — differentiation says "like X but better" without substance.

Best Practices

  • Connect vision directly to validated problem statement.
  • Make principles testable: "When X conflicts with Y, choose X."
  • North star should be measurable within first 90 days (even if baseline is zero).
  • Review vision against persona anti-goals.
  • Keep vision stable; tactics change, vision should not shift weekly.

Output Structure

# Product Vision: [Product Name]

## Vision Statement
[For/Who/Is/That/Unlike/We paragraph]

## Product Principles
| # | Principle | Decision rule |
|---|-----------|---------------|

## North Star
- **Metric:** [name]
- **Definition:** [how measured]
- **Current baseline:** [if known]

## Input Metrics
| Metric | Drives north star by... |
|--------|-------------------------|

## Anti-metrics
- [What we won't optimize]

## 3-Year Direction
| Year | Focus | Key milestone |
|------|-------|---------------|

## Assumptions
- [ ] [Assumption]

Next Skills

OutcomeRecommended Skill
Need to prioritize featuresproduct/feature-prioritization
Ready for detailed requirementsproduct/prd-generator
Need OKRs from visionproduct/feature-prioritization
Vision needs user groundingproduct/persona-generator

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.