agentleFS
DGouronDGouron/review-flow/.claude/skills/discovery/SKILL.md

discovery

Skill44 starsChanged 6 months agoMITView on GitHub

Business discovery before technical specs. Use to explore a problem, define personas, clarify the value proposition. Produces Lean Canvas, Personas, and Problem Statements in /docs/business/.

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use specify, plan and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 6 projects that use this

  • nicolasestremSkill

    brainstorm

    Structured idea generation and solution exploration with systematic analysis.

    Also in 4 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 6 projects that use this

  • MicrosoftSkill

    init

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .claude/roles/specifier.md — adopt this profile and follow all its rules.

    line 10

“Common” is measured: kept by at least 6 in 10 of the 25 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

Discovery - Business Exploration

Persona

Read .claude/roles/specifier.md — adopt this profile and follow all its rules.

Philosophy

Discovery comes BEFORE specs. We explore:

  • The problem — not the solution
  • The users — their pain points, not their requests
  • The value — the benefit, not the feature

"Fall in love with the problem, not the solution." — Uri Levine


Activation

This skill activates when the user wants to explore:

  • "I want to explore...", "What problem are we solving?"
  • "Who are the users?", "Discovery on..."
  • "What is the value proposition?"
  • "Lean canvas for...", "Persona of..."

Produced artifacts

ArtifactFileWhen to use
Problem Statementdocs/business/problems/<name>.mdDefine the problem precisely
Personadocs/business/personas/<name>.mdUnderstand who has the problem
Lean Canvasdocs/business/canvas/<name>.mdOverview of an opportunity

Workflow

Entry point

DISCOVERY - Start

You want to explore: [subject]

Where do we begin?
1. Problem Statement — What problem exactly?
2. Persona — Who has this problem?
3. Lean Canvas — Overview of the opportunity?

Choose your entry point, or tell me what you already know.

Problem Statement

Construction dialogue

PROBLEM STATEMENT - Exploration

I see: [vague description of the problem]

Let's dig deeper:
1. Who exactly has this problem?
2. When/where does it manifest?
3. What do they do today to work around it?
4. What is the consequence if we don't solve it?

Answer what resonates, we'll iterate.

Output template

File: docs/business/problems/<name>.md

# Problem Statement: [Explicit title]

## The problem

[Persona] encounters [problem] when [context/trigger].

Today, [persona] [current behavior / workaround].

This causes [negative consequence] and [measurable impact].

## Frequency and severity

| Dimension | Assessment |
|-----------|------------|
| Frequency | [daily/weekly/monthly/occasional] |
| Severity | [blocking/hindering/irritating] |
| Affected population | [estimate] |

## Hypotheses to validate

- [ ] [Hypothesis about the existence of the problem]
- [ ] [Hypothesis about frequency]
- [ ] [Hypothesis about impact]

## What the problem is NOT

- [Red herring 1 — why it's a red herring]
- [Red herring 2]

## Research questions

- [Open question to explore]

Persona

Construction dialogue

PERSONA - Construction

I'm going to ask you questions to define this persona.

1. Who is this person? (role, context, environment)
2. What are they trying to accomplish? (goals)
3. What frustrates them today? (pain points)
4. How do they handle the problem currently? (workarounds)

Start by describing this person as if you were introducing them to me.

Output template

File: docs/business/personas/<name>.md

# Persona: [Descriptive name]

## Identity

| Attribute | Description |
|-----------|-------------|
| Role | [role in the usage context] |
| Context | [environment, constraints, resources] |
| Experience | [expertise level on the subject] |

## Goals

What this person wants to accomplish:

1. **[Primary goal]** — [why it matters to them]
2. **[Secondary goal]** — [why it matters]

## Frustrations (Pain Points)

What blocks or irritates them today:

1. **[Frustration 1]** — Impact: [concrete consequence]
2. **[Frustration 2]** — Impact: [concrete consequence]

## Current behaviors

How they handle the problem today:

- [Workaround 1] — [limitations of this solution]
- [Workaround 2] — [limitations]

## Typical quote

> "[A sentence this person would say, capturing their mindset]"

## Success criteria

How do they know their problem is solved?

- [Measurable criterion 1]
- [Measurable criterion 2]

## Anti-persona

This persona is NOT:
- [Profile not to confuse with — why]

Lean Canvas

Construction dialogue

LEAN CANVAS - Construction

We're going to build the canvas block by block.

Let's start with the most important:
1. What is the main problem? (not 10, just 1-3)
2. For whom? (priority segment)

Once we have that, we continue with the value proposition.

Output template

File: docs/business/canvas/<name>.md

# Lean Canvas: [Product/feature name]

## 1. Problem

The 3 main problems:

1. **[Problem 1]**
2. **[Problem 2]**
3. **[Problem 3]**

### Existing alternatives

How users solve these problems today:

- [Current solution 1] — [limitations]
- [Current solution 2] — [limitations]

---

## 2. User segments

| Segment | Characteristics | Priority |
|---------|-----------------|----------|
| Early Adopters | [who will adopt first and why] | Target |
| Main market | [who represents the volume] | Later |

---

## 3. Unique value proposition

> [One sentence explaining why it's different and why it's worth it]

### High-Level Concept

"It's like [known analogy] for [specific context]"

---

## 4. Solution

The 3 key features:

| Feature | Solves |
|---------|--------|
| [Feature 1] | Problem 1 |
| [Feature 2] | Problem 2 |
| [Feature 3] | Problem 3 |

---

## 5. Channels

How to reach users:

- **Acquisition**: [how they discover]
- **Activation**: [how they start using]
- **Retention**: [how they come back]

---

## 6. Revenue streams

- [Revenue source 1] — [model: subscription, one-shot, freemium...]
- [Revenue source 2]

---

## 7. Cost structure

| Type | Cost | Recurrence |
|------|------|------------|
| [Fixed cost] | [amount] | [monthly/yearly] |
| [Variable cost] | [amount/unit] | [per usage] |

---

## 8. Key metrics

| Metric | Target | Why this metric |
|--------|--------|-----------------|
| [Metric 1] | [target] | [what it measures] |
| [Metric 2] | [target] | [what it measures] |

---

## 9. Competitive advantage

What cannot be easily copied:

- [Advantage 1] — [why it's defensible]
- [Advantage 2]

---

## Hypotheses to validate

| Hypothesis | Risk if wrong | How to validate | Status |
|------------|---------------|-----------------|--------|
| [Hypothesis 1] | [impact] | [method] | Pending |
| [Hypothesis 2] | [impact] | [method] | Pending |

Anti-patterns to block

Anti-patternExampleReaction
Jumping to solutions"We'll build a mobile app"Go back to the problem
Generic persona"Users want..."Ask who exactly
Problem without impact"It's not optimal"Ask for the consequence
Canvas without hypotheses"We know that..."Challenge the certainties
Confusing request/need"They want a button"Dig into the why

Challenge examples

Request: "We want to add a gamification feature"

DISCOVERY - Challenge

"Gamification" is a solution, not a problem.

Questions:
1. What user behavior do you want to encourage?
2. Why don't users do it naturally?
3. How do you know gamification will work?

Let's go back to the problem before discussing solutions.

Request: "Our users want an Excel export"

DISCOVERY - Challenge

Warning: what users ask for is not always what they need.

Questions:
1. What do they do with that Excel once exported?
2. If we gave them the end result directly, would that work?
3. Who is asking for this exactly? (persona)

Maybe the real need is a dashboard, not an export.

Integration with other skills

After discovery:

  • /pm to turn insights into actionable specs
  • /ddd if a new bounded context emerges

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.