Prd V02 Product Type Classification

What it does

When your agent uses it

• PRD v0.2 work after competitive analysis
• User asks what type of product should we build?
• Should we clone
• Is this a fast-follow opportunity?

Example prompts

• “what type of product should we build?”
• “should we clone or innovate?”
• “is this a fast-follow opportunity?”
• “/prd-v02-product-type-classification”

Requirements

• Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep, WebSearch, WebFetch

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Claiming Innovation when it's really Clone: If competitor exists with revenue, you're not innovating
2. 2Undercut without price evidence: Must show 60%+ reduction is possible AND sustainable
3. 3Slice without ecosystem validation: Platform must actually want third-party apps
4. 4Wrapper without API access confirmed: Technical feasibility must precede classification
5. 5Unbundle from small platform: Only works against large horizontal players

What it can do on your machine

Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Glob
  • Grep
  • WebSearch
  • WebFetch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prd V02 Product Type Classification loads about 1.8k tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 143 tokens; SKILL.md has 457 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~143

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 457 words, ~1,817 tokens.

name

prd-v02-product-type-classification

description

Classify product approach into one of six types (Clone, Unbundle, Undercut, Slice, Wrapper, Innovation) based on competitive landscape. Triggers on PRD v0.2 work after competitive analysis, or when user asks "what type of product should we build?", "should we clone or innovate?", "is this a fast-follow opportunity?", "how should we position against competitors?", "clone vs undercut", "unbundle vs slice", or requests help choosing product strategy. Outputs BR- entries for product type classification and inherited GTM constraints.

allowed-tools

Read, Write, Edit, Glob, Grep, WebSearch, WebFetch

context

fork

BR-042: Product Type Classification

Type: Classification Decision
Date: 2026-02-01
Confidence: 70% (source: competitive-landscape-analysis + 3-customer-interviews)

Classification: UNDERCUT
Rationale: All 3 direct competitors (Notion, Linear, Figma) serve enterprise/mid-market first; SMB segment underserved. We can deliver 80% of feature set at 40% price for SMB-specific workflows.

Evidence:
  - CFD-015 (landscape): "All competitors start at $50/user/month enterprise pricing"
  - CFD-018 (landscape): "3 SMB teams using workarounds because pricing doesn't fit budget"
  - CFD-001 (value hypothesis): "$12,500/year value for 5 core features only"

GTM Constraints (inherited):
  - Pricing: Must be <$200/user/month to justify switching
  - Channel: Direct sales to SMB, not marketplace/enterprise
  - Scope: Ruthlessly cut features; 5 core + 3 differentiators max
  - Timeline: Fast iteration with SMB feedback; can't outspend enterprise marketing

START: What does v0.2 Competitive Landscape show?

Q1: Is there a dominant horizontal platform doing many things?
    YES → Does it do YOUR thing poorly? 
          YES → UNBUNDLE (extract the vertical)
          NO → Continue to Q2
    NO → Continue to Q2

Q2: Is there a single-purpose leader with validated market?
    YES → Can you price 60%+ lower for a niche?
          YES → UNDERCUT
          NO → Can you execute better (speed/UX)?
                YES → CLONE
                NO → Continue to Q3
    NO → Continue to Q3

Q3: Does target customer live in a platform ecosystem?
    YES → Does platform have marketplace/app store?
          YES → SLICE (build extension)
          NO → Continue to Q4
    NO → Continue to Q4

Q4: Is there a data/API integration gap between tools?
    YES → Is the data accessible (API/scraping)?
          YES → WRAPPER
          NO → Continue to Q5
    NO → Continue to Q5

Q5: Are existing solutions fundamentally broken?
    YES → Is pain severe enough for education investment?
          YES → INNOVATION
          NO → Reconsider market
    NO → Reconsider market or revisit Q1-Q4

Type: [Clone | Unbundle | Undercut | Slice | Wrapper | Innovation]
Confidence: [X]%
Primary Evidence: [CFD-XXX reference]
Classification Rationale: [2-3 sentences]

Pricing Constraint: [See references/gtm-constraints.md]
Channel Constraint: [See references/gtm-constraints.md]
Scope Constraint: [See references/gtm-constraints.md]
Timeline Implication: [See references/gtm-constraints.md]

© mattgierhart, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references, assets) in .claude/skills/prd-v02-product-type-classification of mattgierhart/PRD-driven-context-engineering.

• SKILL.md
• assets/classification.md
• references/decision-framework.md
• references/examples.md
• references/gtm-constraints.md

Open the folder on GitHubat commit 30ed1b0