菜单
Map the competitive landscape by tier (direct/indirect/acquirer/adjacent) and argue why each could win. Antidote to competitor neglect.
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 | competitor-mapper |
| description | Map the competitive landscape by tier (direct/indirect/acquirer/adjacent) and argue why each could win. Antidote to competitor neglect. |
| model_tier | sonnet |
User asks: "who else does this?", "competitive landscape for X", "should I worry about Y?", "map the space"
## Competitive map — <space>
### Tier 1: Direct competitors (same problem, similar solution)
| Name | Stage / size | Pricing | Their angle | Why they could win | Their weakness |
|---|---|---|---|---|---|
| X | Series A, ~50 people | $49/mo | feature-rich | distribution | UX bloat |
### Tier 2: Indirect competitors (same problem, different solution shape)
| Name | What they do instead | Why users use them |
|---|---|---|
| X | spreadsheets | already paid for, familiar |
### Tier 3: Potential acquirers / adjacent players
| Name | Why they might enter | What it means for us |
|---|---|---|
| Big Co | already serves the customer; could bundle | exit option but also threat |
### Tier 4: The status quo
What users are doing today *without* any tool. Often the real competitor.
### The strongest argument against us
If a generalist competitor at Tier 3 ships this feature next quarter, what's our defense? <one paragraph>
### Our differentiation hypothesis
<one sentence — what's true about our approach that competitors can't easily copy>
### Disconfirming check
If our differentiation is "better UX": that's not defensible. If it's "we have the customer's data and workflows locked in via X": that's defensible. Be honest.
factory/playbooks/scale-stage/moat-building.md