Four MIT collections ported — growthOS, openclaw-marketing-skills, Marketing-Skills and pm-skills — as 160 skills, 12 agents and 45 commands, each naming its origin in its own frontmatter so the tree can be checked against THIRD_PARTY_NOTICES rather than trusted. Sixteen names appeared in more than one collection and none of the copies were identical; the longest wins, which lands on the more developed text where they genuinely diverge. A fifth collection is deliberately absent. awesome-growth-hacking-skills carries NO licence, which leaves its author every right by default — and it is a list of links rather than a collection of skills, so there is nothing in it to port and no permission to port it with. It is cited as a directory to read. THE CONNECTOR SKILLS ARE REWRITTEN, not ported. They arrived installing vendor SDKs, running OAuth flows of their own, and ending with long-lived credentials in JSON files under .agents/ and ~/.growthos/ at mode 600. That is a secret on a disk with no rotation path, protected from other users and not from the agent — and one auth implementation per skill. Hanzo holds these connectors in Go, per user, sealed in KMS, so `connect` is the one home for the flow and the platform skills defer to it by provider id: google_ads, meta_ads, x. It is reachable as HTTP or as MCP tools at api.hanzo.ai/v1/mcp — the same routes, typed once in Go, so a tool and a curl cannot disagree. Two had nothing real behind them and now say so. There is no search_console provider, so that skill names what does answer the same questions (google_analytics, google_bigquery) and states that the remedy is a provider in hanzoai/cloud rather than a vendor SDK here. And getxapi-connect was a wrapper around a paid reseller of X's public data with the vendor's key in an env var; it is `listen` now, on our own x connector — a skill named after a vendor makes the vendor the capability and dies with it. The skills referenced paths that only existed inside the source repo, so the shared material they read is ported to reference/ and the paths rewritten. Three skills need the growthOS APPLICATION rather than its data; per the estate's own split an application belongs in hanzoai/ads, social, email or sms as a cloud plugin, so those three say what they need instead of carrying an import that resolves to nothing. Third-party product names are out of our prose and kept in the notices, which is where the licence requires them and the only place they belong. A skill's persona names a role, not somebody else's product. Co-authored-by: Hanzo Dev <[email protected]>
5.9 KiB
description, argument-hint, source
| description | argument-hint | source |
|---|---|---|
| Explore business models using Lean Canvas, Business Model Canvas, Startup Canvas, or Value Proposition frameworks | [lean|full|startup|value-prop] <product or business> | phuryn/pm-skills |
/business-model -- Business Model Exploration
Build and analyze business models using four complementary frameworks. Choose one or run all for a complete picture.
Invocation
/business-model lean Marketplace connecting freelance PMs with startups
/business-model full Enterprise analytics platform
/business-model startup AI writing tool for non-native English speakers
/business-model value-prop SaaS onboarding tool
/business-model all SaaS onboarding tool # runs all four
/business-model # asks what you need
Modes
Lean Canvas Mode
Best for: Early-stage ideas, startups, new product lines.
Apply the lean-canvas skill to produce a complete Lean Canvas:
## Lean Canvas: [Product]
| Problem (Top 3) | Solution | Unique Value Proposition |
|-----------------|----------|------------------------|
| 1. [problem] | [solution to each] | [single clear message] |
| 2. [problem] | | |
| 3. [problem] | | |
| Key Metrics | Unfair Advantage |
|------------|-----------------|
| [what you measure] | [what can't be copied] |
| Channels | Customer Segments |
|---------|------------------|
| [how you reach them] | [who, early adopters first] |
| Cost Structure | Revenue Streams |
|---------------|----------------|
| [fixed + variable] | [how you make money] |
### Riskiest Assumptions
[What must be true for this to work — prioritized by risk]
### Experiments to Run
[How to validate the riskiest assumptions cheaply]
Full Business Model Canvas Mode
Best for: Established products, strategic planning, investor materials.
Apply the business-model skill to produce all 9 building blocks:
## Business Model Canvas: [Product]
| Key Partners | Key Activities | Value Propositions | Customer Relationships | Customer Segments |
|-------------|---------------|-------------------|----------------------|------------------|
| [who helps you] | [core actions] | [why customers choose you] | [how you interact] | [who you serve] |
| Key Resources | | Channels | |
|-------------|---|---------|---|
| [what you need] | | [how you deliver] | |
| Cost Structure | Revenue Streams |
|---------------|----------------|
| [your costs] | [your revenue] |
### Analysis
[Strengths and weaknesses of this model]
[How the pieces reinforce each other]
[Vulnerabilities and dependencies]
Startup Canvas Mode
Best for: New products and startups that need both strategy and business model in one artifact. Recommended over Lean Canvas and BMC for new products.
Apply the startup-canvas skill to produce a Startup Canvas with 9 strategy sections + business model:
## Startup Canvas: [Product]
### Part 1: Product Strategy
| Vision | Market Segments | Relative Costs |
|--------|----------------|---------------|
| [inspiring why] | [JTBD, first segment] | [low cost vs unique value] |
| Value Proposition | Trade-offs | Key Metrics |
|------------------|-----------|------------|
| [What before → How → What after → Alternatives] | [what you won't do] | [North Star + OMTM] |
| Growth | Capabilities | Can't/Won't |
|--------|-------------|------------|
| [PLG vs Sales-Led, channels] | [build vs partner] | [why competitors can't copy] |
### Part 2: Business Model
| Cost Structure | Revenue Streams |
|---------------|----------------|
| [fixed + variable, how they scale] | [pricing model, revenue per channel] |
### Strategy Coherence Check
[Do all elements reinforce each other?]
### Riskiest Assumptions
[What must be true — and how to test it]
Value Proposition Mode
Best for: Refining messaging, understanding user value, product-market fit analysis.
Apply the value-proposition skill to produce a JTBD-framed value proposition:
## Value Proposition: [Product]
### For [Segment]:
1. **Who**: [target user profile]
2. **Why**: [the job they're trying to do]
3. **What Before**: [their current painful reality]
4. **How**: [your solution approach]
5. **What After**: [their improved reality]
6. **Alternatives**: [what they'd use without you, and why you're better]
### Value Proposition Statement
[One sentence: For [who] who [need], [product] is a [category] that [benefit]. Unlike [alternative], we [differentiator].]
All Mode
Runs all four frameworks and adds a synthesis section comparing insights across frameworks.
Workflow (All Modes)
Step 1: Gather Context
Ask:
- What is the product or business idea?
- What stage? (idea, validated, scaling)
- Any existing business model to refine?
- Who is the target customer?
Step 2: Generate the Selected Framework(s)
Apply the relevant skill(s) as described above.
Step 3: Save and Iterate
Save as markdown. Offer:
- "Want me to stress-test this model with a SWOT or PESTLE analysis?"
- "Should I design a pricing strategy for the revenue streams?"
- "Want me to build a strategy canvas around this model?"
- "Should I identify the beachhead segment?"
Notes
- Startup Canvas is the recommended starting point for new products — it separates strategy from business model and covers what BMC and Lean Canvas miss (vision, trade-offs, metrics, Can't/Won't)
- Lean Canvas is best for speed and hypothesis testing — don't overthink it, but be aware it mixes strategy and business model into one artifact
- BMC is better for mature businesses that need to articulate how everything connects, but lacks strategic sections (vision, trade-offs, metrics)
- Value Proposition is the sharpest tool for product-market fit conversations
- In "all" mode, highlight where frameworks agree (strong signal) and where they diverge (needs investigation)