zaxbysauce/agentic-engineering
.claude/skills/agentic-engineering/SKILL.md
作为代理工程师，采用评估优先执行、分解和成本感知模型路由进行操作。
data-ai
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add zaxbysauce/ragappv3 agentic-engineeringInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Mar 29, 2026, 5:52 AM36.2s1 file scanned
SKILL.md
- name:
- agentic-engineering
- description:
- 作为代理工程师，采用评估优先执行、分解和成本感知模型路由进行操作。
- origin:
- ECC
智能体工程
在 AI 智能体执行大部分实施工作、而人类负责质量与风险控制的工程工作流中使用此技能。
操作原则
- 在执行前定义完成标准。
- 将工作分解为智能体可处理的单元。
- 根据任务复杂度路由模型层级。
- 使用评估和回归检查进行度量。
评估优先循环
- 定义能力评估和回归评估。
- 运行基线并捕获失败特征。
- 执行实施。
- 重新运行评估并比较差异。
任务分解
应用 15 分钟单元规则：
- 每个单元应可独立验证
- 每个单元应有一个主要风险
- 每个单元应暴露一个清晰的完成条件
模型路由
- Haiku：分类、样板转换、狭窄编辑
- Sonnet：实施和重构
- Opus：架构、根因分析、多文件不变量
会话策略
- 对于紧密耦合的单元，继续使用同一会话。
- 在主要阶段转换后，启动新的会话。
- 在里程碑完成后进行压缩，而不是在主动调试期间。
AI 生成代码的审查重点
优先审查：
- 不变量和边界情况
- 错误边界
- 安全性和身份验证假设
- 隐藏的耦合和上线风险
当自动化格式化/代码检查工具已强制执行代码风格时，不要在仅涉及风格分歧的审查上浪费周期。
成本纪律
按任务跟踪：
- 模型
- 令牌估算
- 重试次数
- 实际用时
- 成功/失败
仅当较低层级的模型失败且存在清晰的推理差距时，才升级模型层级。
Related Skills
zaxbysauce/unswarm
development
VerifiedTrustedCommunity
Disable swarm mode for the current Claude Code session and return to normal behavior.
SKILL.mdUpdated Apr 16, 2026
zaxbysauce/swarm
development
VerifiedTrustedCommunity
Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.
SKILL.mdUpdated Apr 16, 2026
zaxbysauce/swarm-pr-review
tools
VerifiedTrustedCommunity
Run a swarm-like PR review using parallel exploration, independent reviewer validation, and critic challenge. Use for deep pull request review with low false-positive tolerance.
SKILL.mdUpdated Apr 16, 2026
zaxbysauce/.claude/skills/swarm-implement
development
VerifiedTrustedCommunity
--- name: swarm-implement description: Execute complex implementation work with a swarm-like Claude Code workflow: parallel exploration, scoped planning, selective deep validation, and independent reviewer/critic checks where risk justifies them. Use for feature work, bug fixes, refactors, and multi-file changes. disable-model-invocation: true --- # /swarm-implement Use this skill for implementation work when you want Claude Code to behave like a fast, high-quality swarm rather than a single-t
SKILL.mdUpdated Apr 16, 2026