product-delivery — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited product-delivery (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
"The goal isn't shipping. The goal is learning whether your bet was right."
This skill covers the Delivery System — how we ship, measure, and learn. It runs discovery and delivery in parallel (dual-track), ships with staged rollouts, measures with a clear hierarchy, reflects through retrospectives, and executes GTM with precision.
Part of: Modern Product Operating Model — a collection of composable product skills.
Related skills: product-strategy, product-discovery, product-architecture, ai-native-product, product-leadership
Use this skill when:
Cadence: Continuous | Owner: Product Trio + GTM Team
Most teams either:
The Delivery System ensures shipping is the beginning of learning, not the end.
The Core Idea: Discovery and delivery happen simultaneously. While one bet is being built, the next bet is being shaped.
Week 1 Week 2 Week 3 Week 4 Week 5 Week 6
─────────────────────────────────────────────────────────
[ Discover Bet B ][ Shape Bet B ][ Discover Bet C ]
[ Build Bet A ][ Build Bet B ]
[ Ship A ] [ Ship B ]How It Works:
| Track | Activities | Who |
|---|---|---|
| Discovery Track | Interviews, OST updates, solution exploration, assumption tests | Full trio (PM heavy) |
| Delivery Track | Building, testing, shipping, measuring | Full trio (Eng heavy) |
Time Allocation (Example):
| Role | Discovery | Delivery |
|---|---|---|
| PM | 60% | 40% |
| Designer | 50% | 50% |
| Tech Lead | 30% | 70% |
Coordination Points:
0→1 Mode: Tracks may blur. Everyone does everything. Speed > separation.
Scaling Mode: Clear separation. Dedicated discovery time. Research ops support.
The Core Idea: Never ship to everyone at once. Start small, learn, expand.
Default Rollout Stages:
| Stage | Audience | Duration | Purpose |
|---|---|---|---|
| Stage 0: Internal | Team dogfooding | 1-3 days | Find obvious bugs |
| Stage 1: Alpha | 5-10 friendly customers | 1 week | Qualitative feedback |
| Stage 2: Beta | 10% of users | 1-2 weeks | Quantitative signal |
| Stage 3: GA | 100% of users | Ongoing | Full measurement |
Progression Criteria:
| From | To | Criteria |
|---|---|---|
| Internal → Alpha | Ready for external | No P0 bugs, core flow works |
| Alpha → Beta | Validated experience | Positive qualitative feedback, no major usability issues |
| Beta → GA | Metrics acceptable | Leading metrics trending right, no guardrail breaches |
Feature Flags:
Rollback Triggers:
0→1 Mode: Stages can be compressed. Alpha might be 3 customers for 2 days.
Scaling Mode: Formal stage gates. Release management. Beta programs.
The Three-Tier Model:
┌─────────────────────────────────────────────────────┐
│ LAGGING METRICS │
│ (Revenue, Retention, NPS) │
│ Move slowly, hard to attribute │
├─────────────────────────────────────────────────────┤
│ CORE METRICS │
│ (Activation, Engagement, Conversion) │
│ The outcomes your bets target │
├─────────────────────────────────────────────────────┤
│ LEADING METRICS │
│ (Feature adoption, Task completion) │
│ Move fast, early signal │
└─────────────────────────────────────────────────────┘Metric Types:
| Type | Definition | Example | Use For |
|---|---|---|---|
| Leading | Early signal, fast-moving, directly influenced by feature | Feature adoption rate, task completion rate | Weekly decisions, rollout gates |
| Core | Primary outcome you're targeting | Activation rate, conversion rate, engagement score | Bet success criteria |
| Lagging | Business results, slow-moving, influenced by many factors | Revenue, retention, NPS | Quarterly/annual planning |
| Guardrail | Metrics you won't let degrade | Performance, error rate, support tickets | Rollout gates, rollback triggers |
Hierarchy Example (Activation Bet):
Lagging: Revenue growth (quarterly)
↑
Core: Activation rate (weekly)
↑
Leading: Onboarding completion (daily)
First value action (daily)
↑
Guardrail: Support tickets (daily)
Error rate (real-time)Metric Selection Criteria:
| Criterion | Question |
|---|---|
| Measurable | Can we actually track this? |
| Actionable | Can we influence it with our work? |
| Attributable | Can we connect changes to our bet? |
| Timely | Will we see signal fast enough to decide? |
Dashboard Design:
The Core Idea: Every bet concludes with an explicit decision: Scale, Iterate, or Kill.
Retrospective Format:
BET RETROSPECTIVE: [Name]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Timebox: [Duration] | Shipped: [Date]
HYPOTHESIS REVIEW
Original: "We believed [X] would result in [Y]"
Result: [ ] Confirmed [ ] Disproved [ ] Inconclusive
METRICS REVIEW
| Metric | Target | Actual | Verdict |
|-----------|--------|--------|---------|
| Primary | [X] | [Y] | ✅ / ❌ |
| Secondary | [X] | [Y] | ✅ / ❌ |
| Guardrail | [X] | [Y] | ✅ / ❌ |
KEY LEARNINGS
• [Learning 1]
• [Learning 2]
• [Learning 3]
DECISION: [ ] SCALE [ ] ITERATE [ ] KILL
NEXT STEPS
• [Action 1]
• [Action 2]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━Decision Framework:
| Outcome | Criteria | Action |
|---|---|---|
| SCALE | Primary metric hit, no guardrail issues | Expand rollout, invest more |
| ITERATE | Signal positive but not at target | Refine and re-test (one more cycle) |
| KILL | Hypothesis disproved or too costly | Stop investment, document learning |
Iteration Limits:
Retrospective Cadence:
0→1 Mode: Informal but still explicit. Even a Slack message: "Bet X result: [Y]. Decision: [Z]."
Scaling Mode: Formal retrospective meetings. Learning database. Cross-team sharing.
The Core Idea: PM owns adoption, not just availability. GTM is part of delivery, not an afterthought.
GTM Components:
| Component | Owner | Timing |
|---|---|---|
| Positioning & messaging | PMM / PM | During solution shaping |
| Sales enablement | PMM / PM | Before beta |
| Documentation | PM / Tech Writer | Before beta |
| Support training | PM / Support Lead | Before GA |
| Launch communications | PMM / Marketing | At GA |
| Customer success playbook | CS / PM | Before GA |
Launch Tiers:
| Tier | Definition | GTM Effort |
|---|---|---|
| Tier 1 | Major new capability, strategic priority | Full GTM: press, event, sales training, campaign |
| Tier 2 | Significant improvement, notable value | Moderate GTM: blog, email, sales brief |
| Tier 3 | Incremental improvement, quality of life | Light GTM: changelog, in-app, support brief |
| Tier 4 | Bug fix, minor enhancement | No GTM: release notes only |
Launch Checklist (Tier 1/2):
| Phase | Tasks |
|---|---|
| Pre-launch | Positioning defined, Sales trained, Support trained, Docs ready, Success playbook ready |
| Launch | Announcement sent, In-app messaging live, Sales notified, Support notified |
| Post-launch | Feedback monitored, Metrics tracked, Issues triaged, Iteration planned |
Adoption Metrics (PM Responsibility):
| Metric | Definition |
|---|---|
| Awareness | % of target users who know feature exists |
| Trial | % of aware users who try feature |
| Adoption | % of trial users who continue using |
| Habit | % of adopters using regularly |
0→1 Mode: PM does GTM. Scrappy launches. Focus on learning, not polish.
Scaling Mode: PMM partnership. Launch playbooks. Integrated marketing calendar.
| Output | Description | Update Cadence |
|---|---|---|
| Rollout plan | Staged rollout with progression criteria | Per bet |
| Metrics dashboard | Leading, core, lagging, guardrail metrics | Continuous |
| Bet retrospective | Scale/Iterate/Kill decision with learnings | At timebox end |
| GTM checklist | Launch activities by tier | Per launch |
| Learning repository | Archive of bet results and learnings | After each retrospective |
This skill includes templates in the templates/ directory:
rollout-plan.md — Staged rollout checklistmetrics-hierarchy.md — Metrics design templatebet-retrospective.md — Retrospective format and decision frameworklaunch-checklist.md — GTM execution checklist by tierAsk Claude to:
| When you need to... | Use skill |
|---|---|
| Define what metrics ladder up to | product-strategy |
| Validate before delivery | product-discovery |
| Define what you're delivering | product-architecture |
| Adapt delivery for AI products | ai-native-product |
| Scale delivery across teams | product-leadership |
| Anti-Pattern | Why It Fails | Instead |
|---|---|---|
| Ship and forget | No learning, no improvement | Measure and retrospect |
| Big bang launch | Maximum risk, no learning | Staged rollout |
| Vanity metrics | Activity ≠ outcome | Hierarchical metrics |
| Zombie bets | Resources trapped, no clarity | Explicit Scale/Iterate/Kill |
| GTM afterthought | Features available but not adopted | GTM as part of delivery |
| Perfectionism | Never ships, never learns | Timebox and ship |
Before GA:
Part of the Modern Product Operating Model by Yannick Maurice
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.