- Home
- Skills
- Mattgierhart
- Prd Driven Context Engineering
- Prd V02 Product Type Classification
prd-v02-product-type-classification_skill
- Python
17
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill mattgierhart/prd-driven-context-engineering --skill prd-v02-product-type-classification- SKILL.md5.1 KB
Overview
This skill classifies a proposed product approach into one of six types—Clone, Unbundle, Undercut, Slice, Wrapper, or Innovation—based on competitive landscape evidence. It runs after a v0.2 competitive analysis or when a team asks strategy questions like “clone or innovate?” or “is this a fast-follow opportunity?”. The output is a concise BR- style classification plus inherited GTM constraints to guide v0.3 outcome and go-to-market decisions.
How this skill works
The skill inspects v0.2 competitive landscape artifacts for specific signals: market leaders, platform breadth, pricing gaps, ecosystem presence, API/data access, and severity of user pain. It follows a decision flow that sequences checks (horizontal platform → single-purpose leader → platform ecosystem → integration gaps → broken solutions) and maps the highest-confidence match to a product type. It then emits a BR-style classification with confidence, primary evidence references, rationale, and the type-derived GTM constraints.
When to use it
- After completing v0.2 competitive landscape research
- When deciding between cloning, unbundling, undercutting, or innovating
- If you need to anchor MVP scope, pricing, or channel choices
- When assessing feasibility of marketplace plugins or API middleware
- Before drafting v0.3 outcome metrics and GTM playbook
Best practices
- Supply concrete evidence: revenue signals, MAU, price benchmarks, API docs
- Follow the decision flow sequentially to avoid false positives
- Require higher confidence for Slice/Wrapper/Undercut classifications
- Avoid labeling something 'Innovation' if competitor revenue exists
- Document primary evidence references for traceable rationale
Example use cases
- Team asks “should we clone or innovate?” and needs a recommended path and confidence level
- Competitive review shows a large horizontal platform; skill recommends Unbundle with supporting evidence
- Market has a single leader; skill assesses whether a 60%+ price play supports Undercut
- Product lives inside an ecosystem with an app store; skill suggests Slice and lists marketplace constraints
- Toolset lacks an integration layer and APIs are available; skill outputs Wrapper plus API feasibility notes
FAQ
You need clear failed alternatives, severe customer pain, and budget willingness; confidence threshold is very high (≈85%).
Can the skill switch a classification after new evidence?
Yes—rerun after updating the v0.2 landscape. The decision flow and confidence thresholds will adapt the result.