Agent Skills
› NeverSight/learn-skills.dev
› agentic-engineering
agentic-engineering
GitHub指导AI作为代理工程师执行工程工作流。通过评估优先、任务分解和成本感知模型路由，实现自动化实施与人工质量控制的结合，确保高效且低风险的代码交付。
Trigger Scenarios
需要AI主导实现的复杂工程任务
涉及多步骤代码生成与重构的场景
需要在控制成本前提下进行架构设计或根因分析
Install
npx skills add NeverSight/learn-skills.dev --skill agentic-engineering -g -y
SKILL.md
Frontmatter
{
"name": "agentic-engineering",
"origin": "ECC",
"description": "Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing."
}
Agentic Engineering
Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.
Operating Principles
- Define completion criteria before execution.
- Decompose work into agent-sized units.
- Route model tiers by task complexity.
- Measure with evals and regression checks.
Eval-First Loop
- Define capability eval and regression eval.
- Run baseline and capture failure signatures.
- Execute implementation.
- 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.
Version History
- e0220ca Current 2026-07-05 23:50
