Files
skills/commands/write-stories.md
zeekayandHanzo Dev 65c3b27843 160 marketing, growth and PM skills, on our own connectors
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]>
2026-09-15 01:27:26 -07:00

3.8 KiB

description, argument-hint, source
description argument-hint source
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria [user|job|wwa] <feature description or PRD> phuryn/pm-skills

/write-stories -- Backlog Item Generator

Break a feature into well-structured backlog items. Choose from three formats based on your team's preference, each with full acceptance criteria.

Invocation

/write-stories user Allow users to export reports as PDF and CSV
/write-stories job Notification system for task deadlines
/write-stories wwa Dark mode for the mobile app
/write-stories [upload a PRD or feature spec]      # asks format preference
/write-stories                                      # asks for feature and format

Formats

User Stories

Format: "As a [user type], I want [capability], so that [benefit]" Apply the user-stories skill:

  • Follow the 3 C's: Card (brief), Conversation (context), Confirmation (acceptance criteria)
  • Validate against INVEST: Independent, Negotiable, Valuable, Estimable, Small, Testable
  • Include design links or mockup references where relevant

Job Stories

Format: "When [situation], I want to [motivation], so I can [outcome]" Apply the job-stories skill:

  • Focus on the situation and context, not the user role
  • Ground in real user scenarios observed in research
  • Ideal for JTBD-oriented teams

WWA (Why-What-Acceptance)

Format: Why [strategic context] → What [deliverable] → Acceptance [criteria] Apply the wwas skill:

  • Includes strategic reasoning (why we're building this)
  • Produces independent, valuable, testable items
  • Good for cross-functional teams that need business context

Workflow

Step 1: Accept the Feature

Accept in any form: PRD, feature description, user research finding, or verbal idea. If a PRD is provided, extract the requirements to decompose.

Step 2: Determine Format

If not specified in the invocation, ask:

  • "Which format does your team use? User stories, Job stories, or WWA?"
  • If unsure, recommend user stories as the default

Step 3: Decompose the Feature

  • Break the feature into 5-15 independent stories (small enough to complete in one sprint)
  • Ensure each story is independently valuable (delivers user value on its own)
  • Order by dependency and priority
  • Write 3-5 acceptance criteria per story
  • Flag stories that need design input or technical spikes

Step 4: Generate Stories

## Backlog: [Feature Name]

**Format**: [User Stories / Job Stories / WWA]
**Total stories**: [count]
**Estimated total effort**: [if possible]

### Stories

#### Story 1: [Short title]
**[The story in chosen format]**

Acceptance Criteria:
- [ ] [Criterion 1]
- [ ] [Criterion 2]
- [ ] [Criterion 3]

Priority: [P0/P1/P2] | Effort: [S/M/L] | Dependencies: [none or list]

---
[Repeat for each story]

### Story Map
[Visual ordering: must-have → should-have → nice-to-have]

### Technical Notes
[Cross-cutting concerns: API changes, data migration, infrastructure]

### Open Questions
[Things that need answers before implementation can start]

Save as markdown.

Step 5: Offer Next Steps

  • "Want me to generate test scenarios for these stories?"
  • "Should I create dummy data for development and testing?"
  • "Want me to estimate sprint capacity for these stories?"
  • "Should I convert to a different format (user stories ↔ job stories ↔ WWA)?"

Notes

  • One story = one deployable unit of value — if it needs another story to be useful, they should be combined
  • Acceptance criteria should be testable by QA without additional interpretation
  • Error handling and edge cases deserve their own stories, not bullet points within a happy-path story
  • If the feature is large (15+ stories), suggest grouping into epics or phases
  • Flag any story that requires a spike (technical investigation before estimation is possible)