القائمة
Define the measurement framework BEFORE launch. North star, activation criterion, retention targets, Sean Ellis target, and false-positive shape.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Slice a goal into the smallest feature slices that can each be PROVEN — every slice ships with a named eval and an end-to-end test, and a slice you can't evaluate or test doesn't get selected. Use after the goal is set and before the spec, so only provable features make the build.
Guided, stateful provisioning of a product's production stack — deep-links, key-format validation, a secrets backend (fnox recommended, or user-touched .env.local), a resumable ledger, CLI automation after signup, and a blocking A1–A10 live gate. Hands off to /security-check → /ship. The walked version of SETUP.md.
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
Launch the factory's control plane — scaffold and fill FACTORY-ORDERS (weekly mandate + hard budget), STANDING-ORDERS (autonomous-program authority), HEARTBEAT (weekly pulse), and write lifecycle gates for every registered product. A deliberate one-time ritual (re-run to audit); invoke as /factory-launch, not auto-triggered.
One-shot a new product — folders, Next.js starter, product.config.json, CLAUDE.md, scope.md, PRD skeleton, SETUP.md checklist. The Lovable-like ignition.
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
| name | metric-framework-designer |
| description | Define the measurement framework BEFORE launch. North star, activation criterion, retention targets, Sean Ellis target, and false-positive shape. |
| model_tier | sonnet |
Before a product's first real user. User says: "what should I track?", "set up metrics for X", "ready to launch — what do I measure?"
A products/<name>/metrics.md file:
## Metrics Framework — <product>
### North star metric
<single number> — what we optimize for above all else.
Why this one: <reasoning>
### Activation criterion
A user is "activated" when they: <specific action within Y minutes/days of signup>.
Why this defines "real" use: <reasoning>
### Retention targets
- Day 1: ≥ X% of activated users return
- Day 7: ≥ Y%
- Day 30: ≥ Z%
- Benchmarks based on <industry / similar-product reference>
### PMF target
Sean Ellis survey at N=40 active users: ≥40% answer "very disappointed" to "how would you feel if you could no longer use this?"
### False-positive shape (what would LOOK like PMF but isn't?)
1. <e.g. "spike from HN front page that decays in 7 days">
2. <e.g. "high signup rate but D7 retention < 20%">
3. <e.g. "founder's network signup dominance">
### Anti-metrics (things we deliberately don't optimize)
- <e.g. "page views" — vanity>
- <e.g. "signups without activation" — see above>
### Reporting cadence
- Daily: 1 number — yesterday's <NSM>
- Weekly: cohort retention curve + signup → activation funnel
- Monthly: revenue, churn, expansion (post-payments)
### Tracking implementation
- PostHog events to fire: <list of event names>
- PostHog dashboards to create: <list>
- GSC + Plausible: <what to watch>
scope.md and prd.md — what value does this product deliver?factory/playbooks/mvp-stage/measurement-framework.md for indie benchmarks by product type (SaaS, marketplace, content, tool).factory/playbooks/mvp-stage/sean-ellis-survey.md.mvp/builder as a task.factory/playbooks/mvp-stage/measurement-framework.mdfactory/playbooks/mvp-stage/sean-ellis-survey.mdfactory/playbooks/scale-stage/growth-loops-reforge.md (for understanding retention curves)