Ai First Engineering
- 1.4k installs
- 238k repo stars
- Updated August 5, 2026
- affaan-m/ecc
This is a copy of ai-first-engineering by affaan-m - installs and ranking accrue to the original listing.
ai-first-engineering is an ECC operating-model skill that structures process, architecture, code review, and testing standards for developers whose teams ship mostly AI-agent-generated implementation while preserving qua
About
ai-first-engineering from affaan-m/ecc is an ECC skill for designing process, review, and architecture when AI-assisted code generation drives most implementation output. It shifts emphasis from typing speed to plan quality, from personal confidence to evaluation coverage, and from syntax nitpicks to system behavior during review. Architecture guidance favors explicit boundaries, stable contracts, typed interfaces, and deterministic tests over implicit conventions. Review targets regressions, security assumptions, data integrity, failure handling, and rollout safety while minimizing style debates already covered by automation. Strong adoption signals include decomposing ambiguous work, defining measurable acceptance criteria, writing high-signal prompts and evaluations, and enforcing risk controls under deadline pressure.
- Shifts focus from typing speed to planning quality and eval coverage
- Defines agent-friendly architecture with explicit boundaries, stable contracts, typed interfaces and deterministic tests
- Changes code review emphasis to behavior regressions, security assumptions, data integrity, failure handling and rollout
- Outlines hiring signals for AI-first engineers who decompose work, define acceptance criteria, write high-signal prompts
- Raises testing standards for generated code with required regression coverage, explicit edge cases and interface integra
Ai First Engineering by the numbers
- 1,400 all-time installs (skills.sh)
- +83 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/affaan-m/ecc --skill ai-first-engineeringAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1.4k |
|---|---|
| repo stars | ★ 238k |
| Last updated | August 5, 2026 |
| Repository | affaan-m/ecc ↗ |
How do teams review AI-generated code safely?
Adopt an operating model where AI agents produce most of the implementation work while keeping quality, architecture, and reviews effective.
Who is it for?
Engineering teams where AI agents produce most implementation and need durable process, architecture, and review guardrails.
Skip if: Developers seeking one-off prompt tricks or teams with minimal AI-generated code and traditional manual-only workflows.
When should I use this skill?
The team adopts AI-heavy code generation and needs process, architecture, review, or testing operating standards.
What you get
Agent-friendly architecture guidelines, behavior-focused review checklists, elevated test standards, and measurable acceptance criteria.
- review checklists
- architecture guidelines
- test coverage standards
Files
AI ファーストエンジニアリング
AI 支援コード生成でリリースするチームのプロセス、レビュー、アーキテクチャを設計する際にこのスキルを使用します。
プロセスの変化
1. 計画の品質はタイピングスピードより重要。 2. 評価のカバレッジは個人的な自信より重要。 3. レビューの焦点は構文からシステムの動作へ。
アーキテクチャ要件
エージェントフレンドリーなアーキテクチャを優先する：
- 明示的な境界
- 安定したコントラクト
- 型付きインターフェース
- 決定論的なテスト
隠れた慣習に広がる暗黙の動作を避ける。
AI ファーストチームでのコードレビュー
レビュー対象：
- 動作のリグレッション
- セキュリティの前提
- データの整合性
- 障害処理
- ロールアウトの安全性
自動化によって既にカバーされているスタイルの問題に費やす時間を最小化する。
採用と評価シグナル
AI ファーストの強いエンジニア：
- 曖昧な作業を明確に分解する
- 測定可能な受け入れ基準を定義する
- 高シグナルのプロンプトと評価を生成する
- 納期プレッシャー下でリスクコントロールを強制する
テスト標準
生成されたコードのテストバーを引き上げる：
- 操作されたドメインに対する必須のリグレッションカバレッジ
- 明示的なエッジケースのアサーション
- インターフェース境界の統合チェック
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kHow it compares
Use ai-first-engineering for team-wide AI shipping standards; use single-purpose review or test skills for tactical tasks.
FAQ
What does ai-first-engineering change in code review?
ai-first-engineering redirects review from style and syntax toward behavior regressions, security assumptions, data integrity, failure handling, and rollout safety. Automated formatters should absorb low-signal style feedback.
What architecture does ai-first-engineering recommend?
ai-first-engineering prioritizes agent-friendly architecture with explicit module boundaries, stable contracts, typed interfaces, and deterministic tests. Implicit conventions and hidden behavioral assumptions should be eliminated.