ai-first-engineering
- Use it when:
- You're setting process, review gates or ownership rules for a team whose code is largely written by agents.
- It does:
- Shifts the weight from typing to planning, from anecdotes to eval coverage, and from reviewing syntax to reviewing system behavior.
- You get:
- Rules for agent-friendly architecture, what reviews should check, hiring signals and a higher testing bar for generated code.
- Length:
- One short page of principles, with no steps or tools.
TL;DR
A short operating model from ECC for teams where agents write much of the implementation. It asks for architectures agents can work in safely: explicit boundaries, stable contracts, typed interfaces and deterministic tests, without behavior spread across hidden conventions. Code review focuses on behavior regressions, security assumptions, data integrity, failure handling and rollout safety, leaving style to automation. Strong engineers in such a team decompose ambiguous work, define measurable acceptance criteria, write high-signal prompts and evals, and keep risk controls under delivery pressure. Generated code meets a higher testing bar: regression coverage for every touched domain, explicit edge-case assertions and integration checks at interface boundaries.
Summarizes the skill at d2ef268.
npx skills add https://github.com/affaan-m/ecc --skill ai-first-engineering skills.sh pageSource on GitHubAll skills from affaan-m/ecc
- Total Downloads
- 5,500 on skills.sh, Nov 9, 2026
- Repo stars
- 299,776 affaan-m/ecc
- First seen
- May 19, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 262 |
| Sep 28 | 160 |
| Oct 5 | 138 |
| Oct 12 | 237 |
| Oct 19 | 411 |
| Oct 26 | 403 |
| Nov 2 | 473 |
| Nov 9 | 446 |
| Category |
Test-first work, implementation from specs, git hygiene and scope control. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills. |
|---|---|
| Type |
Knowledge and rules the agent applies while it works: best practices, design principles, API references. |
| Effect |
Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code. |
| Needs |
Instructions only. Works in any agent that supports skills. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics |
SKILL.md
From affaan-m/ecc at d2ef268. Checked daily, last changed Nov 6, 2026.
Frontmatter
name: ai-first-engineering
description: Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.
metadata:
origin: ECCAI-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