amplify
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseMANDATORY PREPARATION
强制准备
Invoke {{command_prefix}}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 {{command_prefix}}teach-maestro first.
Consult the tool-orchestration reference in the agent-workflow skill for adding tools effectively.
Take a working workflow and make it more capable. Amplification adds new abilities without breaking existing functionality.
调用 {{command_prefix}}agent-workflow —— 它包含了工作流原则、反模式，以及上下文收集协议。在继续操作前请遵循该协议——如果尚未存在工作流上下文，你必须首先运行 {{command_prefix}}teach-maestro。
参考agent-workflow技能中的工具编排指南来高效添加工具。
基于可正常运行的工作流进一步提升其能力。能力增强会在不破坏现有功能的前提下新增能力。
Amplification Strategies
增强策略
Better Prompts
- Add few-shot examples for edge cases the model currently mishandles
- Add chain-of-thought for tasks where reasoning quality matters
- Add negative instructions for common mistakes
- Upgrade output schema with more structured fields
Better Tools
- Add tools for capabilities the model currently lacks
- Improve existing tool descriptions for better selection accuracy
- Add confirmation steps for high-stakes operations
- Add tools for verification/validation of outputs
Better Context
- Add RAG for domain-specific knowledge
- Add real-time data sources for current information
- Add user profile/history for personalization
- Add project documentation as reference context
Better Models
- Upgrade to a more capable model for critical steps
- Use model cascading (cheap model for simple, capable model for complex)
- Add vision capabilities if processing images/documents
- Add code execution capabilities if generating code
更优提示词
- 针对模型当前处理不当的边缘场景添加小样本示例
- 对推理质量要求较高的任务添加思维链引导
- 针对常见错误添加否定指令
- 通过新增更多结构化字段升级输出schema
更优工具
- 新增工具来弥补模型当前缺失的能力
- 优化现有工具的描述以提升选择准确率
- 为高风险操作添加确认步骤
- 新增用于输出校验/验证的工具
更优上下文
- 为领域特定知识添加RAG
- 新增实时数据源来获取最新信息
- 新增用户画像/历史记录来实现个性化
- 引入项目文档作为参考上下文
更优模型
- 为关键步骤升级到能力更强的模型
- 使用模型级联（简单任务用低成本模型，复杂任务用高能力模型）
- 如果需要处理图像/文档则新增视觉能力
- 如果需要生成代码则新增代码执行能力
Amplification Process
增强流程
- Identify the gap: What can't the workflow do that it should?
- Choose the strategy: Which amplification approach addresses the gap?
- Implement incrementally: Add one capability at a time
- Verify: Run the evaluation suite to confirm improvement without regression
- 识别差距：工作流目前无法完成但应该具备的能力是什么？
- 选择策略：哪种增强方案可以解决该差距？
- 渐进式实现：每次仅新增一项能力
- 验证：运行评估套件确认能力得到提升且没有出现功能退化
Impact Assessment
影响评估
| Strategy | Cost Impact | Latency Impact | Quality Impact |
|---|---|---|---|
| Better prompts | None | None | Medium-High |
| Better tools | Low | Low-Medium | High |
| Better context (RAG) | Medium | Medium | High |
| Better models | High | Medium-High | High |
| 策略 | 成本影响 | 延迟影响 | 质量影响 |
|---|---|---|---|
| 更优提示词 | 无 | 无 | 中-高 |
| 更优工具 | 低 | 低-中 | 高 |
| 更优上下文（RAG） | 中 | 中 | 高 |
| 更优模型 | 高 | 中-高 | 高 |
Amplification Checklist
增强检查清单
- Gap identified with concrete evidence (not assumption)
- Single strategy selected (don't amplify everything at once)
- Baseline quality score recorded before change
- Change implemented and tested
- Quality score improved without regression
- Cost/latency impact documented
- 已通过具体证据（而非假设）识别出差距
- 已选定单一策略（不要一次性增强所有内容）
- 变更前已记录基线质量评分
- 变更已实现并经过测试
- 质量评分得到提升且无功能退化
- 已记录成本/延迟影响
Recommended Next Step
推荐后续步骤
After amplification, run to verify the new capability works, or to set up quality monitoring for the enhanced workflow.
{{command_prefix}}evaluate{{command_prefix}}iterateNEVER:
- Amplify without a specific gap to address (amplification without purpose is bloat)
- Add capabilities without testing them
- Upgrade models without recalculating cost
- Add tools without updating tool descriptions
完成增强后，运行 来验证新能力可正常运行，或运行 为增强后的工作流设置质量监控。
{{command_prefix}}evaluate{{command_prefix}}iterate绝对禁止：
- 没有明确要解决的差距就进行增强（无目的的增强只会导致臃肿）
- 新增能力但不进行测试
- 升级模型但不重新计算成本
- 新增工具但不更新工具描述