A 6-layer AI skill chain powered by an enterprise-grade deep research engine that produces an integrated product/platform strategy thesis — positioning AND a Now/Next/Later roadmap both fall out of one coherent strategy.
Built by Branded Mayhem Collective for Claude. Works in Claude.ai (web), Claude Code, Claude desktop, Cursor, and Codex CLI — anywhere SKILL.md is read.
The Productprint Engine uses an 8-phase deep research pipeline (scope, plan, retrieve, triangulate, synthesize, critique, refine, package) to gather evidence from hundreds of sources, then chains that evidence through 6 product strategy layers to produce a consulting-grade strategy thesis.
Input: A product or platform name, target user description, and 3-5 competitor or substitute product URLs.
Output: A complete Integrated Product Strategy Thesis with:
- Core Strategic Truth (the foundational user tension driving real adoption)
- Playing-to-Win cascade: where-to-play / how-to-win with evidence-gated elements (segments, JTBD outcomes, competitive capability map, economic engine, differentiation wedge)
- Strategic bets + prioritized Now/Next/Later roadmap (3 horizons, 18 months) + build/buy/partner decisions + risk register with leading indicators
- Positioning statement and ≤25-word product one-liner, bet narrative, strategy-on-a-page
- Assumption-test log: load-bearing assumptions extracted, falsification attempts, PROCEED/REFINE verdict
- Economic model with ranges (revenue model, pricing bands, unit economics scenarios)
- Full source bibliography (typically 400-1000+ research sources)
┌─────────────────────────────────────────────────────┐
│ DEEP RESEARCH ENGINE │
│ 8-phase pipeline: scope → plan → retrieve → │
│ triangulate → synthesize → critique → refine → │
│ package │
│ │
│ • 4 research modes (Quick/Standard/Deep/UltraDeep) │
│ • Parallel web search (5-10 concurrent queries) │
│ • Source credibility scoring (0-100) │
│ • Citation verification + anti-hallucination │
│ • Progressive file assembly for unlimited length │
└──────────────┬──────────────────────────────────────┘
│ powers every research-heavy layer
▼
Layer 1: Core Strategic Truth ── one validated sentence capturing user tension
|
v
Layer 2: Productprint Tier-A ── 10 strategy elements with evidence gates
|
v
Layer 3: Productprint Tier-B ── 5 strategy elements: bets, roadmap, build/buy/partner, prioritization, risk register
|
v
Layer 4: Productprint Tier-C ── 4 deployable positioning artifacts: positioning statement, one-liner, bet narrative, strategy-on-a-page
|
v
Layer 5: Thesis Stress-Test ── extracts load-bearing assumptions; tries to FALSIFY them; returns PROCEED or REFINE
|
+-- If REFINE --> re-run Layers 1-4 with constraint package injected (the magic)
|
+-- If PROCEED --v
|
Layer 6: Strategy Thesis Compiler ── integrated product strategy + Now/Next/Later roadmap
- A Claude account — works in Claude.ai (web), Claude Code (CLI), Claude desktop, Cursor, or Codex CLI. Any surface that reads SKILL.md.
- Claude Max or Pro subscription — the research phases are token-intensive
- Web search — built-in WebSearch works out of the box.
- Python 3.9+ — for research engine scripts (validation, citation verification)
- Optional: weasyprint (
pip install weasyprint) — for PDF output
Claude Code (plugin install — primary path):
/plugin marketplace add Branded-Mayhem-Collective-LLC/productprint-engine
/plugin install productprint-engine@bmc-productprint-engine
Claude.ai web / Claude Desktop:
In Claude.ai web, paste the repo URL into the chat and ask:
"Install the skills from https://github.com/Branded-Mayhem-Collective-LLC/productprint-engine"
Alternatively download the repo as a .zip (GitHub Code button → Download ZIP), unzip locally, then upload the skill folders via Settings → Customize → Skills.
In Claude Code:
/plugin list
You should see productprint-engine enabled, with skills available under /productprint-engine:<skill>.
Run the core-strategic-truth skill for [PRODUCT NAME].
Topic: [what it does]
Audience: [who uses it]
Region: [geographic market]
Mode: standard
The skills auto-chain. If they don't, prompt each tier manually:
- "Run productprint-tier-a using the Core Strategic Truth output as seed."
- "Run productprint-tier-b using the Tier-A output as seed."
- "Run productprint-tier-c using the Tier-A and Tier-B outputs as seeds."
Run the thesis-stress-test for [PRODUCT NAME].
Competitors:
1. [Competitor 1] - [URL]
2. [Competitor 2] - [URL]
3. [Competitor 3] - [URL]
Re-run Layers 1-4 with the constraint package from the stress-test injected as a hard constraint. Then re-run Layer 5 to confirm PROCEED.
Run the strategy-thesis-compiler.
Product: [PRODUCT NAME]
Client: [CLIENT NAME]
Prepared by: [YOUR FIRM NAME]
- CONTRACT.md — the domain-neutral skeleton both Brandprint and Productprint conform to. Six conformance points that define what makes a valid "print." Read this before modifying any layer.
/productprint-engine-guide— step-by-step runner guide, troubleshooting, and tips for best results.
productprint-engine/
|-- README.md # This file
|-- CONTRACT.md # Domain-neutral print skeleton (SSOT)
|-- skills/
|-- core-strategic-truth/ # Layer 1
| +-- references/
|-- productprint-tier-a/ # Layer 2
| +-- references/
|-- productprint-tier-b/ # Layer 3
| +-- references/
|-- productprint-tier-c/ # Layer 4
| +-- references/
|-- thesis-stress-test/ # Layer 5
| +-- references/
|-- strategy-thesis-compiler/ # Layer 6
| +-- references/
+-- productprint-engine-guide/ # Runner guide
+-- references/
Questions or issues? Contact michael@brandedmayhem.com
Built by Branded Mayhem Collective | Dallas, Texas