[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75NEF306X8SW8C8D094KVJ5":3,"skill-same:01M75NEF306X8SW8C8D094KVJ5":53},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M75NEF306X8SW8C8D094KVJ5","Briefing Room",null,"Daily news briefing generator — produces a conversational radio-host-style audio briefing + DOCX document covering weather, X\u002FTwitter trends, web trends, world news, politics, tech, local news, sports, markets, and crypto. macOS only (uses Apple TTS and afplay). Use when user asks for a news briefing, morning briefing, daily update, or similar.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmatusvojtek\u002Fbriefing-room\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: Briefing Room\ndescription: \"Daily news briefing generator — produces a conversational radio-host-style audio briefing + DOCX document covering weather, X\u002FTwitter trends, web trends, world news, politics, tech, local news, sports, markets, and crypto. macOS only (uses Apple TTS and afplay). Use when user asks for a news briefing, morning briefing, daily update, or similar.\"\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"📻\",\n        \"requires\": { \"bins\": [\"curl\"] }\n      }\n  }\n---\n\n# Briefing Room 📻\n\n**Your personal daily news briefing — audio + document.**\n\nOn demand, research and compose a comprehensive ~10 minute news briefing in a conversational radio-host style. Output: audio file (MP3) + formatted document (DOCX).\n\n### 💸 100% Free\n\n- **No subscriptions, API keys, or paid services**\n- Uses free public APIs (Open-Meteo weather, Coinbase prices, Google Trends RSS), web search, and local TTS\n- TTS is fully local, no keys needed: MLX-Audio Kokoro (English) or Apple `say` (any language)\n- Reads\u002Fwrites: `~\u002F.briefing-room\u002Fconfig.json` (settings) and `~\u002FDocuments\u002FBriefing Room\u002F` (output)\n\n## First-Run Setup\n\nOn first use, check if `~\u002F.briefing-room\u002Fconfig.json` exists. If not, run:\n\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py init\n```\n\nThis creates default config. The user can customize:\n- **Location** — city, latitude, longitude, timezone (for weather)\n- **Language** — `en`, `sk`, `de`, etc.\n- **Voices** — per-language TTS engine and voice selection\n- **Sections** — which news sections to include\n- **Output folder** — where briefings are saved\n\nShow setup status:\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py status\n```\n\n## Quick Start\n\nWhen user asks for a briefing (e.g. \"give me a briefing\", \"morning update\", \"what's happening today\"):\n\n1. Check config exists (run setup if not)\n2. Play notification sound: `afplay \u002FSystem\u002FLibrary\u002FSounds\u002FBlow.aiff &`\n3. Spawn a sub-agent with the full pipeline task **immediately**\n4. Reply: \"📻 Briefing Room is firing up — gathering today's news. I'll ping you when it's ready!\"\n5. **DO NOT BLOCK** — spawn and move on instantly\n\n**Language override:** If user says \"po slovensky\", \"v slovenčine\", \"auf deutsch\", \"en français\", etc. → pass that to the sub-agent. Otherwise use the configured default language. Any language macOS supports will work — the agent writes the script in that language and TTS auto-detects a matching voice.\n\n### Spawn Command\n\n```\nsessions_spawn(\n  task=\"\u003Cfull pipeline instructions — see below>\",\n  label=\"briefing-room\",\n  runTimeoutSeconds=600,\n  cleanup=\"delete\"\n)\n```\n\nThe task message should include ALL the pipeline steps below so the sub-agent is fully self-contained. **Replace all `SKILL_DIR` references with the actual absolute path to this skill's directory.**\n\n**Host name:** Read `host.name` from config. If empty, use your own agent name (from your identity). Pass it to the sub-agent as the radio host name (e.g. \"Good morning, I'm Jackie, and this is your Briefing Room...\").\n\n## Configuration\n\nConfig file: `~\u002F.briefing-room\u002Fconfig.json`\n\nRead values:\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.city\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py get language\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py get voices.en.mlx_voice\n```\n\nSet values:\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py set location.city \"Vienna\"\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py set location.latitude 48.21\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py set location.longitude 16.37\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py set language \"de\"\n```\n\n### Key Config Options\n\n| Key | Default | Description |\n|-----|---------|-------------|\n| `location.city` | Bratislava | City name for weather + local news |\n| `location.latitude` | 48.15 | Weather API latitude |\n| `location.longitude` | 17.11 | Weather API longitude |\n| `location.timezone` | Europe\u002FBratislava | Timezone for weather API |\n| `language` | en | Default briefing language |\n| `output.folder` | ~\u002FDocuments\u002FBriefing Room | Output directory |\n| `audio.enabled` | true | Generate audio |\n| `audio.format` | mp3 | Audio format (mp3, wav, aiff) |\n| `audio.tts_engine` | auto | TTS engine (auto, mlx, kokoro, builtin) |\n| `sections` | all 11 (see below) | Which sections to include |\n| `host.name` | (empty = agent name) | Radio host name for the briefing |\n| `trends.regions` | united-states,united-kingdom, | X\u002FTwitter trend regions (comma-separated, trailing comma = worldwide) |\n| `webtrends.regions` | US,GB, | Google Trends regions (ISO codes, trailing comma = worldwide) |\n\n### Voice Configuration Per Language\n\nEach language can have its own TTS engine and voice:\n\n```json\n{\n  \"voices\": {\n    \"en\": {\n      \"engine\": \"mlx\",\n      \"mlx_voice\": \"af_heart\",\n      \"mlx_voice_blend\": {\"af_heart\": 0.6, \"af_sky\": 0.4},\n      \"builtin_voice\": \"Samantha\",\n      \"speed\": 1.05\n    },\n    \"sk\": {\n      \"engine\": \"builtin\",\n      \"builtin_voice\": \"Laura (Enhanced)\",\n      \"builtin_rate\": 220\n    },\n    \"de\": {\n      \"engine\": \"builtin\",\n      \"builtin_voice\": \"Petra (Premium)\",\n      \"builtin_rate\": 200\n    }\n  }\n}\n```\n\n**Engine priority (when `auto`):**\n- English: mlx → kokoro → builtin\n- Other languages: builtin (Apple TTS has good multilingual voices)\n\nUsers can add any language by adding a voices entry + a matching `builtin_voice` from `say -v '?'`.\n\n## Output Structure\n\n```\n~\u002FDocuments\u002FBriefing Room\u002FYYYY-MM-DD\u002F\n├── briefing-YYYY-MM-DD-HHMM.docx    # Formatted document\n└── briefing-YYYY-MM-DD-HHMM.mp3     # Audio briefing (~10 min)\n```\n\n**Do NOT save the .md working file in the output folder.** Use `\u002Ftmp\u002F` for working files, delete after.\n\n## Full Pipeline\n\n### Step 0: Setup\n\n```bash\n# Read config\nCITY=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.city)\nLAT=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.latitude)\nLON=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.longitude)\nTZ=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.timezone)\nLANG=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get language)\nOUTPUT_FOLDER=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get output.folder)\n\nDATE=$(date +%Y-%m-%d)\nTIMESTAMP=$(date +%Y-%m-%d-%H%M)\nOUTPUT_DIR=\"$OUTPUT_FOLDER\u002F$DATE\"\nmkdir -p \"$OUTPUT_DIR\"\n```\n\n### Step 1: Gather Data — Weather\n\nUse the configured location coordinates:\n\n```bash\n# Current weather\nTZ_ENC=\"${TZ\u002F\\\u002F\u002F%2F}\"\nBASE=\"https:\u002F\u002Fapi.open-meteo.com\u002Fv1\u002Fforecast\"\nCURRENT=\"temperature_2m,relative_humidity_2m\"\nCURRENT=\"$CURRENT,apparent_temperature,precipitation\"\nCURRENT=\"$CURRENT,weather_code,wind_speed_10m\"\ncurl -s \"$BASE?latitude=$LAT&longitude=$LON\\\n&current=$CURRENT&timezone=$TZ_ENC\"\n\n# 7-day forecast\nDAILY=\"temperature_2m_max,temperature_2m_min\"\nDAILY=\"$DAILY,precipitation_sum,weather_code\"\ncurl -s \"$BASE?latitude=$LAT&longitude=$LON\\\n&daily=$DAILY&timezone=$TZ_ENC\"\n```\n\nOr use the helper: `bash SKILL_DIR\u002Fscripts\u002Fbriefing.sh weather`\n\nMap `weather_code` to descriptions:\n- 0: Clear sky ☀️\n- 1-3: Partly cloudy ⛅\n- 45-48: Fog 🌫️\n- 51-55: Drizzle 🌦️\n- 61-65: Rain 🌧️\n- 71-75: Snow ❄️\n- 80-82: Rain showers 🌦️\n- 95-99: Thunderstorm ⛈️\n\n### Step 2: Gather Data — News (Web Search)\n\nUse `web_search` tool for each section. Add current date to queries for freshness. Use the configured `$CITY` for local news.\n\n**X\u002FTwitter Trends (from getdaytrends.com — real-time, no API key):**\n```bash\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh trends\n```\nThis fetches top 25 trends from US, UK, and Worldwide. Use the output to:\n- Identify the most interesting\u002Fnewsworthy trends (skip generic ones like \"Good Tuesday\", \"Taco Tuesday\")\n- Filter out non-Latin script trends unless they're globally significant\n- Pick ~5-10 trends that overlap across regions or seem newsworthy\n- Use `web_search` to get context on the top trends you selected\n\n**Web Trends (from Google Trends RSS — what people are searching):**\n```bash\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh webtrends\n```\nThis fetches trending Google searches from US, UK, and Worldwide with:\n- Search term and approximate traffic volume\n- Top news headline explaining why it's trending\nUse this data for the Web Trends section. The headlines already provide context — no extra searching needed for most items.\n\n**World News:**\n```\nweb_search(\"top world news today {date}\", count=8)\nweb_search(\"breaking news today\", count=5)\n```\n\n**Politics:**\n```\nweb_search(\"US politics news today {date}\", count=5)\nweb_search(\"EU politics news today {date}\", count=5)\nweb_search(\"geopolitics news today\", count=5)\n```\n\n**⚠️ Source diversity:** All sources have bias. For balanced reporting:\n- Search the same story with different framing\n- Present what happened factually, note what each side says\n- Don't adopt any outlet's framing as truth\n- Stick to verifiable facts: numbers, dates, quotes, actions\n\n**Tech & AI:**\n```\nweb_search(\"tech news today {date}\", count=5)\nweb_search(\"AI artificial intelligence news today {date}\", count=5)\n```\n\n**Local news** (based on configured city):\n```\nweb_search(\"$CITY news today {date}\", count=5)\n```\nAlso search in the configured language if not English:\n```\nweb_search(\"$CITY [news today] in $LANG {date}\", count=5)\n```\nExamples:\n- Slovak: `\"Bratislava správy dnes\"`\n- German: `\"Wien Nachrichten heute\"`\n- Czech: `\"Praha zprávy dnes\"`\n\n**Sports:**\n```\nweb_search(\"sports news today {date}\", count=5)\nweb_search(\"football soccer results today\", count=5)\n```\n\n### Step 3: Gather Data — Markets & Crypto (APIs + Search)\n\n```bash\n# Or use helper:\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh crypto\n```\n\n```bash\ncurl -s \"https:\u002F\u002Fapi.coinbase.com\u002Fv2\u002Fprices\u002FBTC-USD\u002Fspot\"\ncurl -s \"https:\u002F\u002Fapi.coinbase.com\u002Fv2\u002Fprices\u002FETH-USD\u002Fspot\"\ncurl -s \"https:\u002F\u002Fapi.coinbase.com\u002Fv2\u002Fprices\u002FSOL-USD\u002Fspot\"\ncurl -s \"https:\u002F\u002Fapi.coinbase.com\u002Fv2\u002Fprices\u002FXRP-USD\u002Fspot\"\n```\n\n```\nweb_search(\"S&P 500 Dow Jones Nasdaq today {date}\", count=5)\nweb_search(\"stock market today movers {date}\", count=5)\nweb_search(\"gold price silver price today\", count=3)\nweb_search(\"crypto market today {date}\", count=5)\n```\n\n### Step 4: Compose the Briefing Script\n\nWrite as a **conversational radio-host monologue**.\n\n**Style guidelines:**\n- Write like a smart, engaging radio host — NOT a list of headlines\n- **Use the host name** — introduce yourself: \"Good morning, I'm [host name], and this is your Briefing Room for [date]...\"\n- Sprinkle the name naturally throughout (sign-off, transitions) — don't overdo it\n- Do NOT start markdown with a `# Title` header — pandoc adds title from metadata\n- Connect stories with transitions\n- Add context: \"here's why this matters\"\n- **Stay neutral and balanced** — report facts, present sides, let listener decide\n- Target ~2,500-3,500 words for ~10 minutes\n- No emojis in the script (break TTS)\n- Write out numbers\u002Fabbreviations for TTS:\n  - \"$96,500\" → \"ninety-six thousand five hundred dollars\"\n  - \"S&P 500\" → \"S and P 500\"\n  - \"BTC\" → \"Bitcoin\"\n  - \"°C\" → \"degrees celsius\"\n\n**If language is not English**, write the entire script in that language.\n\n**Section order:**\n1. **Opening** — Date, quick teaser of top stories\n2. **Weather** — Current + week outlook for configured city\n3. **Trending on X** — What's hot on X\u002FTwitter\n4. **Web Trends** — What people are searching (Google Trends)\n5. **World** — Top 3-5 global stories\n6. **Politics** — US, EU, geopolitics\n7. **Tech & AI** — Launches, breakthroughs\n8. **Local** — News for configured city\u002Fcountry\n9. **Sports** — Headlines, results\n10. **Markets** — S&P 500, Dow, Nasdaq, movers\n11. **Crypto & Commodities** — BTC, ETH, alts, gold, silver\n12. **This Day in History** — 1-2 interesting events that happened on this date\n13. **Closing** — Wrap-up, sign-off\n\n**This Day in History:** No research needed — use your own knowledge. Pick 1-2 interesting, surprising, or fun events that happened on today's date. Mix it up: science, culture, politics, weird stuff. Keep it conversational: \"And before I let you go — did you know that on this day in 1996...\"\n\nOnly include sections from the configured `sections` list. Skip sections the user has removed.\n\nSave as `\u002Ftmp\u002Fbriefing_draft_$TIMESTAMP.md` (working file).\n\n**For the markdown**, include:\n- Section headers with emojis: `## 🌤️ Weather`, `## 🌍 World`, `## 📜 This Day in History`, etc.\n- Source links after key facts\n- Key data in bold\n\n### Step 5: Generate DOCX\n\n```bash\npandoc \"\u002Ftmp\u002Fbriefing_draft_$TIMESTAMP.md\" \\\n  -o \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.docx\" \\\n  --metadata title=\"Briefing Room - $DATE\"\n```\n\nIf pandoc is not available, skip DOCX and note it.\n\n### Step 6: Generate Audio\n\nRead the config to determine TTS engine and voice for the current language.\n\n**MLX-Audio (English, or if configured for language):**\n\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py get voices.$LANG.engine\n# → if \"mlx\":\n```\n\n```python\nimport os, re, glob, json, subprocess\nfrom datetime import datetime\n\ntimestamp = datetime.now().strftime(\"%Y-%m-%d-%H%M\")  # must match TIMESTAMP from Step 0\n\n# Read config\nconfig_path = os.path.expanduser(\"~\u002F.briefing-room\u002Fconfig.json\")\nwith open(config_path) as f:\n    config = json.load(f)\n\nlang = config.get(\"language\", \"en\")\nvoices = config.get(\"voices\", {})\nvoice_cfg = voices.get(lang, voices.get(\"en\", {}))\n\n# Read and strip markdown from draft\nwith open(f\"\u002Ftmp\u002Fbriefing_draft_{timestamp}.md\", \"r\") as f:\n    text = f.read()\ntext = re.sub(r'#+ ', '', text)\ntext = re.sub(r'\\*\\*([^*]+)\\*\\*', r'\\1', text)\ntext = re.sub(r'\\*([^*]+)\\*', r'\\1', text)\ntext = re.sub(r'\\[([^\\]]+)\\]\\([^)]+\\)', r'\\1', text)\ntext = re.sub(r'---+', '', text)\ntext = re.sub(r'\\n{3,}', '\\n\\n', text)\n\n# Resolve voice\nblend = voice_cfg.get(\"mlx_voice_blend\")\nvoice = voice_cfg.get(\"mlx_voice\", \"af_heart\")\nif blend:\n    model = config.get(\"mlx_audio\", {}).get(\"model\", \"mlx-community\u002FKokoro-82M-bf16\")\n    model_slug = model.replace(\"\u002F\", \"--\")\n    cache_dir = os.path.expanduser(f\"~\u002F.cache\u002Fhuggingface\u002Fhub\u002Fmodels--{model_slug}\")\n    parts = []\n    for v, w in sorted(blend.items(), key=lambda x: -x[1]):\n        parts.append(f\"{v}_{int(w * 100)}\")\n    blend_name = \"_\".join(parts) + \".safetensors\"\n    matches = glob.glob(os.path.join(cache_dir, \"snapshots\u002F*\u002Fvoices\", blend_name))\n    if matches:\n        voice = matches[0]\n\nspeed = voice_cfg.get(\"speed\", 1.05)\nlang_code = config.get(\"mlx_audio\", {}).get(\"lang_code\", \"a\")\n\n# Find MLX-Audio\nmlx_path = config.get(\"mlx_audio\", {}).get(\"path\", \"\")\nif not mlx_path:\n    for p in [\"~\u002F.openclaw\u002Ftools\u002Fmlx-audio\", \"~\u002F.local\u002Fshare\u002Fmlx-audio\"]:\n        ep = os.path.expanduser(p)\n        if os.path.exists(os.path.join(ep, \".venv\u002Fbin\u002Fpython3\")):\n            mlx_path = ep\n            break\n\n# Generate via subprocess (uses MLX-Audio's venv)\npython_bin = os.path.join(mlx_path, \".venv\u002Fbin\u002Fpython3\")\n# ... generate_audio call with resolved voice, speed, lang_code\n```\n\n**Built-in Apple TTS (any language):**\n\nIf there's no voice configured for the language, auto-detect one:\n```bash\n# Try to get configured voice, fall back to auto-detect\nVOICE=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get voices.$LANG.builtin_voice)\nif [ \"$VOICE\" = \"None\" ] || [ -z \"$VOICE\" ]; then\n    # Auto-detect: match locale (e.g. sk_SK, de_DE, fr_FR)\n    # Prefer Enhanced\u002FPremium voices, fall back to any\n    VOICE=$(say -v '?' | grep \"${LANG}_\" \\\n      | grep -i \"Enhanced\\|Premium\" | head -1 \\\n      | sed 's\u002F *[a-z][a-z]_[A-Z][A-Z].*\u002F\u002F' | xargs)\n    [ -z \"$VOICE\" ] && VOICE=$(say -v '?' \\\n      | grep \"${LANG}_\" | head -1 \\\n      | sed 's\u002F *[a-z][a-z]_[A-Z][A-Z].*\u002F\u002F' | xargs)\nfi\nRATE=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get voices.$LANG.builtin_rate)\n# Strip markdown for TTS\nDRAFT=\"\u002Ftmp\u002Fbriefing_draft_$TIMESTAMP.md\"\nTTS_TXT=\"\u002Ftmp\u002Fbriefing_tts_$TIMESTAMP.txt\"\nsed -E 's\u002F#+\u002F\u002Fg; s\u002F\\*+\u002F\u002Fg; s\u002F\\[([^]]*)\\]\\([^)]*\\)\u002F\\1\u002Fg' \\\n  \"$DRAFT\" > \"$TTS_TXT\"\nsay -v \"$VOICE\" ${RATE:+-r $RATE} \\\n  -o \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.aiff\" \\\n  -f \"$TTS_TXT\"\nrm -f \"\u002Ftmp\u002Fbriefing_tts_$TIMESTAMP.txt\"\n```\n\n**Kokoro PyTorch (fallback):**\n\nSimilar to MLX but uses PyTorch backend. See TubeScribe skill for Kokoro usage patterns.\n\n### Step 6b: Convert to MP3\n\n```bash\n# Find the raw audio file (MLX outputs .wav, Apple TTS outputs .aiff)\nRAW=\"\"\nfor ext in wav aiff; do\n    if [ -f \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.$ext\" ]; then\n        RAW=\"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.$ext\"\n        break\n    fi\ndone\n\nif [ -n \"$RAW\" ]; then\n    ffmpeg -y \\\n      -i \"$RAW\" \\\n      -codec:a libmp3lame -qscale:a 2 \\\n      \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.mp3\"\n    if [ -s \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.mp3\" ]; then\n        rm \"$RAW\"\n    fi\nfi\n```\n\n### Step 6c: Cleanup\n\n```bash\nrm -f \"\u002Ftmp\u002Fbriefing_draft_$TIMESTAMP.md\"\n```\n\n### Step 7: Open Output Folder\n\n```bash\nopen \"$OUTPUT_DIR\"\n```\n\n**Do NOT auto-play.** Briefings are long and need playback controls.\n\n### Step 8: Report\n\nReport back with:\n- Date and language of briefing\n- Sections covered\n- Top 3-4 headlines\n- Audio duration\n- File locations\n\n## Helper Script\n\n```bash\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh setup     # Check dependencies + config\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh weather    # Fetch weather (uses config location)\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh trends     # Fetch X\u002FTwitter trends (US + UK + Worldwide)\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh webtrends  # Fetch Google Trends (US + UK + Worldwide)\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh crypto     # Fetch crypto prices\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh open       # Open today's folder\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh list       # List all briefings\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh clean      # Remove briefings >30 days old\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh config     # Show raw config JSON\n```\n\n## Tips\n\n- Full pipeline takes 3-5 minutes (research + composition + TTS)\n- For shorter briefing, say \"quick briefing\" — cover top 3 sections only\n- If markets are closed (weekend\u002Fholiday), note it and skip detailed data\n- The agent IS the intelligence — read search results, compose the script, decide what matters\n- Users can add new languages by adding a `voices` entry + installing the voice via `say -v '?'`\n\n## Dependencies\n\n**Required:**\n- `curl` — API calls (built into macOS)\n- `web_search` tool — News research (OpenClaw built-in)\n\n**Recommended:**\n- MLX-Audio Kokoro — fast English TTS\n- `pandoc` — DOCX generation: `brew install pandoc`\n- `ffmpeg` — MP3 conversion: `brew install ffmpeg`\n\n**Built-in (macOS):**\n- Apple `say` — multilingual TTS (always available as fallback)\n\n## Error Handling\n\n| Issue | Action |\n|-------|--------|\n| No config file | Run `python3 SKILL_DIR\u002Fscripts\u002Fconfig.py init` |\n| API timeout | Retry once, skip that source, note it |\n| Web search empty | Try alternative query, note gaps |\n| TTS fails | Fall back to Apple `say` (always available) |\n| Pandoc not found | Skip DOCX, deliver MP3 only |\n| No internet | Cannot generate — inform user |\n","# Briefing Room 📻\n\n**Your personal daily news briefing — audio + document.**\n\nOn demand, research and compose a comprehensive ~10 minute news briefing in a conversational radio-host style. Output: audio file (MP3) + formatted document (DOCX).\n\n### 💸 100% Free\n\n- **No subscriptions, API keys, or paid services**\n- Uses free public APIs (Open-Meteo weather, Coinbase prices, Google Trends RSS), web search, and local TTS\n- TTS is fully local, no keys needed: MLX-Audio Kokoro (English) or Apple `say` (any language)\n- Reads\u002Fwrites: `~\u002F.briefing-room\u002Fconfig.json` (settings) and `~\u002FDocuments\u002FBriefing Room\u002F` (output)\n\n## First-Run Setup\n\nOn first use, check if `~\u002F.briefing-room\u002Fconfig.json` exists. If not, run:\n\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py init\n```\n\nThis creates default config. The user can customize:\n- **Location** — city, latitude, longitude, timezone (for weather)\n- **Language** — `en`, `sk`, `de`, etc.\n- **Voices** — per-language TTS engine and voice selection\n- **Sections** — which news sections to include\n- **Output folder** — where briefings are saved\n\nShow setup status:\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py status\n```\n\n## Quick Start\n\nWhen user asks for a briefing (e.g. \"give me a briefing\", \"morning update\", \"what's happening today\"):\n\n1. Check config exists (run setup if not)\n2. Play notification sound: `afplay \u002FSystem\u002FLibrary\u002FSounds\u002FBlow.aiff &`\n3. Spawn a sub-agent with the full pipeline task **immediately**\n4. Reply: \"📻 Briefing Room is firing up — gathering today's news. I'll ping you when it's ready!\"\n5. **DO NOT BLOCK** — spawn and move on instantly\n\n**Language override:** If user says \"po slovensky\", \"v slovenčine\", \"auf deutsch\", \"en français\", etc. → pass that to the sub-agent. Otherwise use the configured default language. Any language macOS supports will work — the agent writes the script in that language and TTS auto-detects a matching voice.\n\n### Spawn Command\n\n```\nsessions_spawn(\n  task=\"\u003Cfull pipeline instructions — see below>\",\n  label=\"briefing-room\",\n  runTimeoutSeconds=600,\n  cleanup=\"delete\"\n)\n```\n\nThe task message should include ALL the pipeline steps below so the sub-agent is fully self-contained. **Replace all `SKILL_DIR` references with the actual absolute path to this skill's directory.**\n\n**Host name:** Read `host.name` from config. If empty, use your own agent name (from your identity). Pass it to the sub-agent as the radio host name (e.g. \"Good morning, I'm Jackie, and this is your Briefing Room...\").\n\n## Configuration\n\nConfig file: `~\u002F.briefing-room\u002Fconfig.json`\n\nRead values:\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.city\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py get language\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py get voices.en.mlx_voice\n```\n\nSet values:\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py set location.city \"Vienna\"\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py set location.latitude 48.21\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py set location.longitude 16.37\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py set language \"de\"\n```\n\n### Key Config Options\n\n| Key | Default | Description |\n|-----|---------|-------------|\n| `location.city` | Bratislava | City name for weather + local news |\n| `location.latitude` | 48.15 | Weather API latitude |\n| `location.longitude` | 17.11 | Weather API longitude |\n| `location.timezone` | Europe\u002FBratislava | Timezone for weather API |\n| `language` | en | Default briefing language |\n| `output.folder` | ~\u002FDocuments\u002FBriefing Room | Output directory |\n| `audio.enabled` | true | Generate audio |\n| `audio.format` | mp3 | Audio format (mp3, wav, aiff) |\n| `audio.tts_engine` | auto | TTS engine (auto, mlx, kokoro, builtin) |\n| `sections` | all 11 (see below) | Which sections to include |\n| `host.name` | (empty = agent name) | Radio host name for the briefing |\n| `trends.regions` | united-states,united-kingdom, | X\u002FTwitter trend regions (comma-separated, trailing comma = worldwide) |\n| `webtrends.regions` | US,GB, | Google Trends regions (ISO codes, trailing comma = worldwide) |\n\n### Voice Configuration Per Language\n\nEach language can have its own TTS engine and voice:\n\n```json\n{\n  \"voices\": {\n    \"en\": {\n      \"engine\": \"mlx\",\n      \"mlx_voice\": \"af_heart\",\n      \"mlx_voice_blend\": {\"af_heart\": 0.6, \"af_sky\": 0.4},\n      \"builtin_voice\": \"Samantha\",\n      \"speed\": 1.05\n    },\n    \"sk\": {\n      \"engine\": \"builtin\",\n      \"builtin_voice\": \"Laura (Enhanced)\",\n      \"builtin_rate\": 220\n    },\n    \"de\": {\n      \"engine\": \"builtin\",\n      \"builtin_voice\": \"Petra (Premium)\",\n      \"builtin_rate\": 200\n    }\n  }\n}\n```\n\n**Engine priority (when `auto`):**\n- English: mlx → kokoro → builtin\n- Other languages: builtin (Apple TTS has good multilingual voices)\n\nUsers can add any language by adding a voices entry + a matching `builtin_voice` from `say -v '?'`.\n\n## Output Structure\n\n```\n~\u002FDocuments\u002FBriefing Room\u002FYYYY-MM-DD\u002F\n├── briefing-YYYY-MM-DD-HHMM.docx    # Formatted document\n└── briefing-YYYY-MM-DD-HHMM.mp3     # Audio briefing (~10 min)\n```\n\n**Do NOT save the .md working file in the output folder.** Use `\u002Ftmp\u002F` for working files, delete after.\n\n## Full Pipeline\n\n### Step 0: Setup\n\n```bash\n# Read config\nCITY=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.city)\nLAT=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.latitude)\nLON=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.longitude)\nTZ=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get location.timezone)\nLANG=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get language)\nOUTPUT_FOLDER=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get output.folder)\n\nDATE=$(date +%Y-%m-%d)\nTIMESTAMP=$(date +%Y-%m-%d-%H%M)\nOUTPUT_DIR=\"$OUTPUT_FOLDER\u002F$DATE\"\nmkdir -p \"$OUTPUT_DIR\"\n```\n\n### Step 1: Gather Data — Weather\n\nUse the configured location coordinates:\n\n```bash\n# Current weather\nTZ_ENC=\"${TZ\u002F\\\u002F\u002F%2F}\"\nBASE=\"https:\u002F\u002Fapi.open-meteo.com\u002Fv1\u002Fforecast\"\nCURRENT=\"temperature_2m,relative_humidity_2m\"\nCURRENT=\"$CURRENT,apparent_temperature,precipitation\"\nCURRENT=\"$CURRENT,weather_code,wind_speed_10m\"\ncurl -s \"$BASE?latitude=$LAT&longitude=$LON\\\n&current=$CURRENT&timezone=$TZ_ENC\"\n\n# 7-day forecast\nDAILY=\"temperature_2m_max,temperature_2m_min\"\nDAILY=\"$DAILY,precipitation_sum,weather_code\"\ncurl -s \"$BASE?latitude=$LAT&longitude=$LON\\\n&daily=$DAILY&timezone=$TZ_ENC\"\n```\n\nOr use the helper: `bash SKILL_DIR\u002Fscripts\u002Fbriefing.sh weather`\n\nMap `weather_code` to descriptions:\n- 0: Clear sky ☀️\n- 1-3: Partly cloudy ⛅\n- 45-48: Fog 🌫️\n- 51-55: Drizzle 🌦️\n- 61-65: Rain 🌧️\n- 71-75: Snow ❄️\n- 80-82: Rain showers 🌦️\n- 95-99: Thunderstorm ⛈️\n\n### Step 2: Gather Data — News (Web Search)\n\nUse `web_search` tool for each section. Add current date to queries for freshness. Use the configured `$CITY` for local news.\n\n**X\u002FTwitter Trends (from getdaytrends.com — real-time, no API key):**\n```bash\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh trends\n```\nThis fetches top 25 trends from US, UK, and Worldwide. Use the output to:\n- Identify the most interesting\u002Fnewsworthy trends (skip generic ones like \"Good Tuesday\", \"Taco Tuesday\")\n- Filter out non-Latin script trends unless they're globally significant\n- Pick ~5-10 trends that overlap across regions or seem newsworthy\n- Use `web_search` to get context on the top trends you selected\n\n**Web Trends (from Google Trends RSS — what people are searching):**\n```bash\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh webtrends\n```\nThis fetches trending Google searches from US, UK, and Worldwide with:\n- Search term and approximate traffic volume\n- Top news headline explaining why it's trending\nUse this data for the Web Trends section. The headlines already provide context — no extra searching needed for most items.\n\n**World News:**\n```\nweb_search(\"top world news today {date}\", count=8)\nweb_search(\"breaking news today\", count=5)\n```\n\n**Politics:**\n```\nweb_search(\"US politics news today {date}\", count=5)\nweb_search(\"EU politics news today {date}\", count=5)\nweb_search(\"geopolitics news today\", count=5)\n```\n\n**⚠️ Source diversity:** All sources have bias. For balanced reporting:\n- Search the same story with different framing\n- Present what happened factually, note what each side says\n- Don't adopt any outlet's framing as truth\n- Stick to verifiable facts: numbers, dates, quotes, actions\n\n**Tech & AI:**\n```\nweb_search(\"tech news today {date}\", count=5)\nweb_search(\"AI artificial intelligence news today {date}\", count=5)\n```\n\n**Local news** (based on configured city):\n```\nweb_search(\"$CITY news today {date}\", count=5)\n```\nAlso search in the configured language if not English:\n```\nweb_search(\"$CITY [news today] in $LANG {date}\", count=5)\n```\nExamples:\n- Slovak: `\"Bratislava správy dnes\"`\n- German: `\"Wien Nachrichten heute\"`\n- Czech: `\"Praha zprávy dnes\"`\n\n**Sports:**\n```\nweb_search(\"sports news today {date}\", count=5)\nweb_search(\"football soccer results today\", count=5)\n```\n\n### Step 3: Gather Data — Markets & Crypto (APIs + Search)\n\n```bash\n# Or use helper:\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh crypto\n```\n\n```bash\ncurl -s \"https:\u002F\u002Fapi.coinbase.com\u002Fv2\u002Fprices\u002FBTC-USD\u002Fspot\"\ncurl -s \"https:\u002F\u002Fapi.coinbase.com\u002Fv2\u002Fprices\u002FETH-USD\u002Fspot\"\ncurl -s \"https:\u002F\u002Fapi.coinbase.com\u002Fv2\u002Fprices\u002FSOL-USD\u002Fspot\"\ncurl -s \"https:\u002F\u002Fapi.coinbase.com\u002Fv2\u002Fprices\u002FXRP-USD\u002Fspot\"\n```\n\n```\nweb_search(\"S&P 500 Dow Jones Nasdaq today {date}\", count=5)\nweb_search(\"stock market today movers {date}\", count=5)\nweb_search(\"gold price silver price today\", count=3)\nweb_search(\"crypto market today {date}\", count=5)\n```\n\n### Step 4: Compose the Briefing Script\n\nWrite as a **conversational radio-host monologue**.\n\n**Style guidelines:**\n- Write like a smart, engaging radio host — NOT a list of headlines\n- **Use the host name** — introduce yourself: \"Good morning, I'm [host name], and this is your Briefing Room for [date]...\"\n- Sprinkle the name naturally throughout (sign-off, transitions) — don't overdo it\n- Do NOT start markdown with a `# Title` header — pandoc adds title from metadata\n- Connect stories with transitions\n- Add context: \"here's why this matters\"\n- **Stay neutral and balanced** — report facts, present sides, let listener decide\n- Target ~2,500-3,500 words for ~10 minutes\n- No emojis in the script (break TTS)\n- Write out numbers\u002Fabbreviations for TTS:\n  - \"$96,500\" → \"ninety-six thousand five hundred dollars\"\n  - \"S&P 500\" → \"S and P 500\"\n  - \"BTC\" → \"Bitcoin\"\n  - \"°C\" → \"degrees celsius\"\n\n**If language is not English**, write the entire script in that language.\n\n**Section order:**\n1. **Opening** — Date, quick teaser of top stories\n2. **Weather** — Current + week outlook for configured city\n3. **Trending on X** — What's hot on X\u002FTwitter\n4. **Web Trends** — What people are searching (Google Trends)\n5. **World** — Top 3-5 global stories\n6. **Politics** — US, EU, geopolitics\n7. **Tech & AI** — Launches, breakthroughs\n8. **Local** — News for configured city\u002Fcountry\n9. **Sports** — Headlines, results\n10. **Markets** — S&P 500, Dow, Nasdaq, movers\n11. **Crypto & Commodities** — BTC, ETH, alts, gold, silver\n12. **This Day in History** — 1-2 interesting events that happened on this date\n13. **Closing** — Wrap-up, sign-off\n\n**This Day in History:** No research needed — use your own knowledge. Pick 1-2 interesting, surprising, or fun events that happened on today's date. Mix it up: science, culture, politics, weird stuff. Keep it conversational: \"And before I let you go — did you know that on this day in 1996...\"\n\nOnly include sections from the configured `sections` list. Skip sections the user has removed.\n\nSave as `\u002Ftmp\u002Fbriefing_draft_$TIMESTAMP.md` (working file).\n\n**For the markdown**, include:\n- Section headers with emojis: `## 🌤️ Weather`, `## 🌍 World`, `## 📜 This Day in History`, etc.\n- Source links after key facts\n- Key data in bold\n\n### Step 5: Generate DOCX\n\n```bash\npandoc \"\u002Ftmp\u002Fbriefing_draft_$TIMESTAMP.md\" \\\n  -o \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.docx\" \\\n  --metadata title=\"Briefing Room - $DATE\"\n```\n\nIf pandoc is not available, skip DOCX and note it.\n\n### Step 6: Generate Audio\n\nRead the config to determine TTS engine and voice for the current language.\n\n**MLX-Audio (English, or if configured for language):**\n\n```bash\npython3 SKILL_DIR\u002Fscripts\u002Fconfig.py get voices.$LANG.engine\n# → if \"mlx\":\n```\n\n```python\nimport os, re, glob, json, subprocess\nfrom datetime import datetime\n\ntimestamp = datetime.now().strftime(\"%Y-%m-%d-%H%M\")  # must match TIMESTAMP from Step 0\n\n# Read config\nconfig_path = os.path.expanduser(\"~\u002F.briefing-room\u002Fconfig.json\")\nwith open(config_path) as f:\n    config = json.load(f)\n\nlang = config.get(\"language\", \"en\")\nvoices = config.get(\"voices\", {})\nvoice_cfg = voices.get(lang, voices.get(\"en\", {}))\n\n# Read and strip markdown from draft\nwith open(f\"\u002Ftmp\u002Fbriefing_draft_{timestamp}.md\", \"r\") as f:\n    text = f.read()\ntext = re.sub(r'#+ ', '', text)\ntext = re.sub(r'\\*\\*([^*]+)\\*\\*', r'\\1', text)\ntext = re.sub(r'\\*([^*]+)\\*', r'\\1', text)\ntext = re.sub(r'\\[([^\\]]+)\\]\\([^)]+\\)', r'\\1', text)\ntext = re.sub(r'---+', '', text)\ntext = re.sub(r'\\n{3,}', '\\n\\n', text)\n\n# Resolve voice\nblend = voice_cfg.get(\"mlx_voice_blend\")\nvoice = voice_cfg.get(\"mlx_voice\", \"af_heart\")\nif blend:\n    model = config.get(\"mlx_audio\", {}).get(\"model\", \"mlx-community\u002FKokoro-82M-bf16\")\n    model_slug = model.replace(\"\u002F\", \"--\")\n    cache_dir = os.path.expanduser(f\"~\u002F.cache\u002Fhuggingface\u002Fhub\u002Fmodels--{model_slug}\")\n    parts = []\n    for v, w in sorted(blend.items(), key=lambda x: -x[1]):\n        parts.append(f\"{v}_{int(w * 100)}\")\n    blend_name = \"_\".join(parts) + \".safetensors\"\n    matches = glob.glob(os.path.join(cache_dir, \"snapshots\u002F*\u002Fvoices\", blend_name))\n    if matches:\n        voice = matches[0]\n\nspeed = voice_cfg.get(\"speed\", 1.05)\nlang_code = config.get(\"mlx_audio\", {}).get(\"lang_code\", \"a\")\n\n# Find MLX-Audio\nmlx_path = config.get(\"mlx_audio\", {}).get(\"path\", \"\")\nif not mlx_path:\n    for p in [\"~\u002F.openclaw\u002Ftools\u002Fmlx-audio\", \"~\u002F.local\u002Fshare\u002Fmlx-audio\"]:\n        ep = os.path.expanduser(p)\n        if os.path.exists(os.path.join(ep, \".venv\u002Fbin\u002Fpython3\")):\n            mlx_path = ep\n            break\n\n# Generate via subprocess (uses MLX-Audio's venv)\npython_bin = os.path.join(mlx_path, \".venv\u002Fbin\u002Fpython3\")\n# ... generate_audio call with resolved voice, speed, lang_code\n```\n\n**Built-in Apple TTS (any language):**\n\nIf there's no voice configured for the language, auto-detect one:\n```bash\n# Try to get configured voice, fall back to auto-detect\nVOICE=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get voices.$LANG.builtin_voice)\nif [ \"$VOICE\" = \"None\" ] || [ -z \"$VOICE\" ]; then\n    # Auto-detect: match locale (e.g. sk_SK, de_DE, fr_FR)\n    # Prefer Enhanced\u002FPremium voices, fall back to any\n    VOICE=$(say -v '?' | grep \"${LANG}_\" \\\n      | grep -i \"Enhanced\\|Premium\" | head -1 \\\n      | sed 's\u002F *[a-z][a-z]_[A-Z][A-Z].*\u002F\u002F' | xargs)\n    [ -z \"$VOICE\" ] && VOICE=$(say -v '?' \\\n      | grep \"${LANG}_\" | head -1 \\\n      | sed 's\u002F *[a-z][a-z]_[A-Z][A-Z].*\u002F\u002F' | xargs)\nfi\nRATE=$(python3 SKILL_DIR\u002Fscripts\u002Fconfig.py get voices.$LANG.builtin_rate)\n# Strip markdown for TTS\nDRAFT=\"\u002Ftmp\u002Fbriefing_draft_$TIMESTAMP.md\"\nTTS_TXT=\"\u002Ftmp\u002Fbriefing_tts_$TIMESTAMP.txt\"\nsed -E 's\u002F#+\u002F\u002Fg; s\u002F\\*+\u002F\u002Fg; s\u002F\\[([^]]*)\\]\\([^)]*\\)\u002F\\1\u002Fg' \\\n  \"$DRAFT\" > \"$TTS_TXT\"\nsay -v \"$VOICE\" ${RATE:+-r $RATE} \\\n  -o \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.aiff\" \\\n  -f \"$TTS_TXT\"\nrm -f \"\u002Ftmp\u002Fbriefing_tts_$TIMESTAMP.txt\"\n```\n\n**Kokoro PyTorch (fallback):**\n\nSimilar to MLX but uses PyTorch backend. See TubeScribe skill for Kokoro usage patterns.\n\n### Step 6b: Convert to MP3\n\n```bash\n# Find the raw audio file (MLX outputs .wav, Apple TTS outputs .aiff)\nRAW=\"\"\nfor ext in wav aiff; do\n    if [ -f \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.$ext\" ]; then\n        RAW=\"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.$ext\"\n        break\n    fi\ndone\n\nif [ -n \"$RAW\" ]; then\n    ffmpeg -y \\\n      -i \"$RAW\" \\\n      -codec:a libmp3lame -qscale:a 2 \\\n      \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.mp3\"\n    if [ -s \"$OUTPUT_DIR\u002Fbriefing-$TIMESTAMP.mp3\" ]; then\n        rm \"$RAW\"\n    fi\nfi\n```\n\n### Step 6c: Cleanup\n\n```bash\nrm -f \"\u002Ftmp\u002Fbriefing_draft_$TIMESTAMP.md\"\n```\n\n### Step 7: Open Output Folder\n\n```bash\nopen \"$OUTPUT_DIR\"\n```\n\n**Do NOT auto-play.** Briefings are long and need playback controls.\n\n### Step 8: Report\n\nReport back with:\n- Date and language of briefing\n- Sections covered\n- Top 3-4 headlines\n- Audio duration\n- File locations\n\n## Helper Script\n\n```bash\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh setup     # Check dependencies + config\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh weather    # Fetch weather (uses config location)\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh trends     # Fetch X\u002FTwitter trends (US + UK + Worldwide)\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh webtrends  # Fetch Google Trends (US + UK + Worldwide)\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh crypto     # Fetch crypto prices\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh open       # Open today's folder\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh list       # List all briefings\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh clean      # Remove briefings >30 days old\nbash SKILL_DIR\u002Fscripts\u002Fbriefing.sh config     # Show raw config JSON\n```\n\n## Tips\n\n- Full pipeline takes 3-5 minutes (research + composition + TTS)\n- For shorter briefing, say \"quick briefing\" — cover top 3 sections only\n- If markets are closed (weekend\u002Fholiday), note it and skip detailed data\n- The agent IS the intelligence — read search results, compose the script, decide what matters\n- Users can add new languages by adding a `voices` entry + installing the voice via `say -v '?'`\n\n## Dependencies\n\n**Required:**\n- `curl` — API calls (built into macOS)\n- `web_search` tool — News research (OpenClaw built-in)\n\n**Recommended:**\n- MLX-Audio Kokoro — fast English TTS\n- `pandoc` — DOCX generation: `brew install pandoc`\n- `ffmpeg` — MP3 conversion: `brew install ffmpeg`\n\n**Built-in (macOS):**\n- Apple `say` — multilingual TTS (always available as fallback)\n\n## Error Handling\n\n| Issue | Action |\n|-------|--------|\n| No config file | Run `python3 SKILL_DIR\u002Fscripts\u002Fconfig.py init` |\n| API timeout | Retry once, skip that source, note it |\n| Web search empty | Try alternative query, note gaps |\n| TTS fails | Fall back to Apple `say` (always available) |\n| Pandoc not found | Skip DOCX, deliver MP3 only |\n| No internet | Cannot generate — inform user |\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"emoji":26,"requires":27},"📻",{"bins":28},[29],"curl","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fmatusvojtek\u002Fbriefing-room",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill \"Briefing Room\"",{"tool":45,"command":46},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill \"Briefing Room\"",{"tool":48,"command":49},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill \"Briefing Room\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmatusvojtek\u002Fbriefing-room\u002FSKILL.md",true,[],[54,62,69,76,83,90],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":61},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":61},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":61},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":61},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":61},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":61},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]