reflect

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Reflect Skill

Analyze the current session and propose improvements to skills based on what worked, what didn't, and edge cases discovered.

分析当前会话，基于有效内容、无效内容以及发现的边缘情况，提出技能改进建议。

Trigger

触发方式

Run

/reflect

/reflect [skill-name]

after a session where you used a skill.

Additional commands:

```
/reflect on
```
- Enable automatic end-of-session reflection
```
/reflect off
```
- Disable automatic reflection
```
/reflect status
```
- Check if auto-reflect is enabled

在使用技能的会话结束后，运行

/reflect

或

/reflect [skill-name]

。

额外命令：

```
/reflect on
```
- 启用会话结束时自动反思
```
/reflect off
```
- 禁用自动反思
```
/reflect status
```
- 检查自动反思是否启用

Workflow

工作流程

Step 1: Identify the Skill

步骤1：确定技能

If skill name not provided, ask:

Which skill should I analyze this session for?
- frontend-design
- code-reviewer
- [other]

如果未提供技能名称，请询问：

我应该分析本次会话中的哪个技能？
- frontend-design
- code-reviewer
- [其他]

Step 2: Analyze the Conversation

步骤2：分析对话

Look for these signals in the current conversation:

在当前对话中寻找以下信号：

Corrections (HIGH confidence):

纠正信息（高置信度）：

User said "no", "not like that", "I meant..."
User explicitly corrected output
User asked for changes immediately after generation

用户说“不”、“不是那样”、“我指的是...”
用户明确纠正输出内容
用户在生成内容后立即要求修改

Successes (MEDIUM confidence):

成功信号（中置信度）：

User said "perfect", "great", "yes", "exactly"
User accepted output without modification
User built on top of the output

用户说“完美”、“很棒”、“是的”、“正是如此”
用户未做修改就接受了输出内容
用户基于输出内容进行拓展

Edge Cases (MEDIUM confidence):

边缘情况（中置信度）：

Questions the skill didn't anticipate
Scenarios requiring workarounds
Features user asked for that weren't covered

技能未预料到的问题
需要变通方案的场景
用户要求但技能未覆盖的功能

Preferences (accumulate over sessions):

偏好信息（跨会话积累）：

Repeated patterns in user choices
Style preferences shown implicitly
Tool/framework preferences

用户选择中的重复模式
隐含的风格偏好
工具/框架偏好

Step 3: Propose Changes

步骤3：提出修改建议

Present findings using accessible colors (WCAG AA 4.5:1 contrast ratio):

┌─ Skill Reflection: [skill-name] ───────────────────┐
│                                                    │
│ Signals: X corrections, Y successes                │
│                                                    │
│ Proposed changes:                                  │
│                                                    │
│ 🔴 [HIGH] + Add constraint: "[specific constraint]"│
│ 🟡 [MED]  + Add preference: "[specific preference]"│
│ 🔵 [LOW]  ~ Note for review: "[observation]"       │
│                                                    │
│ Commit: "[skill]: [summary of changes]"            │
│                                                    │
└────────────────────────────────────────────────────┘

Apply these changes? [Y/n] or describe tweaks

使用符合WCAG AA 4.5:1对比度的易读颜色展示发现的内容：

┌─ 技能反思: [skill-name] ───────────────────┐
│                                            │
│ 信号: X 条纠正信息, Y 个成功案例            │
│                                            │
│ 建议修改:                                  │
│                                            │
│ 🔴 [高优先级] + 添加约束: "[具体约束内容]"   │
│ 🟡 [中优先级] + 添加偏好: "[具体偏好内容]"   │
│ 🔵 [低优先级] ~ 待评审备注: "[观察内容]"     │
│                                            │
│ 提交信息: "[skill]: [修改摘要]"             │
│                                            │
└────────────────────────────────────────────┘

是否应用这些修改？[Y/n] 或描述调整内容

Accessible Color Palette (use ANSI codes in terminal output):

易读调色板（终端输出中使用ANSI代码）：

HIGH:
```
\033[1;31m
```
(bold red #FF6B6B - 4.5:1 on dark)
MED:
```
\033[1;33m
```
(bold yellow #FFE066 - 4.8:1 on dark)
LOW:
```
\033[1;36m
```
(bold cyan #6BC5FF - 4.6:1 on dark)
Reset:
```
\033[0m
```

Avoid: pure red (#FF0000) on black, green on red (colorblind users)

高优先级:
```
\033[1;31m
```
(粗体红色 #FF6B6B - 在深色背景上对比度4.5:1)
中优先级:
```
\033[1;33m
```
(粗体黄色 #FFE066 - 在深色背景上对比度4.8:1)
低优先级:
```
\033[1;36m
```
(粗体青色 #6BC5FF - 在深色背景上对比度4.6:1)
重置:
```
\033[0m
```

避免：深色背景上的纯红色(#FF0000)、红色背景上的绿色（色盲用户友好性差）

User Response Options:

用户响应选项：

```
Y
```
– Apply changes, commit, and push
```
n
```
– Skip this update
Or describe any tweaks to the proposed changes

```
Y
```
– 应用修改、提交并推送
```
n
```
– 跳过本次更新
或描述对建议修改的调整内容

Step 4: If Approved

步骤4：如果获得批准

Read the current skill file from
```
.claude/skills/[skill-name]/SKILL.md
```
Apply the changes using the Edit tool

Run git commands:

bash

cd .claude/skills
git add [skill-name]/SKILL.md
git commit -m "[skill]: [change summary]"
git push origin main

Confirm: "Skill updated and pushed to GitHub"

从
```
.claude/skills/[skill-name]/SKILL.md
```
读取当前技能文件
使用编辑工具应用修改

运行git命令：

bash

cd .claude/skills
git add [skill-name]/SKILL.md
git commit -m "[skill]: [修改摘要]"
git push origin main

确认："技能已更新并推送至GitHub"

Step 5: If Declined

步骤5：如果被拒绝

Ask: "Would you like to save these observations for later review?"

If yes, append to

.claude/skills/[skill-name]/OBSERVATIONS.md

询问："你是否希望保存这些观察结果供以后评审？"

如果是，将内容追加到

.claude/skills/[skill-name]/OBSERVATIONS.md

Toggle Commands

切换命令

/reflect on

/reflect on

Enable automatic end-of-session reflection:

Create/update

~/.claude/reflect-skill-state.json

with

{"enabled": true, "updatedAt": "[timestamp]"}

Confirm: "Auto-reflect enabled. Sessions will be analyzed automatically when you stop."

启用会话结束时自动反思：

创建/更新

~/.claude/reflect-skill-state.json

，内容为

{"enabled": true, "updatedAt": "[时间戳]"}

确认："自动反思已启用。当你结束会话时，系统将自动分析会话内容。"

/reflect off

/reflect off

Disable automatic reflection:

Update

~/.claude/reflect-skill-state.json

with

{"enabled": false, "updatedAt": "[timestamp]"}

Confirm: "Auto-reflect disabled. Use /reflect manually to analyze sessions."

禁用自动反思：

更新

~/.claude/reflect-skill-state.json

，内容为

{"enabled": false, "updatedAt": "[时间戳]"}

确认："自动反思已禁用。请手动使用/reflect命令分析会话。"

/reflect status

/reflect status

Check current status:

Read
```
~/.claude/reflect-skill-state.json
```
Report: "Auto-reflect is [enabled/disabled]" with last updated timestamp

Note: The state file is saved in the global Claude user directory (

~/.claude/

) so it persists across plugin upgrades.

检查当前状态：

读取
```
~/.claude/reflect-skill-state.json
```
报告："自动反思当前[已启用/已禁用]"，并显示最后更新时间戳

注意： 状态文件保存在全局Claude用户目录(

~/.claude/

)中，因此在插件升级后仍会保留。

Example Session

示例会话

User runs

/reflect frontend-design

after a UI session:

┌─ Skill Reflection: frontend-design ───────────────┐
│                                                   │
│ Signals: 2 corrections, 3 successes               │
│                                                   │
│ Proposed changes:                                 │
│                                                   │
│ 🔴 [HIGH] + Constraints/NEVER:                    │
│    "Use gradients unless explicitly requested"    │
│                                                   │
│ 🔴 [HIGH] + Color & Theme:                        │
│    "Dark backgrounds: use #000, not #1a1a1a"      │
│                                                   │
│ 🟡 [MED] + Layout:                                │
│    "Prefer CSS Grid for card layouts"             │
│                                                   │
│ Commit: "frontend-design: no gradients, #000 dark"│
│                                                   │
└───────────────────────────────────────────────────┘

Apply these changes? [Y/n] or describe tweaks

用户在UI会话结束后运行

/reflect frontend-design

：

┌─ 技能反思: frontend-design ───────────────┐
│                                           │
│ 信号: 2 条纠正信息, 3 个成功案例           │
│                                           │
│ 建议修改:                                 │
│                                           │
│ 🔴 [高优先级] + 约束/禁止:                 │
│    "除非明确要求，否则不要使用渐变效果"     │
│                                           │
│ 🔴 [高优先级] + 颜色与主题:                │
│    "深色背景使用#000，而非#1a1a1a"         │
│                                           │
│ 🟡 [中优先级] + 布局:                      │
│    "卡片布局优先使用CSS Grid"               │
│                                           │
│ 提交信息: "frontend-design: 禁用渐变，深色用#000"│
│                                           │
└───────────────────────────────────────────┘

是否应用这些修改？[Y/n] 或描述调整内容

Git Integration

Git集成

This skill has permission to:

Read skill files from
```
.claude/skills/
```
Edit skill files (with user approval)
Run
```
git add
```
,
```
git commit
```
,
```
git push
```
in the skills directory

The skills repo should be initialized at

.claude/skills

with a remote origin.

此技能拥有以下权限：

从
```
.claude/skills/
```
读取技能文件
（经用户批准后）编辑技能文件
在技能目录中运行
```
git add
```
、
```
git commit
```
、
```
git push
```
命令

技能仓库应在

.claude/skills

初始化，并配置远程origin。

Important Notes

重要说明

Always show the exact changes before applying
Never modify skills without explicit user approval
Commit messages should be concise and descriptive
Push only after successful commit

应用修改前务必展示具体的变更内容
未经用户明确批准，不得修改技能
提交信息应简洁明了
仅在提交成功后推送代码