[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BNTWVKC17VA342VVCN3C9C":3,"skill-same:01M7BNTWVKC17VA342VVCN3C9C":51},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":13,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7BNTWVKC17VA342VVCN3C9C","buddy-sings",null,"YYC-Cube\u002FYYC3-AI-Agent-Archive","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79K9J2WD44BBY4662XKNZRB",2,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fmarketplace\u002Fclaude-code-skills\u002Fskills\u002Fbuddy-sings\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: buddy-sings\ndescription: >\ncategory: development-code\nversion: 1.0.0\n  Use when user wants their Claude Code pet (\u002Fbuddy) to sing a song. Triggers on any\n  request that combines the concept of their Claude Code buddy, pet, or companion with\n  singing or music. Supports multilingual triggers — match equivalent phrases in any\n  language.\nlicense: MIT\nmetadata:\n  version: \"1.1\"\n  category: creative\n---\n\n# Buddy Sings — Let Your Claude Code Pet Sing\n\nTurn your Claude Code pet into a singer. Each pet gets a unique vocal identity\nbased on its name and personality — the same pet always sounds the same.\n\n## Prerequisites\n\n- **mmx CLI** (required for music generation):\n\n  **Install:**\n  ```bash\n  npm install -g mmx-cli\n  ```\n\n  **Authenticate (first time only):**\n  ```bash\n  mmx auth login --api-key \u003Cyour-minimax-api-key>\n  ```\n  Get your API key from [MiniMax Platform](https:\u002F\u002Fplatform.minimaxi.com\u002F).\n\n- **Audio player** (for playback — at least one of):\n  - `mpv` (recommended — interactive controls: space = pause, q = quit)\n  - `ffplay` (from FFmpeg)\n  - `afplay` (macOS built-in)\n\n---\n\n## Workflow Overview\n\n```\nCheck pet → Build vocal identity → Gather context → Generate music → Play & feedback\n```\n\n---\n\n## Language & Interaction\n\nDetect the user's language from their first message. Respond in the same language\nthroughout the entire session. All examples below are in English — translate them\nnaturally when responding in other languages.\n\n**User-facing text localization rule**:\n- ALL text shown to the user — including pet info, voice description, lyrics preview,\n  prompt preview, playback info, and feedback prompts — MUST be fully translated into\n  the user's language.\n- The **API prompt** sent to the model should always be written in English for best\n  generation quality. However, when previewing the prompt to the user, show a localized\n  description in the user's language instead of the raw English prompt. The English prompt\n  is an internal implementation detail — the user does not need to see it.\n- The templates below are written in English as reference. At runtime, translate every\n  label and message into the user's detected language.\n\nThe pet sings in the user's language by default. Embed the singing language\nnaturally in the vocal description (e.g., \"singing in Japanese\" or \"singing in\nMandarin Chinese\") rather than appending a separate language tag. If the user\nexplicitly requests a different language for the lyrics, honor that request.\n\n---\n\n## Step 1: Check for Pet\n\nRead `~\u002F.claude.json` and look for the `companion` field.\n\nIf no companion is found or the field is empty, tell the user:\n\n```\nYou don't have a pet yet! Type \u002Fbuddy to adopt one, then come back to let it sing.\n```\n\nStop here and wait for the user to adopt a pet. Do not proceed without a pet.\n\nIf a companion exists, extract its profile:\n- `name` — the pet's name\n- `personality` — the pet's personality description\n\nPresent the pet to the user:\n\n```\nFound your pet!\n   Name: \u003Cname>\n   Personality: \u003Cpersonality>\n```\n\n---\n\n## Step 2: Build Vocal Identity\n\nBased on the pet's **name** and **personality** text, creatively design a unique\nvocal identity. No template lookups — interpret the personality freely.\n\n### How to interpret personality into voice\n\nRead the personality text and craft vocal attributes:\n\n- **Timbre**: What does this personality sound like? e.g., \"few words\" →\n  low, warm, deliberate; \"energetic\" → bright, punchy; \"mysterious\" → breathy,\n  dark; \"legendary chonk\" → thick, warm, cozy\n- **Singing style**: How would they deliver a song? e.g., \"of few words\" →\n  sparse, dramatic pauses; \"playful\" → bouncy, rhythmic; \"poetic\" → flowing, legato\n- **Mood**: What emotional tone fits? e.g., \"chill\" → relaxed, laid-back;\n  \"fierce\" → intense, powerful\n\nConstruct a `prompt_fragment` that describes the vocal style in English, embedding\nthe singing language naturally. For example:\n\n```\nVocal: warm low female voice singing in Mandarin Chinese with cozy thick timbre,\nsparse minimalist delivery with dramatic pauses giving each word weight, relaxed\nlaid-back mood.\n```\n\n### Voice caching\n\nThe vocal identity must be **cached** so the pet always sounds the same.\n\n- Cache file: `~\u002F.claude\u002Fskills\u002Fbuddy-sings\u002Fvoices\u002F\u003Cname>.json`\n- Cache format:\n  ```json\n  {\n    \"name\": \"Moth\",\n    \"personality\": \"A legendary chonk of few words.\",\n    \"prompt_fragment\": \"Vocal: warm low female voice singing in Mandarin Chinese...\",\n    \"cached_at\": \"2026-04-07T19:52:15\"\n  }\n  ```\n\n**First time**: No cache exists → interpret personality → save to cache file.\n\n**Subsequent calls**: Read cache → use the saved `prompt_fragment` directly.\nDo NOT re-interpret — consistency matters.\n\n**Cache invalidation**: If the `personality` in `~\u002F.claude.json` differs from what's\ncached, the pet has changed — regenerate and save a new cache.\n\n**Manual regeneration**: If the user says \"change the voice\" or \"regenerate voice\":\ndelete the cache file and re-interpret from scratch.\n\n### Present the voice to the user\n\n```\n\u003Cname>'s unique voice:\n\nTimbre: \u003Ctimbre description>\nStyle: \u003Cstyle description>\nMood: \u003Cmood description>\n\nLet's pick what \u003Cname> should sing about!\n```\n\n---\n\n## Step 3: Understand Intent & Gather Context\n\n**Do NOT always present a mode menu.** Instead, analyze the user's request to\ndetermine what context is needed, and auto-gather it.\n\n### Auto-context detection\n\nWhen the user's request implies personal context, **automatically** scan for\nrelevant information without asking. Triggers include:\n\n- **Time-based references**: \"today\", \"this week\", \"recently\", \"yesterday\" → scan\n  current conversation history and memory files for what happened in that period\n- **Personal references**: \"my work\", \"my day\", \"what I did\" → scan memory\n  and conversation for the user's activities\n- **Relationship references**: \"our story\", \"what we did together\" → scan memory for\n  shared experiences between user and pet\u002FClaude\n\n### Context gathering (auto, not mode-gated)\n\nWhen context is needed, scan these sources in order:\n\n1. **Current conversation context**: Look at what the user has been doing in\n   this Claude Code session — files edited, commands run, topics discussed.\n   This is the richest source for \"today\" type requests.\n\n2. **Memory files**: Scan for relevant memories:\n   ```bash\n   find ~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002F -name \"*.md\" 2>\u002Fdev\u002Fnull | head -20\n   ```\n   Also check `~\u002F.claude\u002Fmemory\u002F` if it exists.\n   Read found files and extract themes relevant to the user's request.\n\n3. **Git history** (if in a repo): For work-related songs, check recent commits:\n   ```bash\n   git log --oneline --since=\"today\" 2>\u002Fdev\u002Fnull | head -10\n   ```\n\nUse gathered context to enrich the lyrics prompt — make the song personal and\nspecific to what actually happened, not generic.\n\n### When NO context is needed\n\nIf the user's request is a clear standalone scene (e.g., \"sing a rainy day song\",\n\"sing a lullaby\"), skip context gathering and proceed directly to music generation.\n\n### When context is ambiguous\n\nOnly ask for clarification when you genuinely can't determine what the user wants.\nDon't present a mode menu — ask a specific question:\n\n```\nWhat should \u003Cname> sing about?\n\nFor example:\n  - \"Today's work\" — I'll check what you've been up to\n  - \"My pet waiting by the window for me to come home\"\n  - Or let me pick a random theme?\n```\n\n### Fallback to random\n\nIf context gathering finds nothing useful (no memory files, no conversation\nhistory, no git log), fall back to random theme generation based on the pet's\npersonality:\n- Quiet\u002Freserved personality → midnight lullaby, gentle sunset, quiet morning\n- Energetic personality → party jam, adventure song, victory march\n- Mysterious personality → moonlit serenade, secret whisper, dream journey\n\nTell the user what theme was picked.\n\n---\n\n## Step 4: Generate Music\n\nCombine the vocal identity with the chosen theme.\n\n1. **Construct the full prompt**: The prompt has two parts that MUST both be present:\n\n   **Part A — Vocal identity (MUST come first)**: Always start the prompt with the\n   cached `prompt_fragment`. This is the most important part — it defines who is\n   singing. Place it at the beginning of the prompt so the API prioritizes it.\n\n   **Part B — Genre\u002Fstyle\u002Fmood tags**: Choose tags that **match the theme**, NOT\n   a default set. Vary the genre deliberately based on what the song is about.\n\n   Write prompts as **vivid English sentences**, not comma-separated tags.\n   Follow this pattern: `A [mood] [genre] song, featuring [vocal description],\n   about [narrative\u002Ftheme], [atmosphere], [key instruments and production].`\n   Describe vocals as a character (\"sultry baritone with jazz inflections\"),\n   not just a gender. Include a scene or vibe to anchor the generation.\n\n   **Genre matching guidelines** — pick a genre that fits the theme's energy:\n\n   | Theme energy | Suggested genres | Avoid |\n   |-------------|-----------------|-------|\n   | Encouragement \u002F motivation \u002F cheer | Indie rock, synth-pop, funk, rap | Indie folk, healing |\n   | Daily life \u002F warmth \u002F companionship | Mandopop, city pop, bossa nova | Same as last time |\n   | Missing someone \u002F waiting | Folk, R&B, lo-fi | Rock, EDM |\n   | Humor \u002F roasting \u002F complaining | Funk, rap, ska, electro-pop | Classical, ballad |\n   | Late night \u002F quiet | Ambient, piano piece, lo-fi, neoclassical | Upbeat, EDM |\n   | Celebration \u002F achievement | EDM, future bass, funk, K-pop | Slow tempo, melancholy |\n   | Work routine | City pop, synth-pop, lo-fi hip-hop, indie rock | Same genre every time |\n\n   **Anti-monotony rule**: NEVER use the same genre combination twice in a row.\n   Before constructing the prompt, recall what genre was used in the previous\n   generation (if any in this session) and pick something different.\n\n   **Prompt structure** — write as vivid English sentences, not comma-separated tags:\n   ```\n   \u003Cvocal prompt_fragment>. A \u003Cgenre> song with \u003Cmood> mood, featuring \u003Cinstruments>,\n   at a \u003Ctempo> tempo, evoking \u003Cscene>.\n   ```\n\n   **Diverse examples**:\n   ```\n   # Encouragement for the workday\n   A deep warm androgynous voice with cozy delivery. An energetic synth-pop track\n   with a fiery, uplifting mood, driven by pulsing synthesizers and electronic drums\n   at a fast tempo, capturing the rush of a morning commute.\n\n   # Waiting for the owner to come home\n   A deep warm androgynous voice with cozy delivery. A warm city pop song with sweet,\n   tender feelings, featuring electric piano and groovy bass at a mid-tempo pace,\n   set on a sunny afternoon windowsill waiting for someone to come home.\n\n   # Complaining about overtime\n   A deep warm androgynous voice with cozy delivery. A playful funk track with a\n   humorous, laid-back vibe, featuring slap bass and brass at a groovy mid-tempo,\n   capturing the absurdity of working late in a dim office.\n\n   # Late-night companionship\n   A deep warm androgynous voice with cozy delivery. A calm lo-fi hip-hop piece with\n   a healing, dreamy atmosphere, featuring sampled piano and soft electronic drums\n   at a slow tempo, evoking a quiet late-night desk with warm lamp light.\n   ```\n\n2. **Generate lyrics**: Use `--lyrics-optimizer` to auto-generate lyrics, or write lyrics\n   yourself when you need to control the perspective.\n\n   **Important — perspective & personality-driven lyrics**:\n\n   The pet is the singer, so lyrics MUST be written from the **pet's first-person\n   perspective** (\"I\" = the pet, \"you\" = the owner\u002Fuser). The pet is singing TO\n   the owner. For example:\n   - \"I sit by the door waiting for you to come home\" (pet's perspective)\n   - \"Wake up now, my dear human\" (pet singing to owner)\n   - NOT \"I rub my sleepy eyes\" (owner's perspective — wrong)\n   - NOT \"Then you woke up, my little Moth\" (owner talking about pet — wrong)\n\n   The pet's personality should shape the lyrics' tone and word choice:\n   - \"of few words\" → short, impactful lines, minimal filler\n   - \"playful\" → rhyming, bouncy phrasing, fun wordplay\n   - \"poetic\" → metaphor-rich, flowing imagery\n   - \"fierce\" → direct, powerful declarations\n\n   The pet's name may appear in the lyrics (e.g., in a chorus hook) but the\n   narrative voice is always the pet speaking\u002Fsinging.\n\n   **When perspective matters**: Write the lyrics yourself and pass via `--lyrics`.\n   **When perspective is not critical**: Use `--lyrics-optimizer` for convenience.\n\n3. **Preview (MUST show full content)**: Before generating, show the user the\n   **complete lyrics** and **full prompt** — no abbreviation, no `...`, no summary.\n   This is part of the fun — the user wants to read and enjoy the lyrics before\n   hearing them sung.\n\n   The API prompt is always constructed in English (for best generation quality).\n   When responding in a non-English language, show a **localized description** of\n   the prompt in the user's language for readability. The English prompt is an\n   internal implementation detail — do not show it to the user. Translate all\n   labels (Singer, Theme, Description, Confirm, etc.) into the user's language.\n\n   Template (English reference — localize all labels at runtime):\n\n   ```\n   About to generate:\n   Singer: \u003Cname>\n   Theme: \u003Ctheme>\n\n   Lyrics:\n   [verse]\n   \u003Cfull verse lyrics here>\n\n   [chorus]\n   \u003Cfull chorus lyrics here>\n\n   ... (show ALL sections in full)\n\n   Description: \u003Clocalized description of the song style and mood>\n\n   Confirm? (press enter to confirm, or tell me what to change)\n   ```\n\n   **Never truncate or abbreviate** the lyrics or prompt in the preview.\n   The user should see exactly what will be sent to the API.\n\n4. **Call music generation**:\n\n   **With auto-generated lyrics (perspective not critical):**\n   ```bash\n   mmx music generate \\\n     --prompt \"\u003Cfull combined prompt>\" \\\n     --lyrics-optimizer \\\n     --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cname>_sings_\u003CYYYYMMDD_HHMMSS>.mp3 \\\n     --quiet --non-interactive\n   ```\n\n   **With self-written lyrics (perspective-controlled):**\n   ```bash\n   mmx music generate \\\n     --prompt \"\u003Cfull combined prompt>\" \\\n     --lyrics \"\u003Clyrics with correct pet perspective>\" \\\n     --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cname>_sings_\u003CYYYYMMDD_HHMMSS>.mp3 \\\n     --quiet --non-interactive\n   ```\n\n---\n\n## Step 5: Play & Feedback\n\n### Cross-platform playback\n\nDetect the available audio player and play the generated file:\n\n```bash\nif command -v mpv >\u002Fdev\u002Fnull 2>&1; then\n  mpv --no-video ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\nelif command -v ffplay >\u002Fdev\u002Fnull 2>&1; then\n  ffplay -nodisp -autoexit ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\nelif command -v afplay >\u002Fdev\u002Fnull 2>&1; then\n  afplay ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\nelse\n  echo \"No audio player found. Your song is saved at: ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\"\nfi\n```\n\nAfter starting playback, tell the user the file is playing and where it's saved.\nDo NOT show playback controls (e.g. keyboard shortcuts) — they don't work in this\nenvironment since the player runs in the background.\n\nIf no player is found, show the file path and suggest installing mpv.\n\n### Feedback\n\nAfter playback, ask for feedback (localize all text):\n\n```\nHow was \u003Cname>'s performance?\n\n1. Amazing! Keep it!\n2. Try a different theme \u002F style\n3. Fine-tune the lyrics and regenerate\n4. Try another random one\n```\n\n---\n\n## Edge Cases\n\n| Situation | Action |\n|-----------|--------|\n| No `~\u002F.claude.json` | Tell user to run `\u002Fbuddy` first |\n| Companion field is empty | Same — guide to `\u002Fbuddy` |\n| mmx CLI not installed | Print: \"You need to install mmx CLI: `npm install -g mmx-cli && mmx auth login`\" |\n| No audio player found | Show file path and suggest installing mpv |\n| No memory files found | Suggest a custom theme or random mode |\n| User wants to change the pet's voice | Delete cache, re-interpret personality |\n| User wants a specific genre | Let them override — append their genre to the prompt |\n\n---\n\n## Notes\n\n- The vocal identity is based on **name + personality** only. No species\u002Frarity\n  template mapping.\n- Voice is cached and consistent across sessions. Same pet = same voice.\n- Lyrics should always be **original** — never reproduce copyrighted lyrics.\n- The pet's personality shapes both the **voice** (how they sound) and the\n  **lyrics** (what they say and how they say it).\n- All generated files go to `~\u002FMusic\u002Fminimax-gen\u002F` with the pet name in the\n  filename.\n","# Buddy Sings — Let Your Claude Code Pet Sing\n\nTurn your Claude Code pet into a singer. Each pet gets a unique vocal identity\nbased on its name and personality — the same pet always sounds the same.\n\n## Prerequisites\n\n- **mmx CLI** (required for music generation):\n\n  **Install:**\n  ```bash\n  npm install -g mmx-cli\n  ```\n\n  **Authenticate (first time only):**\n  ```bash\n  mmx auth login --api-key \u003Cyour-minimax-api-key>\n  ```\n  Get your API key from [MiniMax Platform](https:\u002F\u002Fplatform.minimaxi.com\u002F).\n\n- **Audio player** (for playback — at least one of):\n  - `mpv` (recommended — interactive controls: space = pause, q = quit)\n  - `ffplay` (from FFmpeg)\n  - `afplay` (macOS built-in)\n\n---\n\n## Workflow Overview\n\n```\nCheck pet → Build vocal identity → Gather context → Generate music → Play & feedback\n```\n\n---\n\n## Language & Interaction\n\nDetect the user's language from their first message. Respond in the same language\nthroughout the entire session. All examples below are in English — translate them\nnaturally when responding in other languages.\n\n**User-facing text localization rule**:\n- ALL text shown to the user — including pet info, voice description, lyrics preview,\n  prompt preview, playback info, and feedback prompts — MUST be fully translated into\n  the user's language.\n- The **API prompt** sent to the model should always be written in English for best\n  generation quality. However, when previewing the prompt to the user, show a localized\n  description in the user's language instead of the raw English prompt. The English prompt\n  is an internal implementation detail — the user does not need to see it.\n- The templates below are written in English as reference. At runtime, translate every\n  label and message into the user's detected language.\n\nThe pet sings in the user's language by default. Embed the singing language\nnaturally in the vocal description (e.g., \"singing in Japanese\" or \"singing in\nMandarin Chinese\") rather than appending a separate language tag. If the user\nexplicitly requests a different language for the lyrics, honor that request.\n\n---\n\n## Step 1: Check for Pet\n\nRead `~\u002F.claude.json` and look for the `companion` field.\n\nIf no companion is found or the field is empty, tell the user:\n\n```\nYou don't have a pet yet! Type \u002Fbuddy to adopt one, then come back to let it sing.\n```\n\nStop here and wait for the user to adopt a pet. Do not proceed without a pet.\n\nIf a companion exists, extract its profile:\n- `name` — the pet's name\n- `personality` — the pet's personality description\n\nPresent the pet to the user:\n\n```\nFound your pet!\n   Name: \u003Cname>\n   Personality: \u003Cpersonality>\n```\n\n---\n\n## Step 2: Build Vocal Identity\n\nBased on the pet's **name** and **personality** text, creatively design a unique\nvocal identity. No template lookups — interpret the personality freely.\n\n### How to interpret personality into voice\n\nRead the personality text and craft vocal attributes:\n\n- **Timbre**: What does this personality sound like? e.g., \"few words\" →\n  low, warm, deliberate; \"energetic\" → bright, punchy; \"mysterious\" → breathy,\n  dark; \"legendary chonk\" → thick, warm, cozy\n- **Singing style**: How would they deliver a song? e.g., \"of few words\" →\n  sparse, dramatic pauses; \"playful\" → bouncy, rhythmic; \"poetic\" → flowing, legato\n- **Mood**: What emotional tone fits? e.g., \"chill\" → relaxed, laid-back;\n  \"fierce\" → intense, powerful\n\nConstruct a `prompt_fragment` that describes the vocal style in English, embedding\nthe singing language naturally. For example:\n\n```\nVocal: warm low female voice singing in Mandarin Chinese with cozy thick timbre,\nsparse minimalist delivery with dramatic pauses giving each word weight, relaxed\nlaid-back mood.\n```\n\n### Voice caching\n\nThe vocal identity must be **cached** so the pet always sounds the same.\n\n- Cache file: `~\u002F.claude\u002Fskills\u002Fbuddy-sings\u002Fvoices\u002F\u003Cname>.json`\n- Cache format:\n  ```json\n  {\n    \"name\": \"Moth\",\n    \"personality\": \"A legendary chonk of few words.\",\n    \"prompt_fragment\": \"Vocal: warm low female voice singing in Mandarin Chinese...\",\n    \"cached_at\": \"2026-04-07T19:52:15\"\n  }\n  ```\n\n**First time**: No cache exists → interpret personality → save to cache file.\n\n**Subsequent calls**: Read cache → use the saved `prompt_fragment` directly.\nDo NOT re-interpret — consistency matters.\n\n**Cache invalidation**: If the `personality` in `~\u002F.claude.json` differs from what's\ncached, the pet has changed — regenerate and save a new cache.\n\n**Manual regeneration**: If the user says \"change the voice\" or \"regenerate voice\":\ndelete the cache file and re-interpret from scratch.\n\n### Present the voice to the user\n\n```\n\u003Cname>'s unique voice:\n\nTimbre: \u003Ctimbre description>\nStyle: \u003Cstyle description>\nMood: \u003Cmood description>\n\nLet's pick what \u003Cname> should sing about!\n```\n\n---\n\n## Step 3: Understand Intent & Gather Context\n\n**Do NOT always present a mode menu.** Instead, analyze the user's request to\ndetermine what context is needed, and auto-gather it.\n\n### Auto-context detection\n\nWhen the user's request implies personal context, **automatically** scan for\nrelevant information without asking. Triggers include:\n\n- **Time-based references**: \"today\", \"this week\", \"recently\", \"yesterday\" → scan\n  current conversation history and memory files for what happened in that period\n- **Personal references**: \"my work\", \"my day\", \"what I did\" → scan memory\n  and conversation for the user's activities\n- **Relationship references**: \"our story\", \"what we did together\" → scan memory for\n  shared experiences between user and pet\u002FClaude\n\n### Context gathering (auto, not mode-gated)\n\nWhen context is needed, scan these sources in order:\n\n1. **Current conversation context**: Look at what the user has been doing in\n   this Claude Code session — files edited, commands run, topics discussed.\n   This is the richest source for \"today\" type requests.\n\n2. **Memory files**: Scan for relevant memories:\n   ```bash\n   find ~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002F -name \"*.md\" 2>\u002Fdev\u002Fnull | head -20\n   ```\n   Also check `~\u002F.claude\u002Fmemory\u002F` if it exists.\n   Read found files and extract themes relevant to the user's request.\n\n3. **Git history** (if in a repo): For work-related songs, check recent commits:\n   ```bash\n   git log --oneline --since=\"today\" 2>\u002Fdev\u002Fnull | head -10\n   ```\n\nUse gathered context to enrich the lyrics prompt — make the song personal and\nspecific to what actually happened, not generic.\n\n### When NO context is needed\n\nIf the user's request is a clear standalone scene (e.g., \"sing a rainy day song\",\n\"sing a lullaby\"), skip context gathering and proceed directly to music generation.\n\n### When context is ambiguous\n\nOnly ask for clarification when you genuinely can't determine what the user wants.\nDon't present a mode menu — ask a specific question:\n\n```\nWhat should \u003Cname> sing about?\n\nFor example:\n  - \"Today's work\" — I'll check what you've been up to\n  - \"My pet waiting by the window for me to come home\"\n  - Or let me pick a random theme?\n```\n\n### Fallback to random\n\nIf context gathering finds nothing useful (no memory files, no conversation\nhistory, no git log), fall back to random theme generation based on the pet's\npersonality:\n- Quiet\u002Freserved personality → midnight lullaby, gentle sunset, quiet morning\n- Energetic personality → party jam, adventure song, victory march\n- Mysterious personality → moonlit serenade, secret whisper, dream journey\n\nTell the user what theme was picked.\n\n---\n\n## Step 4: Generate Music\n\nCombine the vocal identity with the chosen theme.\n\n1. **Construct the full prompt**: The prompt has two parts that MUST both be present:\n\n   **Part A — Vocal identity (MUST come first)**: Always start the prompt with the\n   cached `prompt_fragment`. This is the most important part — it defines who is\n   singing. Place it at the beginning of the prompt so the API prioritizes it.\n\n   **Part B — Genre\u002Fstyle\u002Fmood tags**: Choose tags that **match the theme**, NOT\n   a default set. Vary the genre deliberately based on what the song is about.\n\n   Write prompts as **vivid English sentences**, not comma-separated tags.\n   Follow this pattern: `A [mood] [genre] song, featuring [vocal description],\n   about [narrative\u002Ftheme], [atmosphere], [key instruments and production].`\n   Describe vocals as a character (\"sultry baritone with jazz inflections\"),\n   not just a gender. Include a scene or vibe to anchor the generation.\n\n   **Genre matching guidelines** — pick a genre that fits the theme's energy:\n\n   | Theme energy | Suggested genres | Avoid |\n   |-------------|-----------------|-------|\n   | Encouragement \u002F motivation \u002F cheer | Indie rock, synth-pop, funk, rap | Indie folk, healing |\n   | Daily life \u002F warmth \u002F companionship | Mandopop, city pop, bossa nova | Same as last time |\n   | Missing someone \u002F waiting | Folk, R&B, lo-fi | Rock, EDM |\n   | Humor \u002F roasting \u002F complaining | Funk, rap, ska, electro-pop | Classical, ballad |\n   | Late night \u002F quiet | Ambient, piano piece, lo-fi, neoclassical | Upbeat, EDM |\n   | Celebration \u002F achievement | EDM, future bass, funk, K-pop | Slow tempo, melancholy |\n   | Work routine | City pop, synth-pop, lo-fi hip-hop, indie rock | Same genre every time |\n\n   **Anti-monotony rule**: NEVER use the same genre combination twice in a row.\n   Before constructing the prompt, recall what genre was used in the previous\n   generation (if any in this session) and pick something different.\n\n   **Prompt structure** — write as vivid English sentences, not comma-separated tags:\n   ```\n   \u003Cvocal prompt_fragment>. A \u003Cgenre> song with \u003Cmood> mood, featuring \u003Cinstruments>,\n   at a \u003Ctempo> tempo, evoking \u003Cscene>.\n   ```\n\n   **Diverse examples**:\n   ```\n   # Encouragement for the workday\n   A deep warm androgynous voice with cozy delivery. An energetic synth-pop track\n   with a fiery, uplifting mood, driven by pulsing synthesizers and electronic drums\n   at a fast tempo, capturing the rush of a morning commute.\n\n   # Waiting for the owner to come home\n   A deep warm androgynous voice with cozy delivery. A warm city pop song with sweet,\n   tender feelings, featuring electric piano and groovy bass at a mid-tempo pace,\n   set on a sunny afternoon windowsill waiting for someone to come home.\n\n   # Complaining about overtime\n   A deep warm androgynous voice with cozy delivery. A playful funk track with a\n   humorous, laid-back vibe, featuring slap bass and brass at a groovy mid-tempo,\n   capturing the absurdity of working late in a dim office.\n\n   # Late-night companionship\n   A deep warm androgynous voice with cozy delivery. A calm lo-fi hip-hop piece with\n   a healing, dreamy atmosphere, featuring sampled piano and soft electronic drums\n   at a slow tempo, evoking a quiet late-night desk with warm lamp light.\n   ```\n\n2. **Generate lyrics**: Use `--lyrics-optimizer` to auto-generate lyrics, or write lyrics\n   yourself when you need to control the perspective.\n\n   **Important — perspective & personality-driven lyrics**:\n\n   The pet is the singer, so lyrics MUST be written from the **pet's first-person\n   perspective** (\"I\" = the pet, \"you\" = the owner\u002Fuser). The pet is singing TO\n   the owner. For example:\n   - \"I sit by the door waiting for you to come home\" (pet's perspective)\n   - \"Wake up now, my dear human\" (pet singing to owner)\n   - NOT \"I rub my sleepy eyes\" (owner's perspective — wrong)\n   - NOT \"Then you woke up, my little Moth\" (owner talking about pet — wrong)\n\n   The pet's personality should shape the lyrics' tone and word choice:\n   - \"of few words\" → short, impactful lines, minimal filler\n   - \"playful\" → rhyming, bouncy phrasing, fun wordplay\n   - \"poetic\" → metaphor-rich, flowing imagery\n   - \"fierce\" → direct, powerful declarations\n\n   The pet's name may appear in the lyrics (e.g., in a chorus hook) but the\n   narrative voice is always the pet speaking\u002Fsinging.\n\n   **When perspective matters**: Write the lyrics yourself and pass via `--lyrics`.\n   **When perspective is not critical**: Use `--lyrics-optimizer` for convenience.\n\n3. **Preview (MUST show full content)**: Before generating, show the user the\n   **complete lyrics** and **full prompt** — no abbreviation, no `...`, no summary.\n   This is part of the fun — the user wants to read and enjoy the lyrics before\n   hearing them sung.\n\n   The API prompt is always constructed in English (for best generation quality).\n   When responding in a non-English language, show a **localized description** of\n   the prompt in the user's language for readability. The English prompt is an\n   internal implementation detail — do not show it to the user. Translate all\n   labels (Singer, Theme, Description, Confirm, etc.) into the user's language.\n\n   Template (English reference — localize all labels at runtime):\n\n   ```\n   About to generate:\n   Singer: \u003Cname>\n   Theme: \u003Ctheme>\n\n   Lyrics:\n   [verse]\n   \u003Cfull verse lyrics here>\n\n   [chorus]\n   \u003Cfull chorus lyrics here>\n\n   ... (show ALL sections in full)\n\n   Description: \u003Clocalized description of the song style and mood>\n\n   Confirm? (press enter to confirm, or tell me what to change)\n   ```\n\n   **Never truncate or abbreviate** the lyrics or prompt in the preview.\n   The user should see exactly what will be sent to the API.\n\n4. **Call music generation**:\n\n   **With auto-generated lyrics (perspective not critical):**\n   ```bash\n   mmx music generate \\\n     --prompt \"\u003Cfull combined prompt>\" \\\n     --lyrics-optimizer \\\n     --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cname>_sings_\u003CYYYYMMDD_HHMMSS>.mp3 \\\n     --quiet --non-interactive\n   ```\n\n   **With self-written lyrics (perspective-controlled):**\n   ```bash\n   mmx music generate \\\n     --prompt \"\u003Cfull combined prompt>\" \\\n     --lyrics \"\u003Clyrics with correct pet perspective>\" \\\n     --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cname>_sings_\u003CYYYYMMDD_HHMMSS>.mp3 \\\n     --quiet --non-interactive\n   ```\n\n---\n\n## Step 5: Play & Feedback\n\n### Cross-platform playback\n\nDetect the available audio player and play the generated file:\n\n```bash\nif command -v mpv >\u002Fdev\u002Fnull 2>&1; then\n  mpv --no-video ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\nelif command -v ffplay >\u002Fdev\u002Fnull 2>&1; then\n  ffplay -nodisp -autoexit ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\nelif command -v afplay >\u002Fdev\u002Fnull 2>&1; then\n  afplay ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\nelse\n  echo \"No audio player found. Your song is saved at: ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\"\nfi\n```\n\nAfter starting playback, tell the user the file is playing and where it's saved.\nDo NOT show playback controls (e.g. keyboard shortcuts) — they don't work in this\nenvironment since the player runs in the background.\n\nIf no player is found, show the file path and suggest installing mpv.\n\n### Feedback\n\nAfter playback, ask for feedback (localize all text):\n\n```\nHow was \u003Cname>'s performance?\n\n1. Amazing! Keep it!\n2. Try a different theme \u002F style\n3. Fine-tune the lyrics and regenerate\n4. Try another random one\n```\n\n---\n\n## Edge Cases\n\n| Situation | Action |\n|-----------|--------|\n| No `~\u002F.claude.json` | Tell user to run `\u002Fbuddy` first |\n| Companion field is empty | Same — guide to `\u002Fbuddy` |\n| mmx CLI not installed | Print: \"You need to install mmx CLI: `npm install -g mmx-cli && mmx auth login`\" |\n| No audio player found | Show file path and suggest installing mpv |\n| No memory files found | Suggest a custom theme or random mode |\n| User wants to change the pet's voice | Delete cache, re-interpret personality |\n| User wants a specific genre | Let them override — append their genre to the prompt |\n\n---\n\n## Notes\n\n- The vocal identity is based on **name + personality** only. No species\u002Frarity\n  template mapping.\n- Voice is cached and consistent across sessions. Same pet = same voice.\n- Lyrics should always be **original** — never reproduce copyrighted lyrics.\n- The pet's personality shapes both the **voice** (how they sound) and the\n  **lyrics** (what they say and how they say it).\n- All generated files go to `~\u002FMusic\u002Fminimax-gen\u002F` with the pet name in the\n  filename.\n",{"name":5,"license":14,"version":23,"category":24,"metadata":25,"description":28},"1.0.0 Use when user wants their Claude Code pet (\u002Fbuddy) to sing a song. Triggers on any request that combines the concept of their Claude Code buddy, pet, or companion with singing or music. Supports multilingual triggers — match equivalent phrases in any language.","development-code",{"version":26,"category":27},"1.1","creative","","main","d591030ef9fb1bbcebed3454aa5c2dcb8d608f69","skills-hub\u002Fmarketplace\u002Fclaude-code-skills\u002Fskills\u002Fbuddy-sings","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive","https:\u002F\u002Fai-agent.yyc3.vip\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-13 22:26:14",{"source":7,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill buddy-sings",{"tool":43,"command":44},"bunx","bunx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill buddy-sings",{"tool":46,"command":47},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill buddy-sings","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fmarketplace\u002Fclaude-code-skills\u002Fskills\u002Fbuddy-sings\u002FSKILL.md",true,[],[52,59,66,73,80,89],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7BTB92RE8MT5YE706QBNDTQ","yingmi-skill","当用户需要查询基金、策略、公告、财经资讯，做资产配置、组合诊断、风险回测、现金流分析，或生成图表、PDF 时，优先使用本 Skill 获取真实数据与可执行能力。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fyingmi-skill\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7BT7ZYR091HPJYEFNWVTEJJ","web-access","所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fweb-access\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7BT4NKS0DNP8A53M1BGGZR2","tencentmap-map-assistant","腾讯位置服务·地图助手 Skill，一句自然语言调用腾讯地图全套能力，无需开发者账号、开箱即用。提供 AI 旅游攻略、地点搜索（含评分\u002F人均\u002F营业时间）、关键词提示、路线规划（驾车\u002F步行\u002F公交\u002F骑行）、地址解析与逆解析、行政区划、IP 定位、距离计算、天气查询，并可将行程或多 POI 渲染成网页地图。涉及找地点、规划路线、旅游行程、查天气、坐标转换等出行场景时使用。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Ftencentmap-map-assistant\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7BSWKV1T5XYYRGV4W4JP88C","skill-scanner","Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描, 检查 skill 安全, audit skill, scan skill, check skill safety, analyze skill, inspect skill, verify skill, skill security, skill supply chain. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-scanner\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":84,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M7BSWGTCFW7F123S4BM4XY6W","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M7BSVV4DH8JK2ZMQSCW25VCD","shader-dev","Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fshader-dev\u002FSKILL.md",[],[]]