---
id: ssh2-agentic-engineering
name: "agentic-engineering"
url: https://skills.yangsir.net/skill/ssh2-agentic-engineering
author: affaan-m
domain: ai-agent-core-development
tags: ["ai-agent-design", "multi-agent-systems", "autonomous-systems", "agent-orchestration", "llm-powered-agents"]
install_count: 4300
rating: 4.40 (20 reviews)
github: https://github.com/affaan-m/everything-claude-code
---

# agentic-engineering

> 运用智能体工程方法，通过“评估优先”执行策略，优化AI系统开发流程，提升模型性能与可靠性。

**Stats**: 4,300 installs · 4.4/5 (20 reviews)

## Before / After 对比

### Agentic工程，提升AI任务开发效率

## Readme

# 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.


---
*Source: https://skills.yangsir.net/skill/ssh2-agentic-engineering*
*Markdown mirror: https://skills.yangsir.net/api/skill/ssh2-agentic-engineering/markdown*