[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75TGY3WM85QQHR0V9Z23KMF":3,"skill-same:01M75TGY3WM85QQHR0V9Z23KMF":63},{"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":27,"commitSha":28,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M75TGY3WM85QQHR0V9Z23KMF","stressometer",null,"Passive vocal stress analyzer for the Stressometer R1 Creation. Receives voice transcripts from the R1, extracts acoustic stress proxies from the transcript text (pitch variance keywords, speaking rate estimation, pause patterns, emotional language markers), and returns a 0–100 stress index. All processing runs locally — nothing leaves your machine.","ajohnsonnow\u002Fr1-warren","ajohnsonnow","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F8867891?v=4","01M75T7TQ3B5VRHJF6X2Q7AWWW","Anthony Johnson","01M75T7TQPJG8YZTAVCH4SQW27",0,"MIT","https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fstressometer\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: stressometer\ndescription: >\n  Passive vocal stress analyzer for the Stressometer R1 Creation.\n  Receives voice transcripts from the R1, extracts acoustic stress\n  proxies from the transcript text (pitch variance keywords, speaking\n  rate estimation, pause patterns, emotional language markers), and\n  returns a 0–100 stress index. All processing runs locally — nothing\n  leaves your machine.\nversion: 1.0.0\nauthor: rabbit-r1-skillz\n---\n\n# Stressometer — OpenClaw Skill Setup\n\n## What this skill does\n\nWhen the R1's Stressometer app finishes recording a PTT session, it\nsends the voice transcript and session metadata to your local machine\nvia the OpenClaw bridge. This skill receives that payload, runs a\nlightweight text-based stress analysis, and writes the result back to\nshared storage where the R1 picks it up.\n\n**What is analyzed (on your machine, never in the cloud):**\n\n| Signal | Source | Method |\n|---|---|---|\n| Speaking rate | Transcript word count ÷ session duration | Words per minute, elevated rate = stress marker |\n| Pause pattern proxy | Sentence count ÷ word count | Fewer sentences relative to words = less natural phrasing |\n| Emotional language | Keyword density scan | Anxiety\u002Ffrustration\u002Furgency word list vs. calm\u002Fneutral words |\n| Repetition \u002F filler words | \"um\", \"uh\", \"like\", \"you know\" frequency | High filler density = cognitive load marker |\n| Sentence length variance | Std-dev of per-sentence word counts | High variance = choppy speech, low variance = flat affect |\n\nNo audio recordings are made or stored. The STT transcript (plain text)\nis processed and immediately discarded after the index is calculated.\n\n---\n\n## Prerequisites\n\n- **OpenClaw** installed and running on your local machine.\n  See the main `clawhound\u002FSKILL.md` for OpenClaw setup.\n- **Node.js 18+** (or Python 3.10+ if using the Python adapter)\n- The `openclaw` shared storage path configured and accessible\n\n---\n\n## Installation\n\n1. Copy the `stressometer\u002F` skill folder into your OpenClaw skills directory:\n\n   ```\n   cp -r stressometer\u002F ~\u002F.openclaw\u002Fskills\u002Fstressometer\u002F\n   ```\n\n2. Register the skill in `~\u002F.openclaw\u002Fskills.json`:\n\n   ```json\n   {\n     \"stressometer\": {\n       \"entry\": \"~\u002F.openclaw\u002Fskills\u002Fstressometer\u002Fhandler.js\",\n       \"commands\": [\"analyze\"],\n       \"description\": \"Vocal stress analysis for Stressometer R1 app\"\n     }\n   }\n   ```\n\n3. Restart OpenClaw:\n\n   ```\n   openclaw restart\n   ```\n\n---\n\n## Skill handler (handler.js)\n\nCreate `~\u002F.openclaw\u002Fskills\u002Fstressometer\u002Fhandler.js`:\n\n```js\n\"use strict\";\n\n\u002F\u002F Calm-language markers lower the stress score\nconst CALM_WORDS = new Set([\n  'fine','good','great','okay','relaxed','calm','peaceful','happy','nice',\n  'easy','comfortable','enjoying','rested','settled','clear','focused',\n  'balanced','grateful','content','well','refreshed','smooth','steady',\n]);\n\n\u002F\u002F Stress-language markers raise the stress score\nconst STRESS_WORDS = new Set([\n  'anxious','stressed','worried','overwhelmed','nervous','tense','rush',\n  'deadline','urgent','panic','afraid','scared','frustrated','annoyed',\n  'tired','exhausted','behind','late','problem','difficult','struggling',\n  'pressure','stuck','can\\'t','failing','bad','terrible','awful','awful',\n  'disaster','crisis','trouble','confused','lost','desperate','angry',\n  'furious','upset','horrible','dread','fear','hate','awful','painful',\n]);\n\n\u002F\u002F High-filler-density indicates cognitive load\nconst FILLERS = new Set([\n  'um','uh','like','you know','sort of','kind of','basically','literally',\n  'actually','honestly','whatever','anyway','right','okay',\n]);\n\nmodule.exports = {\n  name: 'stressometer',\n\n  async handle(command, params, storage) {\n    if (command !== 'analyze') {\n      return { status: 'error', error: `Unknown command: ${command}` };\n    }\n\n    const { transcript = '', durationSec = 30, baseline = null } = params;\n\n    if (!transcript.trim()) {\n      return writeResult(storage, 50, 'No transcript provided — returning neutral score.');\n    }\n\n    const words      = transcript.trim().split(\u002F\\s+\u002F);\n    const wordCount  = words.length;\n    const sentences  = transcript.split(\u002F[.!?]+\u002F).filter(s => s.trim().length > 2);\n    const sentCount  = Math.max(1, sentences.length);\n\n    \u002F\u002F 1. Speaking rate (words per minute)\n    const wpm = (wordCount \u002F Math.max(durationSec, 1)) * 60;\n    \u002F\u002F Typical calm speech ~130 wpm, stressed ~160-180+\n    const wpmScore = normalize(wpm, 100, 200); \u002F\u002F 0-1\n\n    \u002F\u002F 2. Pause pattern proxy: avg words per sentence\n    \u002F\u002F More words crammed per sentence (run-on) = more stress\n    const wordsPerSent = wordCount \u002F sentCount;\n    const pauseScore   = normalize(wordsPerSent, 8, 25); \u002F\u002F 0-1\n\n    \u002F\u002F 3. Emotional language scan\n    const lower    = transcript.toLowerCase();\n    const allWords = lower.match(\u002F\\b\\w+\\b\u002Fg) || [];\n    let stressHits = 0;\n    let calmHits   = 0;\n    let fillerHits = 0;\n\n    for (const w of allWords) {\n      if (STRESS_WORDS.has(w)) stressHits++;\n      if (CALM_WORDS.has(w))   calmHits++;\n      if (FILLERS.has(w))      fillerHits++;\n    }\n\n    const emotionScore = normalize(\n      (stressHits - calmHits * 0.6) \u002F Math.max(wordCount, 1) * 100,\n      -2, 6\n    );\n\n    \u002F\u002F 4. Filler density\n    const fillerDensity = (fillerHits \u002F Math.max(wordCount, 1)) * 100;\n    const fillerScore   = normalize(fillerDensity, 0, 8);\n\n    \u002F\u002F 5. Sentence length variance\n    const sentLengths = sentences.map(s => s.trim().split(\u002F\\s+\u002F).length);\n    const sentAvg     = sentLengths.reduce((a, v) => a + v, 0) \u002F Math.max(sentLengths.length, 1);\n    const sentVar     = sentLengths.reduce((a, v) => a + Math.pow(v - sentAvg, 2), 0) \u002F Math.max(sentLengths.length, 1);\n    const sentStdDev  = Math.sqrt(sentVar);\n    \u002F\u002F High variance → choppy speech (stressed); very low variance → flat affect (also mildly stressed)\n    const varianceScore = normalize(Math.abs(sentStdDev - 4), 0, 8);\n\n    \u002F\u002F Weighted composite (0-1)\n    const raw = (\n      wpmScore      * 0.25 +\n      pauseScore    * 0.15 +\n      emotionScore  * 0.35 +\n      fillerScore   * 0.15 +\n      varianceScore * 0.10\n    );\n\n    \u002F\u002F Scale to 0-100 with soft floor\u002Fceiling\n    let index = Math.round(raw * 90 + 5);\n\n    \u002F\u002F Anchor to baseline if available (don't drift wildly from known baseline)\n    if (typeof baseline === 'number' && baseline > 0) {\n      const drift = index - baseline;\n      \u002F\u002F Allow up to ±30 points of drift per session\n      index = Math.round(baseline + Math.max(-30, Math.min(30, drift)));\n    }\n\n    index = Math.max(0, Math.min(100, index));\n\n    return writeResult(storage, index, {\n      wpm: Math.round(wpm),\n      wordsPerSentence: Math.round(wordsPerSent * 10) \u002F 10,\n      stressWordHits: stressHits,\n      calmWordHits: calmHits,\n      fillerDensityPct: Math.round(fillerDensity * 10) \u002F 10,\n      sentenceStdDev: Math.round(sentStdDev * 10) \u002F 10,\n      wordCount,\n      durationSec,\n    });\n  },\n};\n\nfunction normalize(val, min, max) {\n  return Math.max(0, Math.min(1, (val - min) \u002F (max - min)));\n}\n\nasync function writeResult(storage, stressIndex, meta) {\n  const result = {\n    status: 'done',\n    ts: Date.now(),\n    data: {\n      stressIndex,\n      ...(typeof meta === 'object' ? meta : { note: meta }),\n    },\n  };\n  await storage.set('openclaw:resp', JSON.stringify(result));\n  return result;\n}\n```\n\n---\n\n## Payload schema\n\n### R1 → OpenClaw (command: `analyze`)\n\n```json\n{\n  \"skill\": \"stressometer\",\n  \"command\": \"analyze\",\n  \"params\": {\n    \"transcript\": \"The full STT transcript text from the session\",\n    \"durationSec\": 42,\n    \"baseline\": 48,\n    \"ts\": 1718300000000\n  }\n}\n```\n\n### OpenClaw → R1 (response)\n\n```json\n{\n  \"status\": \"done\",\n  \"ts\": 1718300001234,\n  \"data\": {\n    \"stressIndex\": 61,\n    \"wpm\": 157,\n    \"wordsPerSentence\": 14.2,\n    \"stressWordHits\": 3,\n    \"calmWordHits\": 1,\n    \"fillerDensityPct\": 3.1,\n    \"sentenceStdDev\": 5.8,\n    \"wordCount\": 110,\n    \"durationSec\": 42\n  }\n}\n```\n\n`stressIndex` is the only field the R1 app requires. All other fields\nare logged locally for debugging and future calibration.\n\n---\n\n## Fallback behavior\n\nIf OpenClaw is offline or the response times out (30-second timeout),\nStressometer falls back to an on-device estimate: a small random\nperturbation around the stored baseline. The reading is still saved\nand included in trend data. The UI shows no error to the user — it\nsilently degrades.\n\n---\n\n## Data retention\n\n- **On the R1:** Stress index numbers and timestamps only (up to 200\n  readings, ~3 months of daily use). No transcripts.\n- **On your machine:** Nothing is persisted by the handler. Transcripts\n  are analyzed in memory and discarded. If you add logging, store only\n  the computed index, never the transcript text.\n\n---\n\n## Deleting your data\n\nFrom the Stressometer app: hold PTT on the main screen → select\n\"Delete Data\" → confirm. This wipes all readings and the baseline from\nR1 storage. OpenClaw retains nothing, so no action needed on the\nlocal machine.\n","# Stressometer — OpenClaw Skill Setup\n\n## What this skill does\n\nWhen the R1's Stressometer app finishes recording a PTT session, it\nsends the voice transcript and session metadata to your local machine\nvia the OpenClaw bridge. This skill receives that payload, runs a\nlightweight text-based stress analysis, and writes the result back to\nshared storage where the R1 picks it up.\n\n**What is analyzed (on your machine, never in the cloud):**\n\n| Signal | Source | Method |\n|---|---|---|\n| Speaking rate | Transcript word count ÷ session duration | Words per minute, elevated rate = stress marker |\n| Pause pattern proxy | Sentence count ÷ word count | Fewer sentences relative to words = less natural phrasing |\n| Emotional language | Keyword density scan | Anxiety\u002Ffrustration\u002Furgency word list vs. calm\u002Fneutral words |\n| Repetition \u002F filler words | \"um\", \"uh\", \"like\", \"you know\" frequency | High filler density = cognitive load marker |\n| Sentence length variance | Std-dev of per-sentence word counts | High variance = choppy speech, low variance = flat affect |\n\nNo audio recordings are made or stored. The STT transcript (plain text)\nis processed and immediately discarded after the index is calculated.\n\n---\n\n## Prerequisites\n\n- **OpenClaw** installed and running on your local machine.\n  See the main `clawhound\u002FSKILL.md` for OpenClaw setup.\n- **Node.js 18+** (or Python 3.10+ if using the Python adapter)\n- The `openclaw` shared storage path configured and accessible\n\n---\n\n## Installation\n\n1. Copy the `stressometer\u002F` skill folder into your OpenClaw skills directory:\n\n   ```\n   cp -r stressometer\u002F ~\u002F.openclaw\u002Fskills\u002Fstressometer\u002F\n   ```\n\n2. Register the skill in `~\u002F.openclaw\u002Fskills.json`:\n\n   ```json\n   {\n     \"stressometer\": {\n       \"entry\": \"~\u002F.openclaw\u002Fskills\u002Fstressometer\u002Fhandler.js\",\n       \"commands\": [\"analyze\"],\n       \"description\": \"Vocal stress analysis for Stressometer R1 app\"\n     }\n   }\n   ```\n\n3. Restart OpenClaw:\n\n   ```\n   openclaw restart\n   ```\n\n---\n\n## Skill handler (handler.js)\n\nCreate `~\u002F.openclaw\u002Fskills\u002Fstressometer\u002Fhandler.js`:\n\n```js\n\"use strict\";\n\n\u002F\u002F Calm-language markers lower the stress score\nconst CALM_WORDS = new Set([\n  'fine','good','great','okay','relaxed','calm','peaceful','happy','nice',\n  'easy','comfortable','enjoying','rested','settled','clear','focused',\n  'balanced','grateful','content','well','refreshed','smooth','steady',\n]);\n\n\u002F\u002F Stress-language markers raise the stress score\nconst STRESS_WORDS = new Set([\n  'anxious','stressed','worried','overwhelmed','nervous','tense','rush',\n  'deadline','urgent','panic','afraid','scared','frustrated','annoyed',\n  'tired','exhausted','behind','late','problem','difficult','struggling',\n  'pressure','stuck','can\\'t','failing','bad','terrible','awful','awful',\n  'disaster','crisis','trouble','confused','lost','desperate','angry',\n  'furious','upset','horrible','dread','fear','hate','awful','painful',\n]);\n\n\u002F\u002F High-filler-density indicates cognitive load\nconst FILLERS = new Set([\n  'um','uh','like','you know','sort of','kind of','basically','literally',\n  'actually','honestly','whatever','anyway','right','okay',\n]);\n\nmodule.exports = {\n  name: 'stressometer',\n\n  async handle(command, params, storage) {\n    if (command !== 'analyze') {\n      return { status: 'error', error: `Unknown command: ${command}` };\n    }\n\n    const { transcript = '', durationSec = 30, baseline = null } = params;\n\n    if (!transcript.trim()) {\n      return writeResult(storage, 50, 'No transcript provided — returning neutral score.');\n    }\n\n    const words      = transcript.trim().split(\u002F\\s+\u002F);\n    const wordCount  = words.length;\n    const sentences  = transcript.split(\u002F[.!?]+\u002F).filter(s => s.trim().length > 2);\n    const sentCount  = Math.max(1, sentences.length);\n\n    \u002F\u002F 1. Speaking rate (words per minute)\n    const wpm = (wordCount \u002F Math.max(durationSec, 1)) * 60;\n    \u002F\u002F Typical calm speech ~130 wpm, stressed ~160-180+\n    const wpmScore = normalize(wpm, 100, 200); \u002F\u002F 0-1\n\n    \u002F\u002F 2. Pause pattern proxy: avg words per sentence\n    \u002F\u002F More words crammed per sentence (run-on) = more stress\n    const wordsPerSent = wordCount \u002F sentCount;\n    const pauseScore   = normalize(wordsPerSent, 8, 25); \u002F\u002F 0-1\n\n    \u002F\u002F 3. Emotional language scan\n    const lower    = transcript.toLowerCase();\n    const allWords = lower.match(\u002F\\b\\w+\\b\u002Fg) || [];\n    let stressHits = 0;\n    let calmHits   = 0;\n    let fillerHits = 0;\n\n    for (const w of allWords) {\n      if (STRESS_WORDS.has(w)) stressHits++;\n      if (CALM_WORDS.has(w))   calmHits++;\n      if (FILLERS.has(w))      fillerHits++;\n    }\n\n    const emotionScore = normalize(\n      (stressHits - calmHits * 0.6) \u002F Math.max(wordCount, 1) * 100,\n      -2, 6\n    );\n\n    \u002F\u002F 4. Filler density\n    const fillerDensity = (fillerHits \u002F Math.max(wordCount, 1)) * 100;\n    const fillerScore   = normalize(fillerDensity, 0, 8);\n\n    \u002F\u002F 5. Sentence length variance\n    const sentLengths = sentences.map(s => s.trim().split(\u002F\\s+\u002F).length);\n    const sentAvg     = sentLengths.reduce((a, v) => a + v, 0) \u002F Math.max(sentLengths.length, 1);\n    const sentVar     = sentLengths.reduce((a, v) => a + Math.pow(v - sentAvg, 2), 0) \u002F Math.max(sentLengths.length, 1);\n    const sentStdDev  = Math.sqrt(sentVar);\n    \u002F\u002F High variance → choppy speech (stressed); very low variance → flat affect (also mildly stressed)\n    const varianceScore = normalize(Math.abs(sentStdDev - 4), 0, 8);\n\n    \u002F\u002F Weighted composite (0-1)\n    const raw = (\n      wpmScore      * 0.25 +\n      pauseScore    * 0.15 +\n      emotionScore  * 0.35 +\n      fillerScore   * 0.15 +\n      varianceScore * 0.10\n    );\n\n    \u002F\u002F Scale to 0-100 with soft floor\u002Fceiling\n    let index = Math.round(raw * 90 + 5);\n\n    \u002F\u002F Anchor to baseline if available (don't drift wildly from known baseline)\n    if (typeof baseline === 'number' && baseline > 0) {\n      const drift = index - baseline;\n      \u002F\u002F Allow up to ±30 points of drift per session\n      index = Math.round(baseline + Math.max(-30, Math.min(30, drift)));\n    }\n\n    index = Math.max(0, Math.min(100, index));\n\n    return writeResult(storage, index, {\n      wpm: Math.round(wpm),\n      wordsPerSentence: Math.round(wordsPerSent * 10) \u002F 10,\n      stressWordHits: stressHits,\n      calmWordHits: calmHits,\n      fillerDensityPct: Math.round(fillerDensity * 10) \u002F 10,\n      sentenceStdDev: Math.round(sentStdDev * 10) \u002F 10,\n      wordCount,\n      durationSec,\n    });\n  },\n};\n\nfunction normalize(val, min, max) {\n  return Math.max(0, Math.min(1, (val - min) \u002F (max - min)));\n}\n\nasync function writeResult(storage, stressIndex, meta) {\n  const result = {\n    status: 'done',\n    ts: Date.now(),\n    data: {\n      stressIndex,\n      ...(typeof meta === 'object' ? meta : { note: meta }),\n    },\n  };\n  await storage.set('openclaw:resp', JSON.stringify(result));\n  return result;\n}\n```\n\n---\n\n## Payload schema\n\n### R1 → OpenClaw (command: `analyze`)\n\n```json\n{\n  \"skill\": \"stressometer\",\n  \"command\": \"analyze\",\n  \"params\": {\n    \"transcript\": \"The full STT transcript text from the session\",\n    \"durationSec\": 42,\n    \"baseline\": 48,\n    \"ts\": 1718300000000\n  }\n}\n```\n\n### OpenClaw → R1 (response)\n\n```json\n{\n  \"status\": \"done\",\n  \"ts\": 1718300001234,\n  \"data\": {\n    \"stressIndex\": 61,\n    \"wpm\": 157,\n    \"wordsPerSentence\": 14.2,\n    \"stressWordHits\": 3,\n    \"calmWordHits\": 1,\n    \"fillerDensityPct\": 3.1,\n    \"sentenceStdDev\": 5.8,\n    \"wordCount\": 110,\n    \"durationSec\": 42\n  }\n}\n```\n\n`stressIndex` is the only field the R1 app requires. All other fields\nare logged locally for debugging and future calibration.\n\n---\n\n## Fallback behavior\n\nIf OpenClaw is offline or the response times out (30-second timeout),\nStressometer falls back to an on-device estimate: a small random\nperturbation around the stored baseline. The reading is still saved\nand included in trend data. The UI shows no error to the user — it\nsilently degrades.\n\n---\n\n## Data retention\n\n- **On the R1:** Stress index numbers and timestamps only (up to 200\n  readings, ~3 months of daily use). No transcripts.\n- **On your machine:** Nothing is persisted by the handler. Transcripts\n  are analyzed in memory and discarded. If you add logging, store only\n  the computed index, never the transcript text.\n\n---\n\n## Deleting your data\n\nFrom the Stressometer app: hold PTT on the main screen → select\n\"Delete Data\" → confirm. This wipes all readings and the baseline from\nR1 storage. OpenClaw retains nothing, so no action needed on the\nlocal machine.\n",{"name":5,"author":24,"version":25,"description":26},"rabbit-r1-skillz","1.0.0","Passive vocal stress analyzer for the Stressometer R1 Creation. Receives voice transcripts from the R1, extracts acoustic stress proxies from the transcript text (pitch variance keywords, speaking rate estimation, pause patterns, emotional language markers), and returns a 0–100 stress index. All processing runs locally — nothing leaves your machine.\n","main","734489c70f6293d3b800cd956559034acaa9f563","https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren","https:\u002F\u002Fgithub.com\u002Fajohnsonnow","structuredforgrowth.com","2026-09-04 21:06:25",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add ajohnsonnow\u002Fr1-warren --skill stressometer",{"tool":39,"command":40},"bunx","bunx skills add ajohnsonnow\u002Fr1-warren --skill stressometer",{"tool":42,"command":43},"pnpm","pnpm dlx skills add ajohnsonnow\u002Fr1-warren --skill stressometer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fstressometer\u002FSKILL.md",true,[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"card.jpg","ASSET","资产文件",25735,"https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fstressometer\u002Fcard.jpg",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"icon.png",9008,"https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fstressometer\u002Ficon.png",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"index.html","REFERENCE","参考文档",55731,"https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fstressometer\u002Findex.html",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M75THZJQ1XYR8QDWB9RXC9QV","whisper-quiz","WhisperQuiz — voice-answered trivia game for Rabbit R1. Generates questions via the R1's built-in LLM, captures spoken answers via STT, and evaluates correctness with flexible LLM-based matching.","https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fwhisper-quiz\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M75THW5BJRSQQM3QP6M568FT","walk-cast","Walking podcast production skill. Receives raw audio metadata and transcript from the R1, removes long pauses, applies noise reduction and normalization, generates AI chapter titles and episode metadata via LLM, and uploads the final episode to your configured podcast RSS host (Spotify for Podcasters \u002F Anchor, Podbean, Buzzsprout, RSS.com, or any FTP-accessible feed).","https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fwalk-cast\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M75THTANZTS2AMDDBP615RTA","voice-novel","Local machine skill for VoiceNovel — handles story export to disk.","https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fvoice-novel\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M75THQ175ZRJ3E0GPFW7QKM8","voice-guide","Environment description and navigation assistant for blind and low-vision users. Analyzes camera frames via a vision LLM, reads visible text, identifies scene categories (people\u002Fvehicles\u002Ffood\u002Fhazards\u002Fexits), performs 360° scans, retrieves GPS position, and sends emergency SMS alerts — all via audio feedback with zero screen dependency.","https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fvoice-guide\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M75THKAJR69WV7QQYJ26X95C","voice-draft","Voice-driven document drafting for the Rabbit R1. Dictate stream-of-consciousness speech; the R1 formats it into Email, Blog Post, Report, Proposal, Meeting Notes, Creative Writing, Code Comments, Cover Letter, or Tweet Thread — then saves the result to a configured folder on your local machine via OpenClaw.","https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fvoice-draft\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M75THGKGY2JY59MM9PREXCXX","voice-commit","Hands-free git and CI workflow voice controller for the Rabbit R1. Speak git\u002FCI commands and hear results — commit, push, status, PR management, test runs, and deploy, all voice-driven via OpenClaw.","https:\u002F\u002Fgithub.com\u002Fajohnsonnow\u002Fr1-warren\u002Fblob\u002Fmain\u002Fvoice-commit\u002FSKILL.md",[],[]]