agentic-engineering — for Claude Code agentic-engineering, AIFlomo, community, for Claude Code, ide skills, agentic engineering, eval-first loop, task decomposition, model routing, code implementation automation, Claude Code

v1.0.0

关于此技能

Ideal for AI Agents like Cursor, Windsurf, or Claude Code needing streamlined code implementation through automated tasks and quality controls. Agentic engineering is an AI agent skill that streamlines code implementation by automating tasks and enforcing quality controls, benefiting developers and enhancing overall development efficiency.

功能特性

Define completion criteria using evals and regression checks
Decompose work into agent-sized units for efficient execution
Route model tiers by task complexity for optimized performance
Measure and compare deltas using eval-first loop

# 核心主题

robinxin robinxin
[1]
[0]
更新于: 3/19/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
20
Canonical Locale
en
Detected Body Locale
en

Ideal for AI Agents like Cursor, Windsurf, or Claude Code needing streamlined code implementation through automated tasks and quality controls. Agentic engineering is an AI agent skill that streamlines code implementation by automating tasks and enforcing quality controls, benefiting developers and enhancing overall development efficiency.

核心价值

Empowers agents to automate tasks, enforce quality controls, and enhance development efficiency using eval-first loops, task decomposition, and model routing with Haiku, Sonnet, and Opus models, while prioritizing invariants, edge cases, and error boundaries.

适用 Agent 类型

Ideal for AI Agents like Cursor, Windsurf, or Claude Code needing streamlined code implementation through automated tasks and quality controls.

赋予的主要能力 · agentic-engineering

Automating code implementation for reduced development time
Enforcing quality controls through evals and regression checks
Decomposing complex tasks into agent-sized units for efficient execution

! 使用限制与门槛

  • Requires clear definition of completion criteria and task complexity
  • Needs human oversight for quality and risk controls
  • Limited to tasks that can be decomposed into 15-minute units with clear done conditions

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

agentic-engineering 是什么?

Ideal for AI Agents like Cursor, Windsurf, or Claude Code needing streamlined code implementation through automated tasks and quality controls. Agentic engineering is an AI agent skill that streamlines code implementation by automating tasks and enforcing quality controls, benefiting developers and enhancing overall development efficiency.

如何安装 agentic-engineering?

运行命令:npx killer-skills add robinxin/AIFlomo/agentic-engineering。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

agentic-engineering 适用于哪些场景?

典型场景包括:Automating code implementation for reduced development time、Enforcing quality controls through evals and regression checks、Decomposing complex tasks into agent-sized units for efficient execution。

agentic-engineering 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

agentic-engineering 有哪些限制?

Requires clear definition of completion criteria and task complexity;Needs human oversight for quality and risk controls;Limited to tasks that can be decomposed into 15-minute units with clear done conditions。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add robinxin/AIFlomo/agentic-engineering。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    agentic-engineering 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Imported Repository Instructions

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

Supporting Evidence

agentic-engineering

Boost development efficiency with agentic engineering, an AI agent skill that automates code implementation and ensures quality control for developers.

SKILL.md
Readonly
Imported Repository Instructions
The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.
Supporting Evidence

Agentic Engineering

Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.

Operating Principles

  1. Define completion criteria before execution.
  2. Decompose work into agent-sized units.
  3. Route model tiers by task complexity.
  4. Measure with evals and regression checks.

Eval-First Loop

  1. Define capability eval and regression eval.
  2. Run baseline and capture failure signatures.
  3. Execute implementation.
  4. Re-run evals and compare deltas.

Task Decomposition

Apply the 15-minute unit rule:

  • each unit should be independently verifiable
  • each unit should have a single dominant risk
  • each unit should expose a clear done condition

Model Routing

  • Haiku: classification, boilerplate transforms, narrow edits
  • Sonnet: implementation and refactors
  • Opus: architecture, root-cause analysis, multi-file invariants

Session Strategy

  • Continue session for closely-coupled units.
  • Start fresh session after major phase transitions.
  • Compact after milestone completion, not during active debugging.

Review Focus for AI-Generated Code

Prioritize:

  • invariants and edge cases
  • error boundaries
  • security and auth assumptions
  • hidden coupling and rollout risk

Do not waste review cycles on style-only disagreements when automated format/lint already enforce style.

Cost Discipline

Track per task:

  • model
  • token estimate
  • retries
  • wall-clock time
  • success/failure

Escalate model tier only when lower tier fails with a clear reasoning gap.

相关技能

寻找 agentic-engineering 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具