$ loading_
Design AI-first engineering processes, architecture, reviews, and testing standards for teams.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "ai-first-engineering" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/ai-first-engineering/SKILL.md 2. Save it as ~/.claude/skills/ai-first-engineering/SKILL.md 3. Reload skills and tell me it's ready
Design an engineering process for an 8-person team using AI-assisted code generation. Focus on planning, acceptance criteria, review priorities, and pre-release checks.
A process recommendation tailored to AI-first teams, covering strong planning, measurable acceptance criteria, behavior-focused reviews, and rollout safety checks.
Based on AI-first engineering principles, create a code review checklist focused on behavior regressions, security assumptions, data integrity, failure handling, and rollout safety.
A practical checklist for reviewing generated code, with less emphasis on style and more on system behavior and risk controls.
Define testing standards for AI-generated code, including regression coverage, explicit edge-case assertions, and integration checks at interface boundaries.
A higher-bar testing standard to control generated code quality and reduce deployment risk.
Engineering leads can use this skill to redesign planning, review, and delivery workflows when teams rely heavily on AI-generated implementation. It shifts the focus from typing speed to planning quality, acceptance criteria, and behavior validation.
When teams want AI agents to contribute more reliably to development, this skill can guide architecture decisions. It emphasizes explicit boundaries, stable contracts, typed interfaces, and deterministic tests while avoiding hidden conventions.
In projects with a high share of generated code, teams can use this skill to enforce stricter review and testing standards. The focus is on regression coverage, edge-case assertions, interface integration checks, and safeguards for security, data integrity, and failure handling.
The document outlines the core principles of AI-First Engineering for teams shipping large amounts of AI-assisted code. It explains how process, architecture, code review, and testing should change in this model. Key themes include stronger planning quality, broader evaluation coverage, agent-friendly architectures with explicit boundaries and typed contracts, and review standards focused on behavior, security, data integrity, failure handling, and rollout safety.
Use this skill when designing process, reviews, and architecture for teams shipping with AI-assisted code generation.
Prefer architectures that are agent-friendly:
Avoid implicit behavior spread across hidden conventions.
Review for:
Minimize time spent on style issues already covered by automation.
Strong AI-first engineers:
Raise testing bar for generated code:
It is for designing an engineering operating model for teams that rely heavily on AI-assisted code generation. The provided material shows it covers process shifts, architecture requirements, code review focus, hiring signals, and testing standards.
The document emphasizes agent-friendly architecture such as explicit boundaries, stable contracts, typed interfaces, and deterministic tests. For reviews, it prioritizes behavior regressions, security assumptions, data integrity, failure handling, and rollout safety over style issues already handled by automation.
The provided material does not mention installation steps, API keys, or specific runtime requirements. For implementation or integration details, see the source repository.
Process documents with OCR, conversion, extraction, redaction, signing, and form filling.
Design security and risk controls for autonomous trading agents with transaction authority
Build polished React and Next.js animations with reusable production-ready patterns.
Verify Laravel projects with environment checks, tests, security scans, and release readiness.
Write and review React 18/19 components using modern best practices.
Conduct multi-source web research and produce cited, source-attributed reports.
Standardize planning, memory, verification, and review across AI coding agents.
Keep AI coding agents architecture-aware, verified, drift-checked, and safer over long tasks.
Provide coding rules and engineering guidance for AI coding agents.
Give AI coding agents design direction, UI code guidance, and critique.
Add engineering discipline to AI coding assistants across design, implementation, and review.
Equip AI coding agents with production-ready engineering and delivery skills.