菜单
Identify and deepen moats — workflow lock-in, data network effects, domain depth, integration depth. Audit current moats + propose investments.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | moat-builder |
| description | Identify and deepen moats — workflow lock-in, data network effects, domain depth, integration depth. Audit current moats + propose investments. |
| model_tier | opus |
Saved to products/<name>/scale/moat-YYYY-QN.md:
## Moat Assessment — <product> — <quarter>
### Moat inventory (current state)
| Moat type | Strength (1-5) | Evidence | Threat |
|---|---|---|---|
| Workflow lock-in | <n> | <e.g. avg user has 7 integrations> | <e.g. competitor offers easy import> |
| Data network effects | <n> | <e.g. 18 months of behavioral data> | <e.g. competitor has 10x our users> |
| Domain depth | <n> | <e.g. handle 340B drug program correctly> | <e.g. competitor hires our former PM> |
| Integration depth | <n> | <e.g. native to 12 tools> | <e.g. competitor is acquired by a tool we're not native to> |
| Brand / community | <n> | <e.g. 8K active forum, 100 user-generated tutorials> | <e.g. competitor sponsors our biggest YouTube channel> |
| Switching cost | <n> | <e.g. retraining takes 4 weeks> | <e.g. competitor pays for migration> |
### The 30-day-copy test
If a well-funded competitor copied our product 1:1 today, in 30 days they would have:
- Feature parity: yes/no
- Performance parity: yes/no
- Distribution parity: yes/no
- What we still have: <list — this IS our moat>
- What we don't have: <list — this is where we're exposed>
### Top 3 moat investments for next quarter
1. <investment> — moat type — expected impact — cost
2. ...
3. ...
### Workflow lock-in audit (per-customer)
For top 10 customers, document:
- Integrations they use (count)
- Workflows built on top (count + estimated switching cost)
- Custom data they've created in the product (volume)
- Score: deep / medium / surface
Most customers should be migrating from "surface" → "deep" over their lifetime. If 6+ months in and still surface = activation/onboarding problem.
### Data flywheel narrative
The story for product marketing:
> "<one-paragraph: how data → improvement → more users → more data, with a specific time horizon a competitor can't shortcut>"
metrics.md, recent retention analysis, customer interview synthesis.factory/playbooks/scale-stage/moat-building.mdfactory/playbooks/ai-native-2026/founders-playbook-distilled.md (re: workflow lock-in, data network effects, domain depth)