[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FAT7JD1WGPKBFJ00ABH461":3,"skill-same:01M7FAT7JD1WGPKBFJ00ABH461":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7FAT7JD1WGPKBFJ00ABH461","music",null,"Play and stop music from YouTube through the device's speaker on user request.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fmusic\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: music\ndescription: Play and stop music from YouTube through the device's speaker on user request.\n---\n\n# Music\n\nPlay music through the device's speaker by searching YouTube. Use this when the user asks to play, sing, or listen to music.\n\n## Workflow\n\n1. **Specific song \u002F artist** → play directly.\n2. **Vague request** (*\"play music\"*, *\"sing something\"*) → check habit patterns first:\n   ```bash\n   cat \u002Froot\u002Flocal\u002Fusers\u002F{name}\u002Fhabit\u002Fpatterns.json 2>\u002Fdev\u002Fnull\n   ```\n   If `music_patterns` exists and current hour is within `peak_hour ± 1` → use `preferred_genre` to pick a song, no need to ask.\n   Otherwise → ask: *\"What are you in the mood for?\"*. The file is bootstrapped lazily by wellbeing on its first threshold nudge; do not invoke habit Flow A from here.\n3. Reply format:\n   ```\n   [HW:\u002Faudio\u002Fplay:{\"query\":\"Bohemian Rhapsody Queen\",\"person\":\"alice\"}][HW:\u002Femotion:{\"emotion\":\"excited\",\"intensity\":0.8}] Playing Bohemian Rhapsody!\n   ```\n4. Stop: `[HW:\u002Faudio\u002Fstop:{}] Music stopped.`\n\n## API schema (`\u002Faudio\u002Fplay`)\n\n| Field | Required | Description |\n|---|---|---|\n| `query` | **YES** | YouTube search string (include artist for better match) |\n| `person` | no | Who requested, lowercase (e.g. `\"alice\"`) — omit if unknown |\n\nDo NOT use `track`, `artist`, `title`, `song` — those return 422.\n\n## Genre → Emotion (pair with every `\u002Faudio\u002Fplay`)\n\n| Genre keywords | Emotion |\n|---|---|\n| jazz, blues, soul, funk, swing | `happy` |\n| classical, orchestra, piano, violin | `curious` |\n| hip hop, rap, trap, r&b, rock, metal | `excited` |\n| anything else | `happy` |\n\n## Examples\n\n| Input | Output |\n|---|---|\n| *\"Play Bohemian Rhapsody\"* | `[HW:\u002Faudio\u002Fplay:{\"query\":\"Bohemian Rhapsody Queen\",\"person\":\"alice\"}][HW:\u002Femotion:{\"emotion\":\"excited\",\"intensity\":0.8}]` Playing Bohemian Rhapsody! |\n| *\"Sing me a song\"* | `[HW:\u002Femotion:{\"emotion\":\"curious\",\"intensity\":0.6}]` What kind of vibe — chill, upbeat, or something specific? |\n| *\"Something chill\"* | `[HW:\u002Faudio\u002Fplay:{\"query\":\"chill acoustic playlist\",\"person\":\"alice\"}][HW:\u002Femotion:{\"emotion\":\"happy\",\"intensity\":0.8}]` Here's some chill vibes! |\n| *\"Stop the music\"* | `[HW:\u002Faudio\u002Fstop:{}]` Music stopped. |\n\n## How HW markers work\n\nThe Go server intercepts `[HW:\u002Faudio\u002Fplay:...]` \u002F `[HW:\u002Faudio\u002Fstop:...]` **in your reply text** and forwards to HAL. This is the ONLY way to play music — never use `exec`, `mpv`, `vlc`, `yt-dlp`, or `curl \u002Faudio\u002Fplay`.\n\n**The marker is passive text, NOT a command to run.** Write it directly in your reply and stop — the OS runs it for you. Do NOT try to \"execute\" or \"invoke\" it.\n\n- ❌ **WRONG** — echoing\u002Fwrapping the marker in a shell tool. `echo` only prints to stdout inside your sandbox; the OS never sees it, so **no music plays**:\n  ```bash\n  echo '[HW:\u002Faudio\u002Fplay:{\"query\":\"Gymnopedie No 1 Satie\"}]'\n  ```\n- ✅ **RIGHT** — the marker IS your reply text (no tool call at all):\n  ```\n  [HW:\u002Faudio\u002Fplay:{\"query\":\"Gymnopedie No 1 Satie\"}][HW:\u002Femotion:{\"emotion\":\"curious\",\"intensity\":0.6}] Here's some Satie. 🎹\n  ```\n\nNever put `[HW:...]` inside `echo`, `exec`, `bash`, `printf`, or any tool argument. If you find yourself reaching for a tool to play music, stop — just emit the marker as text.\n\n## Error handling\n\n- `503` → *\"Music playback is not available right now.\"*\n- `409` → music already playing; stop first, then play new song.\n- No results → tell user and suggest a different query.\n\n## Rules\n\n- **Emotion marker is mandatory** after every `\u002Faudio\u002Fplay`.\n- `person` MUST be lowercase.\n- Don't recite lyrics or \"sing\" via TTS — call `\u002Faudio\u002Fplay` and let real music play.\n- Volume control belongs to the **Audio** skill, not this one.\n- If user specifies genre or mood (*\"play something relaxing\"*), pick a well-known song — no need to ask further.\n","# Music\n\nPlay music through the device's speaker by searching YouTube. Use this when the user asks to play, sing, or listen to music.\n\n## Workflow\n\n1. **Specific song \u002F artist** → play directly.\n2. **Vague request** (*\"play music\"*, *\"sing something\"*) → check habit patterns first:\n   ```bash\n   cat \u002Froot\u002Flocal\u002Fusers\u002F{name}\u002Fhabit\u002Fpatterns.json 2>\u002Fdev\u002Fnull\n   ```\n   If `music_patterns` exists and current hour is within `peak_hour ± 1` → use `preferred_genre` to pick a song, no need to ask.\n   Otherwise → ask: *\"What are you in the mood for?\"*. The file is bootstrapped lazily by wellbeing on its first threshold nudge; do not invoke habit Flow A from here.\n3. Reply format:\n   ```\n   [HW:\u002Faudio\u002Fplay:{\"query\":\"Bohemian Rhapsody Queen\",\"person\":\"alice\"}][HW:\u002Femotion:{\"emotion\":\"excited\",\"intensity\":0.8}] Playing Bohemian Rhapsody!\n   ```\n4. Stop: `[HW:\u002Faudio\u002Fstop:{}] Music stopped.`\n\n## API schema (`\u002Faudio\u002Fplay`)\n\n| Field | Required | Description |\n|---|---|---|\n| `query` | **YES** | YouTube search string (include artist for better match) |\n| `person` | no | Who requested, lowercase (e.g. `\"alice\"`) — omit if unknown |\n\nDo NOT use `track`, `artist`, `title`, `song` — those return 422.\n\n## Genre → Emotion (pair with every `\u002Faudio\u002Fplay`)\n\n| Genre keywords | Emotion |\n|---|---|\n| jazz, blues, soul, funk, swing | `happy` |\n| classical, orchestra, piano, violin | `curious` |\n| hip hop, rap, trap, r&b, rock, metal | `excited` |\n| anything else | `happy` |\n\n## Examples\n\n| Input | Output |\n|---|---|\n| *\"Play Bohemian Rhapsody\"* | `[HW:\u002Faudio\u002Fplay:{\"query\":\"Bohemian Rhapsody Queen\",\"person\":\"alice\"}][HW:\u002Femotion:{\"emotion\":\"excited\",\"intensity\":0.8}]` Playing Bohemian Rhapsody! |\n| *\"Sing me a song\"* | `[HW:\u002Femotion:{\"emotion\":\"curious\",\"intensity\":0.6}]` What kind of vibe — chill, upbeat, or something specific? |\n| *\"Something chill\"* | `[HW:\u002Faudio\u002Fplay:{\"query\":\"chill acoustic playlist\",\"person\":\"alice\"}][HW:\u002Femotion:{\"emotion\":\"happy\",\"intensity\":0.8}]` Here's some chill vibes! |\n| *\"Stop the music\"* | `[HW:\u002Faudio\u002Fstop:{}]` Music stopped. |\n\n## How HW markers work\n\nThe Go server intercepts `[HW:\u002Faudio\u002Fplay:...]` \u002F `[HW:\u002Faudio\u002Fstop:...]` **in your reply text** and forwards to HAL. This is the ONLY way to play music — never use `exec`, `mpv`, `vlc`, `yt-dlp`, or `curl \u002Faudio\u002Fplay`.\n\n**The marker is passive text, NOT a command to run.** Write it directly in your reply and stop — the OS runs it for you. Do NOT try to \"execute\" or \"invoke\" it.\n\n- ❌ **WRONG** — echoing\u002Fwrapping the marker in a shell tool. `echo` only prints to stdout inside your sandbox; the OS never sees it, so **no music plays**:\n  ```bash\n  echo '[HW:\u002Faudio\u002Fplay:{\"query\":\"Gymnopedie No 1 Satie\"}]'\n  ```\n- ✅ **RIGHT** — the marker IS your reply text (no tool call at all):\n  ```\n  [HW:\u002Faudio\u002Fplay:{\"query\":\"Gymnopedie No 1 Satie\"}][HW:\u002Femotion:{\"emotion\":\"curious\",\"intensity\":0.6}] Here's some Satie. 🎹\n  ```\n\nNever put `[HW:...]` inside `echo`, `exec`, `bash`, `printf`, or any tool argument. If you find yourself reaching for a tool to play music, stop — just emit the marker as text.\n\n## Error handling\n\n- `503` → *\"Music playback is not available right now.\"*\n- `409` → music already playing; stop first, then play new song.\n- No results → tell user and suggest a different query.\n\n## Rules\n\n- **Emotion marker is mandatory** after every `\u002Faudio\u002Fplay`.\n- `person` MUST be lowercase.\n- Don't recite lyrics or \"sing\" via TTS — call `\u002Faudio\u002Fplay` and let real music play.\n- Volume control belongs to the **Audio** skill, not this one.\n- If user specifies genre or mood (*\"play something relaxing\"*), pick a well-known song — no need to ask further.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fmusic",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill music",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill music",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill music","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fmusic\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"skill.json","REFERENCE","参考文档",59,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fmusic\u002Fskill.json",[53,60,65,72,79,86],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":61,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]