Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
Examples: Recommendation system, ML pipeline, analytics
Focus: Data quality, model metrics, scalability
Template style: Metrics-driven with data emphasis
Part 2: Product.md Writing Guide
Document Structure
# Mission & Strategy- What problem do we solve?
- Who are the users?
- What's our value proposition?
# Success Metrics- How do we measure impact?
- What are KPIs?
- How often do we measure?
What features are coming?
How are they prioritized?
# Next Features (SPEC Backlog)
-
-
Writing by Project Type
Web Application Product.md Focus:
User personas (team lead, individual contributor, customer)
Adoption targets (80% within 2 weeks)
Integration capabilities (Slack, GitHub, Jira)
Real-time collaboration features
Mobile Application Product.md Focus:
User personas (iOS users, Android users, power users)
Retention metrics (DAU, MAU, churn rate)
App store presence (rating target, download goal)
Offline capability requirements
Push notification strategy
Platform-specific features (GPS, camera, contacts)
Community engagement (issue response time, contributions)
Data Science Product.md Focus:
Model metrics (accuracy, precision, recall)
Data quality requirements
Scalability targets (1B+ records)
Integration with ML platforms (MLflow, W&B)
Part 3: Structure.md Writing Guide
Document Structure
# System Architecture- What's the overall design pattern?
- What layers/tiers exist?
- How do components interact?
# Core Modules- What are the main building blocks?
- What's each module responsible for?
- How do they communicate?
# External Integrations- What external systems do we depend on?
- How do we authenticate?
- What's our fallback strategy?
# Traceability- How do SPECs map to code?
- How do we trace changes?
Public API Surface
↓
Type Guards / Validation
↓
Core Logic
↓
Platform Adapters (Node.js, Browser, Deno)
Data Science Architecture:
Data Ingestion → Feature Engineering → Model Training → Inference
↓
Feature Store
↓
Model Registry
↓
Monitoring & Alerting
Part 4: Tech.md Writing Guide
Document Structure
# Technology Stack- What language(s)?
- What version ranges?
- Why these choices?
# Quality Gates- What's required to merge?
- How do we measure quality?
- What tools enforce standards?
# Security Policy- How do we manage secrets?
- How do we handle vulnerabilities?
- What's our incident response?
# Deployment Strategy- Where do we deploy?
- How do we release?
- How do we rollback?
Framework: Flutter 3.13 or React Native 0.72
Language: Dart or TypeScript
Testing: flutter test or Jest, 80%+ coverage
State Management: Riverpod, Bloc, or Redux
Local Database: SQLite, Hive, or Realm
HTTP Client: Dio or Axios wrapper
UI: Material Design or Cupertino
DevOps: Fastlane, GitHub Actions for app store deployment
Quality: flutter analyze, dart format, excellent test coverage
Performance: App size <50MB (iOS), startup <2s
CLI Tool:
Language: Go 1.21 or Python 3.13
Testing: Go's built-in testing or pytest
Packaging: Single binary (Go) or PyPI (Python)
Quality: golangci-lint or ruff, <100MB binary
Performance: <100ms startup time
Library:
Language: TypeScript 5.2 or Python 3.13
Testing: Vitest or pytest, 90%+ coverage (libraries = higher bar)
Package Manager: npm/pnpm or uv
Documentation: TSDoc/JSDoc or Google-style docstrings
Type Safety: TypeScript strict or mypy strict
Guide interactive creation of three core project documentation files (product.md, structure.md, tech.md) based on project type and user input. Provides templates, examples, checklists, and best practices for each project type (Web App, CLI Tool, Library, Data Science).
Core Content
Part 1: Project Type Selection
Ask user to identify their project type:
Web Application
Examples: SaaS, web dashboard, REST API backend
Focus: User personas, adoption metrics, real-time features
Examples: Recommendation system, ML pipeline, analytics
Focus: Data quality, model metrics, scalability
Template style: Metrics-driven with data emphasis
Part 2: Product.md Writing Guide
Document Structure
# Mission & Strategy- What problem do we solve?
- Who are the users?
- What's our value proposition?
# Success Metrics- How do we measure impact?
- What are KPIs?
- How often do we measure?
# Next Features (SPEC Backlog)- What features are coming?
- How are they prioritized?
Writing by Project Type
Web Application Product.md Focus:
User personas (team lead, individual contributor, customer)
Adoption targets (80% within 2 weeks)
Integration capabilities (Slack, GitHub, Jira)
Real-time collaboration features
Mobile Application Product.md Focus:
User personas (iOS users, Android users, power users)
Retention metrics (DAU, MAU, churn rate)
App store presence (rating target, download goal)
Offline capability requirements
Push notification strategy
Platform-specific features (GPS, camera, contacts)
Community engagement (issue response time, contributions)
Data Science Product.md Focus:
Model metrics (accuracy, precision, recall)
Data quality requirements
Scalability targets (1B+ records)
Integration with ML platforms (MLflow, W&B)
Part 3: Structure.md Writing Guide
Document Structure
# System Architecture- What's the overall design pattern?
- What layers/tiers exist?
- How do components interact?
# Core Modules- What are the main building blocks?
- What's each module responsible for?
- How do they communicate?
# External Integrations- What external systems do we depend on?
- How do we authenticate?
- What's our fallback strategy?
# Traceability- How do SPECs map to code?
- How do we trace changes?
Public API Surface
↓
Type Guards / Validation
↓
Core Logic
↓
Platform Adapters (Node.js, Browser, Deno)
Data Science Architecture:
Data Ingestion → Feature Engineering → Model Training → Inference
↓
Feature Store
↓
Model Registry
↓
Monitoring & Alerting
Part 4: Tech.md Writing Guide
Document Structure
# Technology Stack- What language(s)?
- What version ranges?
- Why these choices?
# Quality Gates- What's required to merge?
- How do we measure quality?
- What tools enforce standards?
# Security Policy- How do we manage secrets?
- How do we handle vulnerabilities?
- What's our incident response?
# Deployment Strategy- Where do we deploy?
- How do we release?
- How do we rollback?
Framework: Flutter 3.13 or React Native 0.72
Language: Dart or TypeScript
Testing: flutter test or Jest, 80%+ coverage
State Management: Riverpod, Bloc, or Redux
Local Database: SQLite, Hive, or Realm
HTTP Client: Dio or Axios wrapper
UI: Material Design or Cupertino
DevOps: Fastlane, GitHub Actions for app store deployment
Quality: flutter analyze, dart format, excellent test coverage
Performance: App size <50MB (iOS), startup <2s
CLI Tool:
Language: Go 1.21 or Python 3.13
Testing: Go's built-in testing or pytest
Packaging: Single binary (Go) or PyPI (Python)
Quality: golangci-lint or ruff, <100MB binary
Performance: <100ms startup time
Library:
Language: TypeScript 5.2 or Python 3.13
Testing: Vitest or pytest, 90%+ coverage (libraries = higher bar)
Package Manager: npm/pnpm or uv
Documentation: TSDoc/JSDoc or Google-style docstrings
Type Safety: TypeScript strict or mypy strict
