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]>
3.9 KiB
3.9 KiB
description, argument-hint, source
| description | argument-hint | source |
|---|---|---|
| Create a comprehensive Product Requirements Document from a feature idea or problem statement | <feature or problem statement> | phuryn/pm-skills |
/write-prd -- Product Requirements Document
Create a structured PRD that aligns stakeholders and guides development. Accepts anything from a vague idea to a detailed brief.
Invocation
/write-prd SSO support for enterprise customers
/write-prd Users are dropping off during onboarding — we need to fix step 3
/write-prd [upload a brief, research doc, or strategy deck]
Workflow
Step 1: Understand the Feature
Accept the input in any form:
- A feature name ("SSO support")
- A problem statement ("Enterprise customers keep asking for centralized auth")
- A user request ("Users want to export their data as CSV")
- A vague idea ("We should do something about onboarding drop-off")
- An uploaded document (brief, research, Slack thread, email)
Step 2: Gather Context
Ask conversationally — most important questions first, fill gaps as you go:
- User problem: What problem does this solve? Who experiences it? How painful is it?
- Target users: Which user segment(s)? How many? What's their current workaround?
- Success metrics: How will we know this worked? What moves if we nail it?
- Constraints: Technical constraints, timeline, regulatory, dependencies on other teams?
- Prior art: Has this been attempted before? Existing solutions in the market?
- Scope preference: Full solution or phased approach?
If the user provides a document with context, extract what's available and only ask about gaps.
Step 3: Generate the PRD
Apply the create-prd skill to produce an 8-section document:
## Product Requirements Document: [Feature Name]
**Author**: [user]
**Date**: [today]
**Status**: Draft
**Stakeholders**: [if known]
### 1. Executive Summary
[2-3 sentences: what, for whom, why now]
### 2. Background & Context
[Problem space, prior research, market context, what prompted this]
### 3. Objectives & Success Metrics
**Goals** (what success looks like):
1. [Specific, measurable goal]
2. [...]
**Non-Goals** (explicitly out of scope):
1. [What we're not doing, and why]
2. [...]
**Success Metrics**:
| Metric | Current | Target | Measurement |
|--------|---------|--------|-------------|
### 4. Target Users & Segments
[Who this serves, user profiles, segment sizing]
### 5. User Stories & Requirements
**P0 — Must Have**:
| # | User Story | Acceptance Criteria |
|---|-----------|-------------------|
**P1 — Should Have**:
| # | User Story | Acceptance Criteria |
|---|-----------|-------------------|
**P2 — Nice to Have / Future**:
| # | User Story | Acceptance Criteria |
|---|-----------|-------------------|
### 6. Solution Overview
[High-level approach, key design decisions, technical approach if known]
### 7. Open Questions
| Question | Owner | Deadline |
|----------|-------|----------|
### 8. Timeline & Phasing
[Milestones, dependencies, phasing if applicable]
Step 4: Review and Iterate
After generating, offer:
- "Want me to tighten the scope? I can challenge which P1s should really be P2s."
- "Should I run a pre-mortem on this PRD?"
- "Want me to break this into user stories for engineering?"
- "Should I create a stakeholder update to socialize this?"
Save the PRD as a markdown file to the user's workspace.
Notes
- Be opinionated about scope — a tight PRD is better than an expansive vague one
- If the idea is too big, proactively suggest phasing and spec only Phase 1
- Non-goals are as important as goals — they prevent scope creep
- Success metrics must be specific: "improve NPS" is bad, "increase NPS from 32 to 45 within 90 days of launch" is good
- Open questions should be genuinely unresolved — don't list things you can answer from context
- If the user provides research, weave insights into the Background section with attribution