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]>
5.1 KiB
description, argument-hint, source
| description | argument-hint | source |
|---|---|---|
| Sprint lifecycle — plan a sprint, run a retrospective, or generate release notes | [plan|retro|release-notes] <context> | phuryn/pm-skills |
/sprint -- Sprint Lifecycle
Three modes covering the sprint lifecycle: plan for sprint planning, retro for retrospectives, release-notes for shipping communication.
Invocation
/sprint plan 2-week sprint, 4 engineers, focus on checkout improvements
/sprint retro [paste team feedback or sprint data]
/sprint release-notes [paste tickets, changelog, or PRD]
/sprint # asks which phase you're in
Modes
Plan Mode
Prepare for sprint planning with capacity estimation, story selection, and risk identification.
Workflow
Step 1: Gather Sprint Context
- Sprint duration (1 or 2 weeks)
- Team composition (engineers, designers, QA — and availability)
- Sprint goal or focus area
- Backlog items to consider (paste, upload, or describe)
- Any carry-over from last sprint
- Known interruptions (holidays, on-call, meetings)
Step 2: Estimate Capacity
Apply the sprint-plan skill:
- Calculate available engineering hours/points after meetings, on-call, PTO
- Apply a velocity adjustment based on historical data (if provided) or industry standard (70% of theoretical capacity)
- Show capacity breakdown per team member
Step 3: Select and Sequence Stories
- Recommend which stories fit within capacity
- Flag dependency chains (A must complete before B starts)
- Identify risks: stories that are underspecified, have external dependencies, or need design input
- Balance quick wins with larger items
- Ensure every story has acceptance criteria
Step 4: Generate Sprint Plan
## Sprint Plan: [Sprint Name/Number]
**Duration**: [dates]
**Sprint Goal**: [one sentence]
**Team**: [members and availability]
### Capacity
| Member | Available Days | Points/Hours | Notes |
|--------|--------------|-------------|-------|
**Total capacity**: [X] points/hours
**Recommended commitment**: [Y] points/hours (with buffer)
### Selected Stories
| # | Story | Points | Owner | Dependencies | Risk |
|---|-------|--------|-------|-------------|------|
### Sprint Risks
1. [Risk] — Mitigation: [action]
### Definition of Done
- [ ] Code reviewed
- [ ] Tests passing
- [ ] Deployed to staging
- [ ] QA approved
- [ ] Documentation updated (if applicable)
Retro Mode
Facilitate a structured retrospective that produces actionable improvements.
Workflow
Step 1: Gather Sprint Feedback
Accept input as:
- Team feedback (pasted from a survey, Slack, or collaborative doc)
- Sprint metrics (velocity, bugs, incidents)
- The user's own observations
Ask: "Which retro format do you prefer?"
- Start/Stop/Continue (simple, fast)
- 4Ls (Liked, Learned, Lacked, Longed for)
- Sailboat (Wind = helps, Anchor = slows, Rocks = risks, Island = goals)
Step 2: Analyze and Structure
Apply the retro skill:
- Categorize feedback into the chosen framework
- Identify themes and patterns
- Separate symptoms from root causes
- Highlight wins worth celebrating
Step 3: Generate Retro Summary
## Sprint Retrospective: [Sprint Name]
**Date**: [today]
**Format**: [Start/Stop/Continue | 4Ls | Sailboat]
**Participants**: [if known]
### What Went Well
[Grouped themes with supporting evidence]
### What Didn't Go Well
[Grouped themes with root cause analysis]
### Key Insights
[2-3 patterns that emerged]
### Action Items
| # | Action | Owner | Deadline | Priority |
|---|--------|-------|----------|----------|
### Metrics This Sprint
| Metric | This Sprint | Last Sprint | Trend |
|--------|-----------|------------|-------|
Release Notes Mode
Generate user-facing release notes from technical artifacts.
Workflow
Step 1: Accept Release Content
Accept:
- Jira/Linear tickets or changelog
- PRD or feature specs
- Git commit messages or PR descriptions
- Team's internal summary of what shipped
Step 2: Transform
Apply the release-notes skill:
- Translate technical language into user benefits
- Categorize as: New Features, Improvements, Bug Fixes
- Write in the product's voice (ask about tone if not clear)
- Highlight the most impactful change first
Step 3: Generate Release Notes
## What's New — [Version/Date]
### Highlights
[1-2 sentence summary of the most important change]
### New Features
- **[Feature Name]** — [user-facing benefit in plain language]
### Improvements
- **[Improvement]** — [what's better now]
### Bug Fixes
- Fixed [issue] that caused [user impact]
### Coming Soon
[Optional teaser for next release]
Save as markdown and offer to format for different channels (blog post, in-app, email, Slack announcement).
Notes
- For plan mode: protect 20% buffer for unplanned work — teams that plan at 100% capacity always miss
- For retro mode: focus on 2-3 high-impact action items, not 10 things nobody will do
- For release notes: always frame changes as user benefits, not technical implementations
- Each mode can chain to the others: plan → (sprint happens) → retro → release-notes