mirror of
https://github.com/hanzoai/skills.git
synced 2026-11-19 00:47:36 +00:00
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]>
3.4 KiB
3.4 KiB
description, argument-hint, source
| description | argument-hint | source |
|---|---|---|
| Convert a feature-based roadmap into an outcome-focused roadmap that communicates strategic intent | <roadmap as text, file, or list of planned features> | phuryn/pm-skills |
/transform-roadmap -- Outcome-Focused Roadmap
Take a list of planned features or an output-focused roadmap and rewrite it as an outcome-focused roadmap that communicates why instead of what.
Invocation
/transform-roadmap [paste your feature list or roadmap]
/transform-roadmap [upload a roadmap doc, spreadsheet, or screenshot]
Workflow
Step 1: Accept the Current Roadmap
Accept in any format:
- Feature list or backlog items
- Roadmap document (Now/Next/Later, quarterly, timeline)
- Spreadsheet or Gantt chart export
- Screenshot of a roadmap tool
Parse each item to extract: feature name, description, target date/timeframe, and any context.
Step 2: Understand Strategic Context
Ask:
- What are the product goals or OKRs for this period?
- Who is the audience for this roadmap? (execs, engineering, customers, board)
- What format do you prefer? (Now/Next/Later, quarterly, timeline)
Step 3: Transform Each Item
Apply the outcome-roadmap skill:
For each feature/output on the roadmap:
- Identify the user or business outcome it's trying to achieve
- Rewrite as an outcome statement: "[Verb] [metric/experience] for [user segment]"
- Group features that serve the same outcome under one initiative
- Add success metrics to each outcome
Before → After examples:
- "Build SSO integration" → "Reduce enterprise onboarding friction — target: 50% faster time-to-first-value for enterprise accounts"
- "Redesign dashboard" → "Help power users find insights faster — target: 30% reduction in time-to-insight"
- "Add CSV export" → "Enable teams to share data outside the product — target: 25% increase in report sharing"
Step 4: Generate Transformed Roadmap
## Outcome-Focused Roadmap: [Product] — [Period]
**Strategic themes**: [2-3 high-level themes]
### Now (Current Quarter)
**Theme: [Strategic Theme]**
| Outcome | Success Metric | Key Initiatives | Status |
|---------|---------------|----------------|--------|
### Next (Next Quarter)
**Theme: [Strategic Theme]**
| Outcome | Success Metric | Key Initiatives | Confidence |
|---------|---------------|----------------|------------|
### Later (Future)
**Theme: [Strategic Theme]**
| Outcome | Success Metric | Key Initiatives | Dependencies |
|---------|---------------|----------------|-------------|
### Transformation Notes
| Original Feature | Transformed Outcome | Why This Framing |
|-----------------|--------------------|-----------------|
### What Changed
[Summary of how the roadmap narrative shifted]
Save as a markdown file.
Step 5: Review
Offer:
- "Want me to add OKR alignment for each outcome?"
- "Should I draft a stakeholder presentation of this roadmap?"
- "Want me to identify risks for the Now items?"
Notes
- Outcomes should be measurable and have a clear "done" state
- Multiple features can map to one outcome — this is a feature, not a bug
- If an output doesn't clearly serve an outcome, flag it for the user to justify or deprioritize
- The audience matters: exec roadmaps should be outcome-only, engineering roadmaps can include deliverables under each outcome
- "Later" items should be less specific — outcomes without committed solutions