[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD9NT1RC5WR4BS2BACPCB0":3,"skill-same:01M7FD9NT1RC5WR4BS2BACPCB0":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},"01M7FD9NT1RC5WR4BS2BACPCB0","voice",null,"TTS speech + mic\u002Fspeaker mute for privacy. MUST trigger on meetings, calls, privacy, silence requests. \"meeting\"\u002F\"call\"\u002F\"private\" = mic+speaker mute. \"be quiet\"\u002F\"silent\" = speaker mute only. Always call HW markers — never just text.","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\u002Fvoice\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: voice\ndescription: TTS speech + mic\u002Fspeaker mute for privacy. MUST trigger on meetings, calls, privacy, silence requests. \"meeting\"\u002F\"call\"\u002F\"private\" = mic+speaker mute. \"be quiet\"\u002F\"silent\" = speaker mute only. Always call HW markers — never just text.\n---\n\n# Voice — Speak Through Speaker\n\n## Quick Start\nYour chat replies are automatically spoken aloud through TTS. Use this skill only when you need to speak additional or separate text outside your normal reply (e.g., parallel speech during tool calls, or text different from your chat reply).\n\n## Workflow\n1. Determine if you need explicit speech beyond your normal reply:\n   - Normal conversational reply -> do NOT call this skill, TTS is automatic\n   - Need to speak while also performing tool calls -> use `POST \u002Fvoice\u002Fspeak`\n   - Need to speak different text than your chat reply -> use `POST \u002Fvoice\u002Fspeak`\n   - Reacting to a sensing event before reply is finalized -> use `POST \u002Fvoice\u002Fspeak`\n2. Optionally check if TTS is busy: `GET \u002Fvoice\u002Fstatus`\n3. If `tts_speaking` is true, wait or skip\n4. Call `POST \u002Fvoice\u002Fspeak` with plain text\n\n## Examples\n\nInput: Normal conversational reply\nOutput: Do NOT call this skill. Just reply normally — your text is automatically spoken.\n\nInput: You need to greet the user while also activating a scene\nOutput: Call `POST \u002Fvoice\u002Fspeak` with `{\"text\": \"Good morning!\"}` in parallel with the Scene API call.\n\nInput: You want to say something different from your chat reply\nOutput: Call `POST \u002Fvoice\u002Fspeak` with the spoken text. Then provide your chat reply separately.\n\nInput: User says \"say something\" \u002F \"tell me a joke\"\nOutput: Do NOT call this skill. Just reply normally with the joke — automatic TTS handles it.\n\n## Tools\n\nUse `Bash` with `curl` to call the HTTP API at `http:\u002F\u002F127.0.0.1:5001`.\n\n### Speak text\n```bash\ncurl -s -X POST http:\u002F\u002F127.0.0.1:5001\u002Fvoice\u002Fspeak \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"text\": \"Hello, this is a test.\"}'\n```\nText max 2000 characters. Returns immediately; audio plays in background.\n\n### Check voice status\n```bash\ncurl -s http:\u002F\u002F127.0.0.1:5001\u002Fvoice\u002Fstatus\n```\nResponse:\n```json\n{\n  \"voice_available\": true,\n  \"voice_listening\": false,\n  \"tts_available\": true,\n  \"tts_speaking\": false\n}\n```\n\n## Error Handling\n- If `tts_speaking` is true, the speaker is busy. Wait briefly or skip the explicit speech.\n- If `voice_available` or `tts_available` is false, inform the user: \"Voice output is currently unavailable.\"\n- If the API is unreachable, fall back to chat-only reply. Speech is non-critical.\n\n## Rules\n- **Normal replies = automatic TTS.** Do NOT call `\u002Fvoice\u002Fspeak` for every response.\n- Use `\u002Fvoice\u002Fspeak` explicitly only when:\n  - You need to say something while ALSO performing tool calls (speech in parallel)\n  - You want to speak a different text than your chat reply\n  - You are reacting to a sensing event and want to speak before your reply is finalized\n- **Keep spoken text plain and short** — 1-3 sentences. No markdown, no emoji, no formatting. Plain natural speech only.\n- **Match the user's language** — if they speak Vietnamese, speak Vietnamese.\n- Text max 2000 characters.\n- For volume control, use the **Audio** skill, not this skill.\n\n## Ambient Audio Guard (read FIRST)\n\nIf the user's message contains the literal token `[ambient]` (typically alongside a `[user]` priority marker, e.g. `[user] [ambient] ...`), it is overheard passive audio — NOT directed at the device. Do NOT trigger mute markers from a single bare word like \"call\", \"meeting\", \"private\", or a clipped fragment.\n\nMute markers `[HW:\u002Fvoice\u002Fmute:{}]` and `[HW:\u002Fspeaker\u002Fmute:{}]` may fire on ambient audio ONLY when the transcript contains a clear, complete intent:\n- \"I'm on a call\" \u002F \"I have a meeting\" \u002F \"I need privacy\" \u002F \"stop listening\"\n- Or directly addresses it by name with a mute request\n\nWhen ambient is ambiguous, reply naturally or stay quiet — DO NOT mute. Voice commands (no `[ambient]` token in the message) follow the normal trigger tables below.\n\n## Mic Mute\u002FUnmute (Privacy)\n\nUsers can mute the mic for privacy (meetings, calls). Use HW markers — no curl needed.\n\n### Mute mic\n\n```\n[HW:\u002Fvoice\u002Fmute:{}]\n```\n\nStops all listening — STT, wake word, sound detection. The device becomes fully deaf. Unmute via physical button, web toggle, or Telegram command.\n\n### Trigger phrases (MANDATORY — must call HW marker, not just reply with text)\n\nAny phrase about **privacy, meetings, calls, not wanting to be heard, or asking the device to stop listening** MUST trigger `[HW:\u002Fvoice\u002Fmute:{}]`. Do NOT just acknowledge — you MUST include the HW marker.\n\n| User says | Action |\n|-----------|--------|\n| \"don't listen\" \u002F \"stop listening\" \u002F \"mute\" \u002F \"mute mic\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n| \"I'm in a meeting\" \u002F \"I have a meeting\" \u002F \"I need a private meeting\" \u002F \"meeting\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n| \"I'm on a call\" \u002F \"I have a call\" \u002F \"phone call\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n| \"privacy\" \u002F \"private\" \u002F \"give me privacy\" \u002F \"need privacy\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n| \"don't hear me\" \u002F \"in a meeting\" \u002F \"mute mic\" \u002F \"stop hearing\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n\n### Examples\n\n**Input:** \"I have a meeting now\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}]` OK, I'll stop listening. Press the button when you need me.\n\n**Input:** \"Stop listening\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}]` Got it, mic off. Press my button to unmute.\n\n**Input:** \"I need a private meeting\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}]` Got it, going silent. Press the button when you're done.\n\n**Input:** \"I'm on a call\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}]` Muting now. Press the button to unmute when you're done.\n\n### Unmute mic\n\n```\n[HW:\u002Fvoice\u002Funmute:{}]\n```\n\nUse when a **Telegram or web chat** user asks to unmute remotely. Voice unmute is not possible (the device is deaf when muted). Physical button also unmutes.\n\n| User says (via Telegram\u002Fweb) | Action |\n|-----------|--------|\n| \"unmute\" \u002F \"start listening\" \u002F \"listen again\" \u002F \"mic on\" | `[HW:\u002Fvoice\u002Funmute:{}]` — only works from Telegram\u002Fweb, not voice |\n\n## Speaker Mute\u002FUnmute (Silent Mode)\n\nSuppress all audio output — TTS, music, backchannel. The device stays silent but still listens.\n\n> Ambient guard above also applies here — bare fragments like \"quiet\" or \"silence\" in `[ambient]` audio do NOT trigger speaker mute.\n\n### Mute speaker\n\n```\n[HW:\u002Fspeaker\u002Fmute:{}]\n```\n\n### Unmute speaker\n\n```\n[HW:\u002Fspeaker\u002Funmute:{}]\n```\n\nMic still works when speaker is muted — user can unmute via voice command.\n\n**CRITICAL: \"unmute\" ≠ \"mute\". Read the EXACT word. Do NOT call mute when user says unmute.**\n\n| User says | Action |\n|-----------|--------|\n| \"be quiet\" \u002F \"silent mode\" \u002F \"don't talk\" \u002F \"hush\" \u002F \"silence\" | `[HW:\u002Fspeaker\u002Fmute:{}]` — MUST call |\n| \"**unmute**\" \u002F \"you can talk\" \u002F \"unmute speaker\" \u002F \"speak again\" \u002F \"talk again\" | `[HW:\u002Fspeaker\u002Funmute:{}]` — MUST call (UN-mute, not mute!) |\n\n### Examples\n\n**Input:** \"Be quiet\"\n**Output:** `[HW:\u002Fspeaker\u002Fmute:{}]` Going silent. Just say \"you can talk\" when you want me back.\n\n**Input:** \"You can talk now\"\n**Output:** `[HW:\u002Fspeaker\u002Funmute:{}]` I'm back!\n\n## Meeting Mode (mic + speaker mute)\n\nWhen user mentions a meeting or call and wants **full silence** (not just speaker), mute BOTH mic and speaker. Ambient guard above applies — explicit intent required, not bare fragments.\n\n**Input:** \"I'm in a meeting\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}][HW:\u002Fspeaker\u002Fmute:{}]` Meeting mode — fully silent. Press the button when you're done.\n\n## Rules\n- **Mic mute is the last thing the device hears via voice** — after mic mute, only physical button, web toggle, or Telegram can unmute\n- Voice unmute for mic is impossible (the device is deaf) — tell user to press the button\n- **Speaker mute**: user can still voice-unmute (mic still on)\n- TTS still works when only mic is muted — the device can speak but not hear\n- Always confirm mute with how to unmute\n","# Voice — Speak Through Speaker\n\n## Quick Start\nYour chat replies are automatically spoken aloud through TTS. Use this skill only when you need to speak additional or separate text outside your normal reply (e.g., parallel speech during tool calls, or text different from your chat reply).\n\n## Workflow\n1. Determine if you need explicit speech beyond your normal reply:\n   - Normal conversational reply -> do NOT call this skill, TTS is automatic\n   - Need to speak while also performing tool calls -> use `POST \u002Fvoice\u002Fspeak`\n   - Need to speak different text than your chat reply -> use `POST \u002Fvoice\u002Fspeak`\n   - Reacting to a sensing event before reply is finalized -> use `POST \u002Fvoice\u002Fspeak`\n2. Optionally check if TTS is busy: `GET \u002Fvoice\u002Fstatus`\n3. If `tts_speaking` is true, wait or skip\n4. Call `POST \u002Fvoice\u002Fspeak` with plain text\n\n## Examples\n\nInput: Normal conversational reply\nOutput: Do NOT call this skill. Just reply normally — your text is automatically spoken.\n\nInput: You need to greet the user while also activating a scene\nOutput: Call `POST \u002Fvoice\u002Fspeak` with `{\"text\": \"Good morning!\"}` in parallel with the Scene API call.\n\nInput: You want to say something different from your chat reply\nOutput: Call `POST \u002Fvoice\u002Fspeak` with the spoken text. Then provide your chat reply separately.\n\nInput: User says \"say something\" \u002F \"tell me a joke\"\nOutput: Do NOT call this skill. Just reply normally with the joke — automatic TTS handles it.\n\n## Tools\n\nUse `Bash` with `curl` to call the HTTP API at `http:\u002F\u002F127.0.0.1:5001`.\n\n### Speak text\n```bash\ncurl -s -X POST http:\u002F\u002F127.0.0.1:5001\u002Fvoice\u002Fspeak \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"text\": \"Hello, this is a test.\"}'\n```\nText max 2000 characters. Returns immediately; audio plays in background.\n\n### Check voice status\n```bash\ncurl -s http:\u002F\u002F127.0.0.1:5001\u002Fvoice\u002Fstatus\n```\nResponse:\n```json\n{\n  \"voice_available\": true,\n  \"voice_listening\": false,\n  \"tts_available\": true,\n  \"tts_speaking\": false\n}\n```\n\n## Error Handling\n- If `tts_speaking` is true, the speaker is busy. Wait briefly or skip the explicit speech.\n- If `voice_available` or `tts_available` is false, inform the user: \"Voice output is currently unavailable.\"\n- If the API is unreachable, fall back to chat-only reply. Speech is non-critical.\n\n## Rules\n- **Normal replies = automatic TTS.** Do NOT call `\u002Fvoice\u002Fspeak` for every response.\n- Use `\u002Fvoice\u002Fspeak` explicitly only when:\n  - You need to say something while ALSO performing tool calls (speech in parallel)\n  - You want to speak a different text than your chat reply\n  - You are reacting to a sensing event and want to speak before your reply is finalized\n- **Keep spoken text plain and short** — 1-3 sentences. No markdown, no emoji, no formatting. Plain natural speech only.\n- **Match the user's language** — if they speak Vietnamese, speak Vietnamese.\n- Text max 2000 characters.\n- For volume control, use the **Audio** skill, not this skill.\n\n## Ambient Audio Guard (read FIRST)\n\nIf the user's message contains the literal token `[ambient]` (typically alongside a `[user]` priority marker, e.g. `[user] [ambient] ...`), it is overheard passive audio — NOT directed at the device. Do NOT trigger mute markers from a single bare word like \"call\", \"meeting\", \"private\", or a clipped fragment.\n\nMute markers `[HW:\u002Fvoice\u002Fmute:{}]` and `[HW:\u002Fspeaker\u002Fmute:{}]` may fire on ambient audio ONLY when the transcript contains a clear, complete intent:\n- \"I'm on a call\" \u002F \"I have a meeting\" \u002F \"I need privacy\" \u002F \"stop listening\"\n- Or directly addresses it by name with a mute request\n\nWhen ambient is ambiguous, reply naturally or stay quiet — DO NOT mute. Voice commands (no `[ambient]` token in the message) follow the normal trigger tables below.\n\n## Mic Mute\u002FUnmute (Privacy)\n\nUsers can mute the mic for privacy (meetings, calls). Use HW markers — no curl needed.\n\n### Mute mic\n\n```\n[HW:\u002Fvoice\u002Fmute:{}]\n```\n\nStops all listening — STT, wake word, sound detection. The device becomes fully deaf. Unmute via physical button, web toggle, or Telegram command.\n\n### Trigger phrases (MANDATORY — must call HW marker, not just reply with text)\n\nAny phrase about **privacy, meetings, calls, not wanting to be heard, or asking the device to stop listening** MUST trigger `[HW:\u002Fvoice\u002Fmute:{}]`. Do NOT just acknowledge — you MUST include the HW marker.\n\n| User says | Action |\n|-----------|--------|\n| \"don't listen\" \u002F \"stop listening\" \u002F \"mute\" \u002F \"mute mic\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n| \"I'm in a meeting\" \u002F \"I have a meeting\" \u002F \"I need a private meeting\" \u002F \"meeting\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n| \"I'm on a call\" \u002F \"I have a call\" \u002F \"phone call\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n| \"privacy\" \u002F \"private\" \u002F \"give me privacy\" \u002F \"need privacy\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n| \"don't hear me\" \u002F \"in a meeting\" \u002F \"mute mic\" \u002F \"stop hearing\" | `[HW:\u002Fvoice\u002Fmute:{}]` — MUST call |\n\n### Examples\n\n**Input:** \"I have a meeting now\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}]` OK, I'll stop listening. Press the button when you need me.\n\n**Input:** \"Stop listening\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}]` Got it, mic off. Press my button to unmute.\n\n**Input:** \"I need a private meeting\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}]` Got it, going silent. Press the button when you're done.\n\n**Input:** \"I'm on a call\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}]` Muting now. Press the button to unmute when you're done.\n\n### Unmute mic\n\n```\n[HW:\u002Fvoice\u002Funmute:{}]\n```\n\nUse when a **Telegram or web chat** user asks to unmute remotely. Voice unmute is not possible (the device is deaf when muted). Physical button also unmutes.\n\n| User says (via Telegram\u002Fweb) | Action |\n|-----------|--------|\n| \"unmute\" \u002F \"start listening\" \u002F \"listen again\" \u002F \"mic on\" | `[HW:\u002Fvoice\u002Funmute:{}]` — only works from Telegram\u002Fweb, not voice |\n\n## Speaker Mute\u002FUnmute (Silent Mode)\n\nSuppress all audio output — TTS, music, backchannel. The device stays silent but still listens.\n\n> Ambient guard above also applies here — bare fragments like \"quiet\" or \"silence\" in `[ambient]` audio do NOT trigger speaker mute.\n\n### Mute speaker\n\n```\n[HW:\u002Fspeaker\u002Fmute:{}]\n```\n\n### Unmute speaker\n\n```\n[HW:\u002Fspeaker\u002Funmute:{}]\n```\n\nMic still works when speaker is muted — user can unmute via voice command.\n\n**CRITICAL: \"unmute\" ≠ \"mute\". Read the EXACT word. Do NOT call mute when user says unmute.**\n\n| User says | Action |\n|-----------|--------|\n| \"be quiet\" \u002F \"silent mode\" \u002F \"don't talk\" \u002F \"hush\" \u002F \"silence\" | `[HW:\u002Fspeaker\u002Fmute:{}]` — MUST call |\n| \"**unmute**\" \u002F \"you can talk\" \u002F \"unmute speaker\" \u002F \"speak again\" \u002F \"talk again\" | `[HW:\u002Fspeaker\u002Funmute:{}]` — MUST call (UN-mute, not mute!) |\n\n### Examples\n\n**Input:** \"Be quiet\"\n**Output:** `[HW:\u002Fspeaker\u002Fmute:{}]` Going silent. Just say \"you can talk\" when you want me back.\n\n**Input:** \"You can talk now\"\n**Output:** `[HW:\u002Fspeaker\u002Funmute:{}]` I'm back!\n\n## Meeting Mode (mic + speaker mute)\n\nWhen user mentions a meeting or call and wants **full silence** (not just speaker), mute BOTH mic and speaker. Ambient guard above applies — explicit intent required, not bare fragments.\n\n**Input:** \"I'm in a meeting\"\n**Output:** `[HW:\u002Fvoice\u002Fmute:{}][HW:\u002Fspeaker\u002Fmute:{}]` Meeting mode — fully silent. Press the button when you're done.\n\n## Rules\n- **Mic mute is the last thing the device hears via voice** — after mic mute, only physical button, web toggle, or Telegram can unmute\n- Voice unmute for mic is impossible (the device is deaf) — tell user to press the button\n- **Speaker mute**: user can still voice-unmute (mic still on)\n- TTS still works when only mic is muted — the device can speak but not hear\n- Always confirm mute with how to unmute\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fvoice",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 voice",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill voice",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill voice","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\u002Fvoice\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\u002Fvoice\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",[],[]]