omc-help
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseHow OMC Works
OMC 工作原理
You don't need to learn any commands! OMC enhances Claude Code with intelligent behaviors that activate automatically.
无需学习任何命令! OMC 可自动激活智能行为,增强 Claude Code 的能力。
What Happens Automatically
自动触发的功能
| When You... | I Automatically... |
|---|---|
| Give me a complex task | Parallelize and delegate to specialist agents |
| Ask me to plan something | Start a planning interview |
| Need something done completely | Persist until verified complete |
| Work on UI/frontend | Activate design sensibility |
| Say "stop" or "cancel" | Intelligently stop current operation |
| 当你... | 我会自动... |
|---|---|
| 交给我复杂任务 | 并行处理并委派给专业 Agent |
| 要求我制定计划 | 启动规划访谈 |
| 需要彻底完成某项工作 | 持续执行直到验证完成 |
| 处理 UI/前端相关工作 | 激活设计敏感度 |
| 说“stop”或“cancel” | 智能停止当前操作 |
Magic Keywords (Optional Shortcuts)
魔法关键词(可选快捷方式)
You can include these words naturally in your request for explicit control:
| Keyword | Effect | Example |
|---|---|---|
| ralph | Persistence mode | "ralph: fix all the bugs" |
| ralplan | Iterative planning | "ralplan this feature" |
| ulw | Max parallelism | "ulw refactor the API" |
| plan | Planning interview | "plan the new endpoints" |
ralph includes ultrawork: When you activate ralph mode, it automatically includes ultrawork's parallel execution. No need to combine keywords.
你可以在请求中自然加入以下词汇,实现显式控制:
| 关键词 | 效果 | 示例 |
|---|---|---|
| ralph | 持久化模式 | "ralph: 修复所有漏洞" |
| ralplan | 迭代规划 | "ralplan 这个功能" |
| ulw | 最大并行度 | "ulw 重构 API" |
| plan | 规划访谈 | "plan 新的端点" |
ralph 包含 ultrawork: 激活 ralph 模式时,会自动启用 ultrawork 的并行执行功能,无需组合多个关键词。
Stopping Things
停止操作
Just say:
- "stop"
- "cancel"
- "abort"
I'll figure out what to stop based on context.
只需说:
- "stop"
- "cancel"
- "abort"
我会根据上下文判断需要停止的内容。
First Time Setup
首次设置
If you haven't configured OMC yet:
/oh-my-claudecode:omc-setupThis is the only command you need to know. It downloads the configuration and you're done.
如果你还未配置 OMC:
/oh-my-claudecode:omc-setup这是你唯一需要了解的命令。执行后会下载配置,设置完成。
For 2.x Users
针对 2.x 用户
Your old commands still work! , , , etc. all function exactly as before.
/ralph/ultrawork/planBut now you don't NEED them - everything is automatic.
旧命令依然可用!、、 等命令的功能与之前完全一致。
/ralph/ultrawork/plan但现在你无需依赖它们——所有功能都是自动的。
Usage Analysis
使用情况分析
Analyze your oh-my-claudecode usage and get tailored recommendations to improve your workflow.
Note: This replaces the formerskill./oh-my-claudecode:learn-about-omc
分析你的 oh-my-claudecode 使用情况,获取量身定制的建议以优化工作流。
注意:此功能替代了之前的技能。/oh-my-claudecode:learn-about-omc
What It Does
功能说明
- Reads token tracking from
~/.omc/state/token-tracking.jsonl - Reads session history from
.omc/state/session-history.json - Analyzes agent usage patterns
- Identifies underutilized features
- Recommends configuration changes
- 读取 中的令牌跟踪数据
~/.omc/state/token-tracking.jsonl - 读取 中的会话历史
.omc/state/session-history.json - 分析 Agent 使用模式
- 识别未充分利用的功能
- 推荐配置调整方案
Step 1: Gather Data
步骤 1:收集数据
bash
undefinedbash
undefinedCheck for token tracking data
检查令牌跟踪数据
TOKEN_FILE="$HOME/.omc/state/token-tracking.jsonl"
SESSION_FILE=".omc/state/session-history.json"
CONFIG_FILE="$HOME/.claude/.omc-config.json"
echo "Analyzing OMC Usage..."
echo ""
TOKEN_FILE="$HOME/.omc/state/token-tracking.jsonl"
SESSION_FILE=".omc/state/session-history.json"
CONFIG_FILE="$HOME/.claude/.omc-config.json"
echo "正在分析 OMC 使用情况..."
echo ""
Check what data is available
检查可用数据
HAS_TOKENS=false
HAS_SESSIONS=false
HAS_CONFIG=false
if [[ -f "$TOKEN_FILE" ]]; then
HAS_TOKENS=true
TOKEN_COUNT=$(wc -l < "$TOKEN_FILE")
echo "Token records found: $TOKEN_COUNT"
fi
if [[ -f "$SESSION_FILE" ]]; then
HAS_SESSIONS=true
SESSION_COUNT=$(cat "$SESSION_FILE" | jq '.sessions | length' 2>/dev/null || echo "0")
echo "Sessions found: $SESSION_COUNT"
fi
if [[ -f "$CONFIG_FILE" ]]; then
HAS_CONFIG=true
DEFAULT_MODE=$(cat "$CONFIG_FILE" | jq -r '.defaultExecutionMode // "not set"')
echo "Default execution mode: $DEFAULT_MODE"
fi
undefinedHAS_TOKENS=false
HAS_SESSIONS=false
HAS_CONFIG=false
if [[ -f "$TOKEN_FILE" ]]; then
HAS_TOKENS=true
TOKEN_COUNT=$(wc -l < "$TOKEN_FILE")
echo "找到令牌记录:$TOKEN_COUNT"
fi
if [[ -f "$SESSION_FILE" ]]; then
HAS_SESSIONS=true
SESSION_COUNT=$(cat "$SESSION_FILE" | jq '.sessions | length' 2>/dev/null || echo "0")
echo "找到会话记录:$SESSION_COUNT"
fi
if [[ -f "$CONFIG_FILE" ]]; then
HAS_CONFIG=true
DEFAULT_MODE=$(cat "$CONFIG_FILE" | jq -r '.defaultExecutionMode // "not set"')
echo "默认执行模式:$DEFAULT_MODE"
fi
undefinedStep 2: Analyze Agent Usage (if token data exists)
步骤 2:分析 Agent 使用情况(如果有令牌数据)
bash
if [[ "$HAS_TOKENS" == "true" ]]; then
echo ""
echo "TOP AGENTS BY USAGE:"
cat "$TOKEN_FILE" | jq -r '.agentName // "main"' | sort | uniq -c | sort -rn | head -10
echo ""
echo "MODEL DISTRIBUTION:"
cat "$TOKEN_FILE" | jq -r '.modelName' | sort | uniq -c | sort -rn
fibash
if [[ "$HAS_TOKENS" == "true" ]]; then
echo ""
echo "按使用次数排序的 TOP AGENTS:"
cat "$TOKEN_FILE" | jq -r '.agentName // "main"' | sort | uniq -c | sort -rn | head -10
echo ""
echo "模型分布:"
cat "$TOKEN_FILE" | jq -r '.modelName' | sort | uniq -c | sort -rn
fiStep 3: Generate Recommendations
步骤 3:生成建议
Based on patterns found, output recommendations:
If high Opus usage (>40%) and no :
- "Consider using for routine tasks to save tokens"
If no pipeline usage:
- "Try /pipeline for code review workflows"
If no security-reviewer usage:
- "Use security-reviewer after auth/API changes"
If defaultExecutionMode not set:
- "Set defaultExecutionMode in /omc-setup for consistent behavior"
根据发现的模式输出建议:
如果 Opus 使用率过高(>40%)且未使用 :
- "考虑使用 处理常规任务以节省令牌"
如果未使用 pipeline 功能:
- "尝试使用 /pipeline 进行代码审查工作流"
如果未使用 security-reviewer:
- "在进行认证/API 变更后使用 security-reviewer"
如果未设置 defaultExecutionMode:
- "在 /omc-setup 中设置 defaultExecutionMode 以获得一致的行为"
Step 4: Output Report
步骤 4:输出报告
Format a summary with:
- Token summary (total, by model)
- Top agents used
- Underutilized features
- Personalized recommendations
格式化包含以下内容的摘要:
- 令牌摘要(总数、按模型分类)
- 最常用的 Agent
- 未充分利用的功能
- 个性化建议
Example Output
示例输出
📊 Your OMC Usage Analysis
TOKEN SUMMARY:
- Total records: 1,234
- By Model: opus 45%, sonnet 40%, haiku 15%
TOP AGENTS:
1. executor (234 uses)
2. architect (89 uses)
3. explore (67 uses)
UNDERUTILIZED FEATURES:
- : 0 uses (could save ~30% on routine tasks)
- pipeline: 0 uses (great for review workflows)
RECOMMENDATIONS:
1. Set defaultExecutionMode: "" to save tokens
2. Try /pipeline review for PR reviews
3. Use explore agent before architect to save context📊 你的 OMC 使用情况分析
令牌摘要:
- 总记录数:1,234
- 按模型分类:opus 45%,sonnet 40%,haiku 15%
TOP AGENTS:
1. executor(234 次使用)
2. architect(89 次使用)
3. explore(67 次使用)
未充分利用的功能:
- :0 次使用(常规任务使用可节省约 30% 令牌)
- pipeline:0 次使用(非常适合审查工作流)
建议:
1. 设置 defaultExecutionMode:"" 以节省令牌
2. 尝试使用 /pipeline review 进行 PR 审查
3. 在使用 architect 之前先用 explore Agent 以节省上下文Graceful Degradation
优雅降级
If no data found:
📊 Limited Usage Data Available
No token tracking found. To enable tracking:
1. Ensure ~/.omc/state/ directory exists
2. Run any OMC command to start tracking
Tip: Run /omc-setup to configure OMC properly.如果未找到数据:
📊 可用使用数据有限
未找到令牌跟踪数据。要启用跟踪:
1. 确保 ~/.omc/state/ 目录存在
2. 运行任意 OMC 命令开始跟踪
提示:运行 /omc-setup 以正确配置 OMC。Need More Help?
需要更多帮助?
- README: https://github.com/Yeachan-Heo/oh-my-claudecode
- Issues: https://github.com/Yeachan-Heo/oh-my-claudecode/issues
Version: 4.2.3