一键导入
feature-scaffold
Scaffold new features with standard file structure before implementation
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。
菜单
Scaffold new features with standard file structure before implementation
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
Builds production-grade Claude Projects and CustomGPTs, improves AI output quality using meta-thinking prompts, and architects self-improving AI systems. Use proactively when a founder wants to build a reliable AI workflow, automate a repeatable task with AI, improve the quality of AI outputs they're getting, feels stuck with generic AI responses, or wants to build internal tools powered by Claude. Trigger for "build a Claude project", "my AI outputs are generic", "how do I make Claude more specific", "build an AI workflow", "automate this with AI", or "my prompts aren't working".
One-command review pipeline. Chains CEO review → design review → eng review automatically. Surfaces only taste decisions for PD approval. Everything else runs autonomously.
Performance baseline measurement. Captures page load times, Core Web Vitals, and resource sizes. Compare before/after on every PR.
Playbook for bootstrapped and early-stage SaaS founders based on proven case studies ($0 to $5M ARR with 6 people, and creator-to-business flywheel models). Use proactively when a founder is bootstrapped or capital-efficient, needs to grow without paid acquisition, is facing a churn crisis, wants to build a freemium or usage-based model, or asks "how do I grow without VC money". Also trigger for "PLG", "inbound-led outbound", "creator-led growth", "build in public", or "how did [bootstrapped company] grow".
Real browser automation for testing, QA, and demo verification. Provides Playwright-based browser control for navigating the live app, clicking elements, filling forms, taking screenshots, and verifying visual state.
Post-deploy monitoring. After release-engineer pushes to production, canary watches the live site for errors, performance regressions, and page failures.
| name | feature-scaffold |
| description | Scaffold new features with standard file structure before implementation |
| used_by | ["frontend-dev","backend-dev","ceo-thinking-partner"] |
When building a NEW feature (not modifying existing), scaffold first, implement second. Rule: Never write business logic until the scaffold compiles with ZERO TypeScript errors.
src/pages/[FeatureName]Page.tsx — empty with TODO commentssrc/components/[feature-name]/index.ts with exportssrc/services/[featureName]Service.ts — typed functions returning mock datasrc/types/[featureName].ts — interfaces only, no logicbackend/src/routes/[feature-name].ts — Hono route handlers as TODO stubsbackend/src/index.tsbackend/migrations/XXXX_[feature].sql — schema only, no databackend/src/types/ — TypeScript interfaces matching the schemaBefore writing any business logic:
npx tsc --noEmit — ZERO errors (all stubs are typed)Only after all boxes checked: start implementing feature logic.
Frontend scaffold:
src/pages/ReportPage.tsx ← empty page, route added
src/components/report/ ← empty dir, index.ts
src/services/reportService.ts ← getReports(): Promise<Report[]> returns []
src/types/report.ts ← interface Report { id: string; ... }
Backend scaffold:
backend/src/routes/report.ts ← GET /api/report → { reports: [] }
backend/migrations/0016_reports.sql ← CREATE TABLE ...
backend/src/index.ts ← app.route('/api/report', reportRoutes)
Verify: npx tsc --noEmit → CLEAN
Then: implement business logic