Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.
中文简介正在准备中。当前显示原文说明。
sharpdeveye/maestro5912026年4月29日 更新
免费在 GitHub 公开
temper
Use when the workflow feels over-engineered, has premature optimizations, unnecessary abstraction layers, or complexity beyond actual requirements.
中文简介正在准备中。当前显示原文说明。
sharpdeveye/maestro星标 591(GitHub 591 + cccskills 0)
实测评分 未实测
查看安装方法包含的文件（1）
- SKILL.md2.6 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
MANDATORY PREPARATION
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the agent-architecture reference in the agent-workflow skill for topology patterns and when multi-agent is justified.
Pull back from over-engineering. The most common mistake isn't building too little — it's building too much.
Over-Engineering Detection
Signs you've over-engineered:
- Multi-agent for a single-agent problem
- Premature optimization before you have performance data
- Abstraction layers with one implementation
- Configuration for things that never change
- Evaluation loops on non-critical outputs
- Framework before features
The Complexity Test
For each component:
- Is this solving a problem we actually have? (not "might have")
- Is this the simplest solution that works?
- Would removing this break anything? (if not, remove it)
- Can someone new understand this in 5 minutes? (if not, simplify)
Tempering Strategies
Collapse Unnecessary Agents
OVER-ENGINEERED: User → Classifier → Router → Specialist → Formatter → Checker (6 components)
TEMPERED: User → Single Agent with good prompt (1 component, same quality)
Remove Premature Abstraction
OVER-ENGINEERED: class AgentOrchestrator with 5 strategy interfaces
TEMPERED: async function runWorkflow(input) — direct, readable
Simplify Configuration
OVER-ENGINEERED: config.yaml (200 lines, 47 params, 3 inheritance levels)
TEMPERED: config.yaml (20 lines, essential params only, sensible defaults)
What NOT to Temper
- Error handling — essential, not overhead
- Logging — saves you when things go wrong
- Input validation — prevents cascading failures
- Core guardrails — safety is non-negotiable
- The golden test set — how you know it still works
Recommended Next Step
After tempering, run /evaluate to confirm quality is preserved, or /diagnose for a full health check.
NEVER:
- Temper without measuring output quality before and after
- Remove error handling in the name of simplicity
- Simplify below the level of correctness
- Remove features users actively rely on
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Use when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.
中文简介正在准备中。当前显示原文说明。
sharpdeveye/maestro5912026年4月29日 更新
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.
中文简介正在准备中。当前显示原文说明。
sharpdeveye/maestro5912026年4月29日 更新
amplify
免费Use when the workflow works but needs to handle more complex cases or produce higher-quality output through better tools, context, prompts, or models.
中文简介正在准备中。当前显示原文说明。
sharpdeveye/maestro5912026年4月29日 更新
Use when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.
中文简介正在准备中。当前显示原文说明。
sharpdeveye/maestro5912026年4月29日 更新
capture
免费Capture a session summary — what was done, what decisions were made, and what to do next.
中文简介正在准备中。当前显示原文说明。
sharpdeveye/maestro5912026年4月29日 更新