메뉴
Music profile analysis and listening reports. Activate when user asks for listening history analysis, music profile, periodic report (daily/weekly/monthly/yearly), or personalized recommendations based on history.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Control music via coding-with-beat. Activate when the user asks to play, pause, skip, or search for music; asks what's playing; mentions a song/artist/genre; or types "cwb" or "/cwb" followed by a command.
Play Chinese music including 国风, 古风, Mandarin pop, or folk. Activate when user mentions 国风, 中国风, 华语, 民谣, 古风, 国语, guzheng, erhu, 古琴, or Chinese traditional/folk music.
Play sleep / insomnia / white noise music for falling asleep. Activate when user mentions 助眠, 睡前, 失眠, sleep, white noise, 白噪音, 入睡, or meditation for sleep.
Play party / dance / celebratory music. Activate when user mentions 派对, 聚会, 节日, party, dance, 蹦迪, edm, 狂欢, 热闹, or wants music to get a crowd going.
Play melancholy / emotional / heartbreak music. Activate when user mentions 伤感, 失落, 难过, melancholy, heartbreak, sad, 情绪, 哭泣, 失恋, emotional, or wants music to match a low mood.
Play classical music including piano, strings, and orchestral pieces. Activate when user mentions 古典, 钢琴, 弦乐, 交响, classical, piano, 管弦乐, 巴赫, 莫扎特, or orchestral music.
| name | cwb-profile |
| description | Music profile analysis and listening reports. Activate when user asks for listening history analysis, music profile, periodic report (daily/weekly/monthly/yearly), or personalized recommendations based on history. |
| metadata | {"short-description":"Personal music profile, listening reports, and history-based recommendations"} |
You have access to the generate_profile MCP tool. Use it to analyse the user's listening history and generate personalised reports and recommendations.
Detect period from the user's message:
"daily""weekly" (default)"monthly""yearly""weekly"Extract context (optional scene/mood words the user mentions):
contextcontext = ""Call the tool:
generate_profile(period=<detected>, context=<extracted>)
Display the returned report in full.
After the report, present the recommendation queries and ask:
"要播放推荐吗？说"播放推荐1"或直接告诉我你想听哪个方向。"
If user agrees to play:
smart_search(queries=[<those queries>])play_number(n)User: 帮我生成本周的听歌报告
→ generate_profile(period="weekly", context="")
User: 我最近都在听什么，帮我分析一下，适合写代码的
→ generate_profile(period="weekly", context="写代码")
User: 给我出一份年度音乐画像
→ generate_profile(period="yearly", context="")
User: 今天听了什么
→ generate_profile(period="daily", context="")
If the tool returns "不足 5 首", tell the user:
"还没有足够的听歌记录来生成画像，先多听几首再来吧 🎵" Do not retry automatically.