ai-first-engineering
affaan-m/everything-claude-code
Engineering operating model for teams shipping with AI-assisted code generation.
What is ai-first-engineering?
AI-First Engineering is a process framework for teams where AI agents generate significant implementation output. Use it to reshape planning, reviews, architecture, and testing practices to maximize quality and safety when working with AI-assisted development.
- Shift review focus from syntax to system behavior and risk assessment
- Design agent-friendly architectures with explicit boundaries and typed interfaces
- Establish higher testing standards for generated code with regression and edge-case coverage
- Define measurable acceptance criteria and high-signal prompts for AI agents
- Identify hiring signals for engineers who excel in AI-assisted environments
How to install ai-first-engineering
npx skills add https://github.com/affaan-m/everything-claude-code --skill ai-first-engineeringHow to use ai-first-engineering
- 1.Review the process shifts section to understand how planning, evaluation, and review priorities change with AI assistance
- 2.Audit your current architecture against the agent-friendly principles (explicit boundaries, stable contracts, typed interfaces)
- 3.Adapt code review checklists to focus on behavior, security, data integrity, and failure handling rather than style
- 4.Implement the higher testing standard with regression coverage and edge-case assertions for generated code
- 5.Evaluate and hire for the identified signals: decomposition skills, acceptance criteria definition, prompt quality, and risk control discipline
Use cases
- Restructuring code review processes when adopting AI pair programming at scale
- Designing system architecture to work well with AI code generation tools
- Setting up evaluation frameworks and test coverage standards for AI-generated features
- Training teams on decomposing ambiguous requirements into clear acceptance criteria
- Establishing rollout and risk control practices for AI-assisted development
- Engineering managers adopting AI-assisted development
- Architects designing systems for AI code generation
- Teams scaling from manual to AI-assisted implementation
- Tech leads establishing quality standards for generated code
ai-first-engineering FAQ
Review shifts from syntax and style (handled by automation) to system behavior, security assumptions, data integrity, failure handling, and rollout safety. The focus is on what the code does and its risks, not how it's formatted.
Prefer architectures with explicit boundaries, stable contracts, typed interfaces, and deterministic tests. Avoid implicit behavior spread across hidden conventions, as these are harder for AI agents to understand and maintain correctly.
Raise the testing bar with required regression coverage for touched domains, explicit edge-case assertions, and integration checks for interface boundaries. This compensates for the different failure modes of generated code.
Look for engineers who decompose ambiguous work cleanly, define measurable acceptance criteria, produce high-signal prompts and evals, and enforce risk controls under delivery pressure.
With AI handling implementation, the bottleneck shifts upstream. Clear requirements, measurable acceptance criteria, and well-decomposed tasks enable AI agents to generate better code and reduce rework.
Full instructions (SKILL.md)
Source of truth, from affaan-m/everything-claude-code.
name: ai-first-engineering description: Engineering operating model for teams where AI agents generate a large share of implementation output. metadata: origin: ECC
AI-First Engineering
Use this skill when designing process, reviews, and architecture for teams shipping with AI-assisted code generation.
Process Shifts
- Planning quality matters more than typing speed.
- Eval coverage matters more than anecdotal confidence.
- Review focus shifts from syntax to system behavior.
Architecture Requirements
Prefer architectures that are agent-friendly:
- explicit boundaries
- stable contracts
- typed interfaces
- deterministic tests
Avoid implicit behavior spread across hidden conventions.
Code Review in AI-First Teams
Review for:
- behavior regressions
- security assumptions
- data integrity
- failure handling
- rollout safety
Minimize time spent on style issues already covered by automation.
Hiring and Evaluation Signals
Strong AI-first engineers:
- decompose ambiguous work cleanly
- define measurable acceptance criteria
- produce high-signal prompts and evals
- enforce risk controls under delivery pressure
Testing Standard
Raise testing bar for generated code:
- required regression coverage for touched domains
- explicit edge-case assertions
- integration checks for interface boundaries
Related skills
More from affaan-m/everything-claude-code and the wider catalog.
security-review
Security checklist and patterns for authentication, input validation, secrets, and sensitive features.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable applications.
coding-standards
Baseline coding conventions for naming, readability, immutability, and quality across projects.
frontend-patterns
React and Next.js patterns for components, state management, performance, and modern frontend practices.
backend-patterns
REST/GraphQL API design, database optimization, and server-side patterns for Node.js, Express, and Next.js.
golang-testing
Go testing patterns: table-driven tests, subtests, benchmarks, fuzzing, and TDD methodology.