sensei

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Sensei

"A true master teaches not by telling, but by refining." - The Skill Sensei

Automates skill frontmatter improvement using the Ralph loop pattern - iteratively improving skills until they reach Medium-High compliance with passing tests, then checking token usage and prompting for action.

“真正的大师不是通过说教，而是通过打磨来传授技艺。” —— Skill Sensei

使用Ralph循环模式自动完成Skill frontmatter的改进——迭代优化Skill，直至其达到中高合规性且测试通过，随后检查令牌使用情况并提示用户采取行动。

Help

帮助

When user says "sensei help" or asks how to use sensei, show this:

╔══════════════════════════════════════════════════════════════════╗
║  SENSEI - Skill Frontmatter Compliance Improver                  ║
╠══════════════════════════════════════════════════════════════════╣
║                                                                  ║
║  USAGE:                                                          ║
║    Run sensei on <skill-name>              # Single skill        ║
║    Run sensei on <skill-name> --skip-integration  # Fast mode    ║
║    Run sensei on <skill1>, <skill2>, ...   # Multiple skills     ║
║    Run sensei on all Low-adherence skills  # Batch by score      ║
║    Run sensei on all skills                # All skills       ║
║                                                                  ║
║  EXAMPLES:                                                       ║
║    Run sensei on appinsights-instrumentation                     ║
║    Run sensei on azure-security --skip-integration               ║
║    Run sensei on azure-security, azure-networking                ║
║    Run sensei on all Low-adherence skills                        ║
║                                                                  ║
║  WHAT IT DOES:                                                   ║
║    1. READ    - Load skill's SKILL.md, tests, and token count    ║
║    2. SCORE   - Check compliance (Low/Medium/Medium-High/High)   ║
║    3. SCAFFOLD- Create tests from template if missing            ║
║    4. IMPROVE - Add USE FOR triggers + DO NOT USE FOR            ║
║    5. TEST    - Run tests, fix if needed                         ║
║    6. TOKENS  - Check token budget, gather suggestions           ║
║    7. SUMMARY - Show before/after with suggestions               ║
║    8. PROMPT  - Ask: Commit, Create Issue, or Skip?              ║
║    9. REPEAT  - Until Medium-High score + tests pass             ║
║                                                                  ║
║  TARGET SCORE: Medium-High                                       ║
║    ✓ Description > 150 chars                                     ║
║    ✓ Has "USE FOR:" trigger phrases                              ║
║    ✓ Has "DO NOT USE FOR:" anti-triggers                         ║
║    ✓ SKILL.md < 500 tokens (soft limit)                          ║
║                                                                  ║
║  MORE INFO:                                                      ║
║    See .github/skills/sensei/README.md for full documentation    ║
║                                                                  ║
╚══════════════════════════════════════════════════════════════════╝

当用户输入“sensei help”或询问如何使用sensei时，显示以下内容：

╔══════════════════════════════════════════════════════════════════╗
║  SENSEI - Skill Frontmatter合规性提升工具                          ║
╠══════════════════════════════════════════════════════════════════╣
║                                                                  ║
║  使用方法:                                                         ║
║    Run sensei on <skill-name>              # 单个Skill            ║
║    Run sensei on <skill-name> --skip-integration  # 快速模式      ║
║    Run sensei on <skill1>, <skill2>, ...   # 多个Skill             ║
║    Run sensei on all Low-adherence skills  # 按分数批量处理        ║
║    Run sensei on all skills                # 所有Skill           ║
║                                                                  ║
║  示例:                                                           ║
║    Run sensei on appinsights-instrumentation                     ║
║    Run sensei on azure-security --skip-integration               ║
║    Run sensei on azure-security, azure-networking                ║
║    Run sensei on all Low-adherence skills                        ║
║                                                                  ║
║  功能说明:                                                       ║
║    1. 读取    - 加载Skill的SKILL.md、测试用例和令牌计数            ║
║    2. 评分   - 检查合规性（低/中/中高/高）                       ║
║    3. 搭建脚手架- 若测试用例缺失则从模板创建                      ║
║    4. 改进 - 添加适用场景触发词 + 不适用场景反触发词              ║
║    5. 测试    - 运行测试，必要时修复问题                         ║
║    6. 令牌  - 检查令牌预算，收集优化建议                         ║
║    7. 总结 - 展示改进前后对比及未实施的建议                       ║
║    8. 提示  - 询问：提交修改、创建Issue还是跳过？                 ║
║    9. 重复  - 直至达到中高评分 + 测试通过                         ║
║                                                                  ║
║  目标评分: 中高                                                   ║
║    ✓ 描述内容 > 150字符                                          ║
║    ✓ 包含“适用场景:”触发短语                                      ║
║    ✓ 包含“不适用场景:”反触发词                                    ║
║    ✓ SKILL.md < 500令牌（软限制）                                ║
║                                                                  ║
║  更多信息:                                                      ║
║    完整文档请查看.github/skills/sensei/README.md                 ║
║                                                                  ║
╚══════════════════════════════════════════════════════════════════╝

When to Use

适用场景

Improving a skill's frontmatter compliance score
Adding trigger phrases and anti-triggers to skill descriptions
Batch-improving multiple skills at once
Auditing and fixing Low-adherence skills

提升Skill的frontmatter合规性评分
为Skill描述添加触发词和反触发词
批量优化多个Skill
审计并修复低合规性的Skill

Invocation Modes

调用模式

Single Skill

单个Skill

Run sensei on azure-deploy

Run sensei on azure-deploy

Multiple Skills

多个Skill

Run sensei on azure-security, azure-networking, azure-observability

Run sensei on azure-security, azure-networking, azure-observability

By Adherence Level

按合规性等级

Run sensei on all Low-adherence skills

Run sensei on all Low-adherence skills

All Skills

所有Skill

Run sensei on all skills

Run sensei on all skills

The Ralph Loop

Ralph循环流程

For each skill, execute this loop until score >= Medium-High AND tests pass:

READ - Load
```
plugin/skills/{skill-name}/SKILL.md
```
, tests, and token count
SCORE - Run rule-based compliance check (see SCORING.md)
CHECK - If score >= Medium-High AND tests pass → go to TOKENS step
SCAFFOLD - If
```
tests/{skill-name}/
```
doesn't exist, create from
```
tests/_template/
```
IMPROVE FRONTMATTER - Add triggers, anti-triggers, compatibility (stay under 1024 chars)

IMPROVE TESTS - Update

shouldTriggerPrompts

and

shouldNotTriggerPrompts

to match

VERIFY - Run

cd tests && npm test -- --testPathPattern={skill-name}

TOKENS - Check token budget, gather optimization suggestions
SUMMARY - Display before/after comparison with unimplemented suggestions
PROMPT - Ask user: Commit, Create Issue, or Skip?
REPEAT - Go to step 2 (max 5 iterations per skill)

对每个Skill执行以下循环，直至评分≥中高且测试通过：

读取 - 加载
```
plugin/skills/{skill-name}/SKILL.md
```
、测试用例和令牌计数
评分 - 运行基于规则的合规性检查（详见SCORING.md）
检查 - 若评分≥中高且测试通过 → 进入令牌检查步骤
搭建脚手架 - 若
```
tests/{skill-name}/
```
目录不存在，则从
```
tests/_template/
```
创建
优化Frontmatter - 添加触发词、反触发词、兼容性信息（总长度不超过1024字符）
优化测试用例 - 更新
```
shouldTriggerPrompts
```
和
```
shouldNotTriggerPrompts
```
以匹配新内容

验证 - 运行

cd tests && npm test -- --testPathPattern={skill-name}

令牌检查 - 检查令牌预算，收集优化建议
总结 - 展示改进前后的对比及未实施的建议
提示 - 询问用户：提交修改、创建Issue还是跳过？
重复 - 返回步骤2（每个Skill最多迭代5次）

Scoring Criteria (Quick Reference)

评分标准（快速参考）

Score	Requirements
Low	Basic description, no explicit triggers, no anti-triggers
Medium	Has trigger keywords/phrases, description > 150 chars
Medium-High	Has "USE FOR:" triggers AND "DO NOT USE FOR:" anti-triggers
High	Triggers + anti-triggers + compatibility field

Target: Medium-High (triggers + anti-triggers present)

评分	要求
低	基础描述，无明确触发词，无反触发词
中	包含触发关键词/短语，描述内容>150字符
中高	包含“适用场景:”触发词 AND “不适用场景:”反触发词
高	触发词 + 反触发词 + 兼容性字段

目标：中高（同时包含触发词和反触发词）

Frontmatter Template

Frontmatter模板

yaml

---
name: skill-name
description: |
  [1-2 sentence description of what the skill does]
  USE FOR: [trigger phrase 1], [trigger phrase 2], [trigger phrase 3]
  DO NOT USE FOR: [scenario] (use other-skill), [scenario] (use another-skill)
---

IMPORTANT: Always use multi-line YAML format (
|
) for descriptions over 200 characters. Single-line descriptions become difficult to read, review, and maintain. See azure-ai, azure-functions for examples.

Keep total description under 1024 characters.

yaml

---
name: skill-name
description: |
  [1-2句话描述Skill功能]
  USE FOR: [触发短语1], [触发短语2], [触发短语3]
  DO NOT USE FOR: [场景] (使用other-skill), [场景] (使用another-skill)
---

重要提示: 当描述内容超过200字符时，请始终使用多行YAML格式（
|
）。单行描述会难以阅读、审核和维护。示例可参考azure-ai、azure-functions。

描述内容总长度不得超过1024字符。

Test Scaffolding

测试脚手架

When tests don't exist, scaffold from

tests/_template/

bash

cp -r tests/_template tests/{skill-name}

Then update:

```
SKILL_NAME
```
constant in all test files
```
shouldTriggerPrompts
```
- 5+ prompts matching new frontmatter triggers
```
shouldNotTriggerPrompts
```
- 5+ prompts matching anti-triggers

Commit Messages:

sensei: improve {skill-name} frontmatter

若测试用例不存在，从

tests/_template/

搭建：

bash

cp -r tests/_template tests/{skill-name}

然后更新：

所有测试文件中的
```
SKILL_NAME
```
常量
```
shouldTriggerPrompts
```
- 添加5个以上与新frontmatter触发词匹配的提示语
```
shouldNotTriggerPrompts
```
- 添加5个以上与反触发词匹配的提示语

提交信息格式:

sensei: improve {skill-name} frontmatter

Constraints

约束条件

Only modify
```
plugin/skills/
```
- these are the Azure skills used by Copilot
```
.github/skills/
```
contains meta-skills like sensei for developer tooling
Max 5 iterations per skill before moving on
Description must stay under 1024 characters
SKILL.md should stay under 500 tokens (soft limit)
Tests must pass before prompting for action
User chooses: Commit, Create Issue, or Skip after each skill

仅修改
```
plugin/skills/
```
目录下的内容——这些是Copilot使用的Azure Skill
```
.github/skills/
```
目录包含sensei等面向开发者工具的元Skill
每个Skill最多迭代5次后即停止
描述内容长度不得超过1024字符
SKILL.md的令牌数应低于500（软限制）
测试通过后方可提示用户采取行动
用户可选择：提交修改、创建Issue或跳过当前Skill

Flags

命令行参数

Flag	Description
`--skip-integration`	Skip integration tests for faster iteration. Only runs unit and trigger tests.

⚠️ Skipping integration tests speeds up the loop but may miss runtime issues. Consider running full tests before final commit.

参数	描述
`--skip-integration`	跳过集成测试以加快迭代速度。仅运行单元测试和触发词测试。

⚠️ 跳过集成测试会加快循环速度，但可能会遗漏运行时问题。建议在最终提交前运行完整测试。

sensei

Original

Translation

Sensei

Sensei

Help

帮助

When to Use

适用场景

Invocation Modes

调用模式

Single Skill

单个Skill

Multiple Skills

多个Skill

By Adherence Level

按合规性等级

All Skills

所有Skill

The Ralph Loop

Ralph循环流程

Scoring Criteria (Quick Reference)

评分标准（快速参考）

Frontmatter Template

Frontmatter模板

Test Scaffolding

测试脚手架

Constraints

约束条件

Flags

命令行参数

Reference Documentation

参考文档

Related Skills

相关Skill