Back to Details

optimize-skill

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Workflow

工作流程

Follow these 5 steps in order. Copy this checklist into your response and check off each step as you complete it:
Task Progress:
- [ ] Step 1: Read the target skill
- [ ] Step 2: Run the quality checklist
- [ ] Step 3: Identify optimization opportunities
- [ ] Step 4: Apply optimizations
- [ ] Step 5: Validate improvements
请按顺序执行以下5个步骤。将此检查清单复制到你的回复中，并在完成每个步骤后勾选：
任务进度：
- [ ] 步骤1：阅读目标Skill
- [ ] 步骤2：运行质量检查清单
- [ ] 步骤3：识别优化机会
- [ ] 步骤4：实施优化
- [ ] 步骤5：验证改进效果

Step 1: Read the Target Skill

步骤1：阅读目标Skill

Read the target skill's SKILL.md and all files in its 
reference/
directory (if any).
Collect these metrics:
  • Total line count of SKILL.md
  • Total line count across all reference files
  • Frontmatter fields present vs. missing
  • Number of reference files and whether all are linked from SKILL.md
Report these metrics to the user before proceeding.
阅读目标Skill的SKILL.md文件及其
reference/
目录下的所有文件（如有）。
收集以下指标：
  • SKILL.md的总行数
  • 所有参考文件的总行数
  • 已存在的Frontmatter字段与缺失的字段
  • 参考文件的数量，以及所有文件是否均已在SKILL.md中关联
在继续下一步前，将这些指标反馈给用户。

Step 2: Run the Quality Checklist

步骤2：运行质量检查清单

Score each item in the quality checklist as PASS, FAIL, or N/A: -> See quality-checklist
Present the full scorecard to the user before making any changes. Ask for confirmation to proceed with optimizations.
为质量检查清单中的每一项打分，结果分为PASS（通过）、FAIL（失败）或N/A（不适用）： -> 参见quality-checklist
在进行任何修改前，将完整的评分卡反馈给用户，并请求确认是否继续优化。

Step 3: Identify Optimization Opportunities

步骤3：识别优化机会

Review all FAIL items from the checklist. Prioritize by impact (highest first):
  1. Description quality — Most common cause of skill not being invoked. Fix first.
  2. Content compression — Remove knowledge the agent already has. Reduces token cost and noise.
  3. Progressive disclosure — Split oversized SKILL.md into reference files, or merge tiny reference files back.
  4. Structure clarity — Improve headers, cross-references, and flow. Numbered steps for workflows.
  5. Consistency — Fix terminology, formatting, and style inconsistencies.
  6. Triggering precision — Under-triggering: add keywords, trigger phrases, concrete use cases. Over-triggering: add negative triggers ("Do NOT use for X"), narrow the scope.
List each optimization opportunity with:
  • What is wrong
  • Why it matters
  • What the fix will be
回顾检查清单中所有FAIL项，按影响优先级排序（从高到低）：
  1. 描述质量——Skill未被调用的最常见原因，优先修复。
  2. 内容压缩——移除Agent已有的知识，降低Token成本与冗余信息。
  3. 渐进式披露——将过大的SKILL.md拆分为参考文件，或将过小的参考文件合并回SKILL.md。
  4. 结构清晰度——优化标题、交叉引用与流程逻辑，为工作流程添加编号步骤。
  5. 一致性——修正术语、格式与风格的不一致问题。
  6. 触发精准性——触发不足：添加关键词、触发短语、具体用例；触发过度：添加负面触发规则（"请勿用于X场景"）、缩小适用范围。
列出每个优化机会，包含：
  • 问题所在
  • 影响原因
  • 修复方案

Step 4: Apply Optimizations

步骤4：实施优化

For each issue identified in Step 3, apply the fix. Use compression techniques where applicable: -> See compression-techniques
For each change, briefly explain what changed and why in your response (one line per change is sufficient).
针对步骤3中识别出的每个问题，实施修复。适用时使用压缩技术： -> 参见compression-techniques
对于每一项修改，在回复中简要说明修改内容及原因（每项修改一行即可）。

Step 5: Validate Improvements

步骤5：验证改进效果

After applying all optimizations:
  • Re-run the quality checklist — all previously FAIL items should now PASS
  • Verify SKILL.md is under 500 lines
  • Verify no content was lost — all original capabilities are preserved
  • Read the final SKILL.md end-to-end for coherence
  • Verify all reference file links resolve to existing files
  • Triggering test: Ask yourself "When would you use the [skill-name] skill?" — verify the description clearly communicates the skill's purpose and trigger conditions
Report the before/after metrics:
  • Line count: before -> after
  • Checklist score: X/Y PASS -> X/Y PASS
  • Key improvements made
完成所有优化后：
  • 重新运行质量检查清单——所有之前的FAIL项现在应全部PASS
  • 验证SKILL.md的行数不超过500行
  • 验证无内容丢失——所有原有功能均被保留
  • 通读最终版SKILL.md以确保逻辑连贯
  • 验证所有参考文件链接均指向存在的文件
  • 触发测试：自问“何时会使用[skill-name] Skill？”——验证描述是否清晰传达了Skill的用途与触发条件
反馈优化前后的指标对比：
  • 行数：优化前 -> 优化后
  • 检查清单得分：X/Y项通过 -> X/Y项通过
  • 关键改进内容

Output

输出结果

Deliver the optimized skill files to the user with a summary of all changes made and their rationale.
将优化后的Skill文件交付给用户，并附上所有修改内容及其理由的总结。