Menü
Engineering budget planning, headcount forecasting, infrastructure cost modeling and ROI analysis
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | engineering-budget |
| description | Engineering budget planning, headcount forecasting, infrastructure cost modeling and ROI analysis |
| category | management |
| preferred-model | sonnet |
| min-confidence | 0.8 |
| depends-on | ["engineering-metrics"] |
| estimated-tokens | 4000 |
| triggers | {} |
| tags | ["budget","headcount","roi","planning"] |
Headcount Plan:
┌──────────────────────────────────────────────────────┐
│ Role │ Current │ Q+1 │ Q+2 │ Q+3 │ Q+4 │
│ Sr Engineer │ 5 │ 6 │ 7 │ 7 │ 8 │
│ Mid Engineer │ 3 │ 4 │ 4 │ 5 │ 5 │
│ Jr Engineer │ 2 │ 2 │ 3 │ 3 │ 3 │
│ Tech Lead │ 1 │ 1 │ 2 │ 2 │ 2 │
│ DevOps/SRE │ 1 │ 1 │ 1 │ 2 │ 2 │
│ QA │ 1 │ 1 │ 2 │ 2 │ 2 │
├──────────────────────────────────────────────────────┤
│ Total │ 13 │ 15 │ 19 │ 21 │ 22 │
│ Cost/month │ XXk │ XXk │ XXk │ XXk │ XXk │
└──────────────────────────────────────────────────────┘
ROI = (Net Benefit / Cost) × 100
Where:
Net Benefit = Revenue Gain + Cost Savings - Implementation Cost
Example — Implementing caching layer:
Revenue Gain: R$0 (não gera receita direta)
Cost Savings: R$15k/mês (redução de 40% na conta AWS)
Implementation: R$30k (2 engineers × 2 weeks)
Payback Period: 30k / 15k = 2 meses
Annual ROI: ((15k × 12) - 30k) / 30k × 100 = 500%
# Investment Case: [Project Name]
## Problem
[What business problem this solves]
## Proposed Solution
[Technical approach in 2-3 sentences]
## Costs
| Item | One-time | Monthly | Annual |
|------|----------|---------|--------|
| Engineering time | R$XX | - | - |
| Infrastructure | - | R$XX | R$XX |
| Licenses | - | R$XX | R$XX |
| **Total** | **R$XX** | **R$XX** | **R$XX** |
## Benefits
| Benefit | Monthly Value | Annual Value |
|---------|--------------|-------------|
| [Quantified benefit 1] | R$XX | R$XX |
| [Quantified benefit 2] | R$XX | R$XX |
| **Total** | **R$XX** | **R$XX** |
## Key Metrics
- Payback period: X months
- 3-year ROI: XX%
- Risk level: Low/Medium/High
## Non-Quantifiable Benefits
- [Developer productivity improvement]
- [Reduced incident frequency]
- [Better user experience]
For SaaS/platform businesses:
Unit Economics:
Infrastructure cost = R$X/month
Transactions/month = N
Cost per transaction = R$X / N
Target: Cost per transaction should DECREASE as volume grows
Warning signs:
- Cost per transaction increasing → scaling problem
- Cost per transaction > 10% of revenue per transaction → margin problem
| Frequency | What to Review |
|---|---|
| Weekly | Cloud cost anomalies (spikes > 20%) |
| Monthly | Actual vs budget variance by category |
| Quarterly | Headcount plan, tool renewals, capacity planning |
| Annually | Full budget rebuild, vendor renegotiation, strategy alignment |
# Engineering Budget: [Period]
## Summary
| Category | Budget | Actual | Variance |
|----------|--------|--------|---------|
| People | R$XX | R$XX | +/-X% |
| Infrastructure | R$XX | R$XX | +/-X% |
| Tools & Services | R$XX | R$XX | +/-X% |
| **Total** | **R$XX** | **R$XX** | **+/-X%** |
## Key Variances
1. [Explanation of significant variances]
## Recommendations
1. [Budget adjustments needed]
2. [Cost optimization opportunities]
**Architecture Decision Record (ADR) — Philosophy-First**: Creates well-structured ADRs using a 3-phase process: (1) Define the architectural philosophy and identity of the system, (2) Explore options through the lens of that philosophy, (3) Adversarial review by a devil's advocate agent. Use this skill whenever the user wants to document a technical decision, create an ADR, record why a technology or approach was chosen, compare architectural alternatives, or mentions 'ADR', 'architecture decision', 'decision record', 'technical decision', 'why did we choose', or 'document this decision'. Also trigger when the user is evaluating trade-offs between technical approaches and wants to formalize the reasoning.
**AI/ML Engineering Review**: Reviews AI/ML systems for production readiness — model serving, MLOps pipelines, LLM integration patterns, prompt engineering, evaluation frameworks, and responsible AI. Covers model deployment, feature stores, experiment tracking, monitoring/drift detection, and AI safety. Use when the user mentions ML, AI, machine learning, model, LLM, GPT, Claude, embeddings, RAG, fine-tuning, MLOps, model serving, feature store, or any AI/ML infrastructure.
**API Documentation & Design (OpenAPI/Swagger)**: Helps write and review API documentation, generate OpenAPI/Swagger specs, design RESTful APIs, and document GraphQL schemas. Use whenever the user mentions 'API docs', 'Swagger', 'OpenAPI', 'API specification', 'API design', 'REST API', 'endpoint documentation', 'API contract', 'API versioning', 'GraphQL schema', 'API reference', or asks to document their API, generate a Swagger spec, design API endpoints, or review API contracts for consistency.
API Gateway design patterns including rate limiting, authentication, versioning, BFF and circuit breaking
ARB process design, RFC governance, decision log and technical review workflows
**Backend Code Review (Node.js, Java, Microservices)**: Expert review of backend code focusing on Node.js, Java, Clean Architecture, SOLID principles, microservices patterns, SQL/database design, messaging (Kafka, SQS, SNS), and payment flows. Use whenever the user wants a review of backend code, API design, service architecture, database queries, or mentions Node, Java, Spring, NestJS, Express, microservices, REST API, gRPC, or asks to review server-side code. Also trigger for database schema reviews, query optimization, and message queue patterns.