[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FTW9NBGPR2CCTJ1A4F4FE9":3,"skill-same:01M6FTW9NBGPR2CCTJ1A4F4FE9":121},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":68,"commitSha":69,"skillDirectory":70,"forksCount":71,"repositoryHtmlUrl":72,"repositoryHomepageUrl":6,"ownerHtmlUrl":73,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":74,"install":75,"resources":88},"01M6FTW9NBGPR2CCTJ1A4F4FE9","gettr-transcribe-summarize",null,"Download audio from a GETTR post (via HTML og:video), transcribe it locally with MLX Whisper on Apple Silicon (with timestamps via VTT), and summarize the transcript into bullet points and\u002For a timestamped outline. Use when given a GETTR post URL and asked to produce a transcript or summary.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"gettr transcribe summarize","transcribe","summarize","html","timestamps","URL","with","silicon","apple","mlx whisper","whisper","mlx","use","install","brew","apple silicon","Audio","Video","produce","transcript","2026-11-10 10:12:30",false,"---\nname: gettr-transcribe-summarize\ndescription: Download audio from a GETTR post (via HTML og:video), transcribe it locally with MLX Whisper on Apple Silicon (with timestamps via VTT), and summarize the transcript into bullet points and\u002For a timestamped outline. Use when given a GETTR post URL and asked to produce a transcript or summary.\nhomepage: https:\u002F\u002Fgettr.com\nmetadata: {\"clawdbot\":{\"emoji\":\"?\",\"requires\":{\"bins\":[\"mlx_whisper\",\"ffmpeg\"]},\"install\":[{\"id\":\"mlx-whisper\",\"kind\":\"pip\",\"package\":\"mlx-whisper\",\"bins\":[\"mlx_whisper\"],\"label\":\"Install mlx-whisper (pip)\"},{\"id\":\"ffmpeg\",\"kind\":\"brew\",\"formula\":\"ffmpeg\",\"bins\":[\"ffmpeg\"],\"label\":\"Install ffmpeg (brew)\"}]}}\n---\n\n# Gettr Transcribe + Summarize (MLX Whisper)\n\n## Quick start\n\n```bash\n# 1. Parse the slug from the URL (just read it — no script needed)\n#    https:\u002F\u002Fgettr.com\u002Fpost\u002Fp1abc2def  → slug = p1abc2def\n#    https:\u002F\u002Fgettr.com\u002Fstreaming\u002Fp3xyz → slug = p3xyz\n\n# 2. Get the video URL\n#    For \u002Fpost\u002F URLs: use the extraction script\npython3 scripts\u002Fextract_gettr_og_video.py \"\u003CGETTR_POST_URL>\"\n\n#    For \u002Fstreaming\u002F URLs: use browser automation directly (extraction script is unreliable)\n#    See Step 1 below for browser automation instructions\n\n# 3. Run download + transcription pipeline\nbash scripts\u002Frun_pipeline.sh \"\u003CVIDEO_URL>\" \"\u003CSLUG>\"\n```\n\nTo explicitly set the transcription language (recommended for non-English content):\n```bash\nbash scripts\u002Frun_pipeline.sh --language zh \"\u003CVIDEO_URL>\" \"\u003CSLUG>\"\n```\n\nCommon language codes: `zh` (Chinese), `en` (English), `ja` (Japanese), `ko` (Korean), `es` (Spanish), `fr` (French), `de` (German), `ru` (Russian).\n\nThis outputs:\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Faudio.wav`\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Faudio.vtt`\n\nThen proceed to Step 3 (Summarize) to generate the final deliverable.\n\n---\n\n## Workflow (GETTR URL → transcript → summary)\n\n### Inputs to confirm\nAsk for:\n- GETTR post URL\n- Output format: **bullets only** or **bullets + timestamped outline**\n- Summary size: **short**, **medium** (default), or **detailed**\n- Language (optional): if the video is non-English and auto-detection fails, ask for the language code (e.g., `zh` for Chinese)\n\nNotes:\n- This skill does **not** handle authentication-gated GETTR posts.\n- This skill does **not** translate; outputs stay in the video's original language.\n- If transcription quality is poor or mixed with English, re-run with explicit `--language` flag.\n\n### Prereqs (local)\n- `mlx_whisper` installed and on PATH\n- `ffmpeg` installed (recommended: `brew install ffmpeg`)\n\n### Step 0 — Parse the slug and pick an output directory\n\nParse the slug directly from the GETTR URL — just read the last path segment, no script needed:\n- `https:\u002F\u002Fgettr.com\u002Fpost\u002Fp1abc2def` → slug = `p1abc2def`\n- `https:\u002F\u002Fgettr.com\u002Fstreaming\u002Fp3xyz789` → slug = `p3xyz789`\n\nOutput directory: `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002F`\n\nDirectory structure:\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Faudio.wav`\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Faudio.vtt`\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Fsummary.md`\n\n### Step 1 — Get the video URL\n\nThe approach depends on the URL type:\n\n#### For `\u002Fpost\u002F` URLs — Use the extraction script\n\nRun the extraction script to get the video URL from the post HTML:\n\n```bash\npython3 scripts\u002Fextract_gettr_og_video.py \"\u003CGETTR_POST_URL>\"\n```\n\nThis prints the best candidate video URL (often an HLS `.m3u8`) to stdout.\n\nIf extraction fails, ask the user to provide the `.m3u8`\u002FMP4 URL directly (common if the post is private\u002Fgated or the HTML is dynamic).\n\n#### For `\u002Fstreaming\u002F` URLs — Use browser automation directly\n\n**Do not use the extraction script for streaming URLs.** The `og:video` URL from static HTML extraction is unreliable for streaming content — it either fails outright or the download stalls and fails near the end.\n\nInstead, use browser automation to get a fresh, dynamically-signed URL:\n1. Open the GETTR streaming URL and wait for the page to fully load (JavaScript must execute)\n2. Extract the `og:video` meta tag content from the rendered DOM:\n   ```javascript\n   document.querySelector('meta[property=\"og:video\"]').getAttribute('content')\n   ```\n3. Use that fresh URL for the pipeline in Step 2\n\nIf browser automation is not available or fails, see `references\u002Ftroubleshooting.md` for how to guide the user to manually extract the fresh URL from their browser.\n\n### Step 2 — Run the pipeline (download + transcribe)\n\nFeed the extracted video URL and slug into the pipeline:\n\n```bash\nbash scripts\u002Frun_pipeline.sh \"\u003CVIDEO_URL>\" \"\u003CSLUG>\"\n```\n\nTo explicitly set the language (recommended when auto-detection fails):\n```bash\nbash scripts\u002Frun_pipeline.sh --language zh \"\u003CVIDEO_URL>\" \"\u003CSLUG>\"\n```\n\nThe pipeline does two things:\n1. Downloads audio as 16kHz mono WAV via ffmpeg\n2. Transcribes with MLX Whisper, outputting VTT with timestamps\n\n#### If the pipeline fails with HTTP 412 (stale signed URL)\n\nThis error occurs with `\u002Fstreaming\u002F` URLs when the signed URL has expired. If browser automation returned a stale URL, retry by re-running browser automation to get a fresh URL, then retry the pipeline.\n\nIf browser automation is not available or fails, see `references\u002Ftroubleshooting.md` for how to guide the user to manually extract the fresh URL from their browser.\n\nNotes:\n- By default, language is auto-detected. For non-English content where detection fails, use `--language`.\n- If too slow or memory-heavy, try smaller models: `mlx-community\u002Fwhisper-medium` or `mlx-community\u002Fwhisper-small`.\n- If quality is poor, try the full model: `mlx-community\u002Fwhisper-large-v3` (slower but more accurate).\n- If `--word-timestamps` causes issues, the pipeline retries automatically without it.\n\n### Step 3 — Summarize\nWrite the final deliverable to `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Fsummary.md`.\n\nPick a **summary size** (user-selectable):\n- **Short:** 5–8 bullets; (if outline) 4–6 sections\n- **Medium (default):** 8–20 bullets; (if outline) 6–15 sections\n- **Detailed:** 20–40 bullets; (if outline) 15–30 sections\n\nInclude:\n- **Bullets** (per size above)\n- Optional **timestamped outline** (per size above)\n\nTimestamped outline format (default heading style):\n```\n[00:00 - 02:15] Section heading\n- 1–3 sub-bullets\n```\n\nWhen building the outline from VTT cues:\n- Group adjacent cues into coherent sections.\n- Use the start time of the first cue and end time of the last cue in the section.\n\n## Bundled scripts\n- `scripts\u002Frun_pipeline.sh`: download + transcription pipeline (takes a video URL and slug)\n- `scripts\u002Fextract_gettr_og_video.py`: fetch GETTR HTML and extract the `og:video` URL (with retry\u002Fbackoff)\n- `scripts\u002Fdownload_audio.sh`: download\u002Fextract audio from HLS or MP4 URL to 16kHz mono WAV\n\n### Error handling\n- **Non-video posts**: The extraction script detects image\u002Ftext posts and provides a helpful error message.\n- **Network errors**: Automatic retry with exponential backoff (up to 3 attempts).\n- **No audio track**: The download script validates output and reports if the source has no audio.\n- **HTTP 412 errors**: Occurs with `\u002Fstreaming\u002F` URLs when the signed URL has expired. Re-run browser automation to get a fresh URL (see Step 1); if that fails, see `references\u002Ftroubleshooting.md`.\n\n## Troubleshooting\nSee `references\u002Ftroubleshooting.md` for detailed solutions to common issues including:\n- HTTP 412 errors (stale signed URLs)\n- Extraction failures\n- Download errors\n- Transcription quality issues\n","# Gettr Transcribe + Summarize (MLX Whisper)\n\n## Quick start\n\n```bash\n# 1. Parse the slug from the URL (just read it — no script needed)\n#    https:\u002F\u002Fgettr.com\u002Fpost\u002Fp1abc2def  → slug = p1abc2def\n#    https:\u002F\u002Fgettr.com\u002Fstreaming\u002Fp3xyz → slug = p3xyz\n\n# 2. Get the video URL\n#    For \u002Fpost\u002F URLs: use the extraction script\npython3 scripts\u002Fextract_gettr_og_video.py \"\u003CGETTR_POST_URL>\"\n\n#    For \u002Fstreaming\u002F URLs: use browser automation directly (extraction script is unreliable)\n#    See Step 1 below for browser automation instructions\n\n# 3. Run download + transcription pipeline\nbash scripts\u002Frun_pipeline.sh \"\u003CVIDEO_URL>\" \"\u003CSLUG>\"\n```\n\nTo explicitly set the transcription language (recommended for non-English content):\n```bash\nbash scripts\u002Frun_pipeline.sh --language zh \"\u003CVIDEO_URL>\" \"\u003CSLUG>\"\n```\n\nCommon language codes: `zh` (Chinese), `en` (English), `ja` (Japanese), `ko` (Korean), `es` (Spanish), `fr` (French), `de` (German), `ru` (Russian).\n\nThis outputs:\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Faudio.wav`\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Faudio.vtt`\n\nThen proceed to Step 3 (Summarize) to generate the final deliverable.\n\n---\n\n## Workflow (GETTR URL → transcript → summary)\n\n### Inputs to confirm\nAsk for:\n- GETTR post URL\n- Output format: **bullets only** or **bullets + timestamped outline**\n- Summary size: **short**, **medium** (default), or **detailed**\n- Language (optional): if the video is non-English and auto-detection fails, ask for the language code (e.g., `zh` for Chinese)\n\nNotes:\n- This skill does **not** handle authentication-gated GETTR posts.\n- This skill does **not** translate; outputs stay in the video's original language.\n- If transcription quality is poor or mixed with English, re-run with explicit `--language` flag.\n\n### Prereqs (local)\n- `mlx_whisper` installed and on PATH\n- `ffmpeg` installed (recommended: `brew install ffmpeg`)\n\n### Step 0 — Parse the slug and pick an output directory\n\nParse the slug directly from the GETTR URL — just read the last path segment, no script needed:\n- `https:\u002F\u002Fgettr.com\u002Fpost\u002Fp1abc2def` → slug = `p1abc2def`\n- `https:\u002F\u002Fgettr.com\u002Fstreaming\u002Fp3xyz789` → slug = `p3xyz789`\n\nOutput directory: `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002F`\n\nDirectory structure:\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Faudio.wav`\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Faudio.vtt`\n- `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Fsummary.md`\n\n### Step 1 — Get the video URL\n\nThe approach depends on the URL type:\n\n#### For `\u002Fpost\u002F` URLs — Use the extraction script\n\nRun the extraction script to get the video URL from the post HTML:\n\n```bash\npython3 scripts\u002Fextract_gettr_og_video.py \"\u003CGETTR_POST_URL>\"\n```\n\nThis prints the best candidate video URL (often an HLS `.m3u8`) to stdout.\n\nIf extraction fails, ask the user to provide the `.m3u8`\u002FMP4 URL directly (common if the post is private\u002Fgated or the HTML is dynamic).\n\n#### For `\u002Fstreaming\u002F` URLs — Use browser automation directly\n\n**Do not use the extraction script for streaming URLs.** The `og:video` URL from static HTML extraction is unreliable for streaming content — it either fails outright or the download stalls and fails near the end.\n\nInstead, use browser automation to get a fresh, dynamically-signed URL:\n1. Open the GETTR streaming URL and wait for the page to fully load (JavaScript must execute)\n2. Extract the `og:video` meta tag content from the rendered DOM:\n   ```javascript\n   document.querySelector('meta[property=\"og:video\"]').getAttribute('content')\n   ```\n3. Use that fresh URL for the pipeline in Step 2\n\nIf browser automation is not available or fails, see `references\u002Ftroubleshooting.md` for how to guide the user to manually extract the fresh URL from their browser.\n\n### Step 2 — Run the pipeline (download + transcribe)\n\nFeed the extracted video URL and slug into the pipeline:\n\n```bash\nbash scripts\u002Frun_pipeline.sh \"\u003CVIDEO_URL>\" \"\u003CSLUG>\"\n```\n\nTo explicitly set the language (recommended when auto-detection fails):\n```bash\nbash scripts\u002Frun_pipeline.sh --language zh \"\u003CVIDEO_URL>\" \"\u003CSLUG>\"\n```\n\nThe pipeline does two things:\n1. Downloads audio as 16kHz mono WAV via ffmpeg\n2. Transcribes with MLX Whisper, outputting VTT with timestamps\n\n#### If the pipeline fails with HTTP 412 (stale signed URL)\n\nThis error occurs with `\u002Fstreaming\u002F` URLs when the signed URL has expired. If browser automation returned a stale URL, retry by re-running browser automation to get a fresh URL, then retry the pipeline.\n\nIf browser automation is not available or fails, see `references\u002Ftroubleshooting.md` for how to guide the user to manually extract the fresh URL from their browser.\n\nNotes:\n- By default, language is auto-detected. For non-English content where detection fails, use `--language`.\n- If too slow or memory-heavy, try smaller models: `mlx-community\u002Fwhisper-medium` or `mlx-community\u002Fwhisper-small`.\n- If quality is poor, try the full model: `mlx-community\u002Fwhisper-large-v3` (slower but more accurate).\n- If `--word-timestamps` causes issues, the pipeline retries automatically without it.\n\n### Step 3 — Summarize\nWrite the final deliverable to `.\u002Fout\u002Fgettr-transcribe-summarize\u002F\u003Cslug>\u002Fsummary.md`.\n\nPick a **summary size** (user-selectable):\n- **Short:** 5–8 bullets; (if outline) 4–6 sections\n- **Medium (default):** 8–20 bullets; (if outline) 6–15 sections\n- **Detailed:** 20–40 bullets; (if outline) 15–30 sections\n\nInclude:\n- **Bullets** (per size above)\n- Optional **timestamped outline** (per size above)\n\nTimestamped outline format (default heading style):\n```\n[00:00 - 02:15] Section heading\n- 1–3 sub-bullets\n```\n\nWhen building the outline from VTT cues:\n- Group adjacent cues into coherent sections.\n- Use the start time of the first cue and end time of the last cue in the section.\n\n## Bundled scripts\n- `scripts\u002Frun_pipeline.sh`: download + transcription pipeline (takes a video URL and slug)\n- `scripts\u002Fextract_gettr_og_video.py`: fetch GETTR HTML and extract the `og:video` URL (with retry\u002Fbackoff)\n- `scripts\u002Fdownload_audio.sh`: download\u002Fextract audio from HLS or MP4 URL to 16kHz mono WAV\n\n### Error handling\n- **Non-video posts**: The extraction script detects image\u002Ftext posts and provides a helpful error message.\n- **Network errors**: Automatic retry with exponential backoff (up to 3 attempts).\n- **No audio track**: The download script validates output and reports if the source has no audio.\n- **HTTP 412 errors**: Occurs with `\u002Fstreaming\u002F` URLs when the signed URL has expired. Re-run browser automation to get a fresh URL (see Step 1); if that fails, see `references\u002Ftroubleshooting.md`.\n\n## Troubleshooting\nSee `references\u002Ftroubleshooting.md` for detailed solutions to common issues including:\n- HTTP 412 errors (stale signed URLs)\n- Extraction failures\n- Download errors\n- Transcription quality issues\n",{"name":5,"homepage":51,"metadata":52,"description":7},"https:\u002F\u002Fgettr.com",{"clawdbot":53},{"emoji":54,"install":55,"requires":66},"?",[56,62],{"id":57,"bins":58,"kind":60,"label":61,"package":57},"mlx-whisper",[59],"mlx_whisper","pip","Install mlx-whisper (pip)",{"id":63,"bins":64,"kind":40,"label":65,"formula":63},"ffmpeg",[63],"Install ffmpeg (brew)",{"bins":67},[59,63],"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fkevin37li\u002Fgettr-transcribe-summarize",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add kbarbel640-del\u002Fskills --skill gettr-transcribe-summarize",{"tool":81,"command":82},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill gettr-transcribe-summarize",{"tool":84,"command":85},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill gettr-transcribe-summarize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002FSKILL.md",true,[89,95,99,103,107,113,117],{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"_meta.json","REFERENCE","参考文档",839,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002F_meta.json",{"path":96,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":97,"sourceHtmlUrl":98},"README.md",1335,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002FREADME.md",{"path":100,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fapi_reference.md",844,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002Freferences\u002Fapi_reference.md",{"path":104,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Ftroubleshooting.md",3458,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002Freferences\u002Ftroubleshooting.md",{"path":108,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Fdownload_audio.sh","SCRIPT","脚本",1068,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002Fscripts\u002Fdownload_audio.sh",{"path":114,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Fextract_gettr_og_video.py",4570,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002Fscripts\u002Fextract_gettr_og_video.py",{"path":118,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":119,"sourceHtmlUrl":120},"scripts\u002Frun_pipeline.sh",3984,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fkevin37li\u002Fgettr-transcribe-summarize\u002Fscripts\u002Frun_pipeline.sh",[122,152,178,197,203,223],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":133,"publishedAt":46},"01M6G8J55967D6281ACMKAKTEQ","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\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[128],{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[134,135,136,32,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151],"crowd prompting","prompting","api","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":161,"publishedAt":46},"01M6G8J0PKPAYVET6BWE8W4C26","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\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[158],{"categoryNo":159,"categoryName":160,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[162,136,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,140,38],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":185,"publishedAt":46},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[184],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[186,187,188,189,190,191,192,32,193,176,38,194,136,195,196],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":198,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":202,"publishedAt":46},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[201],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[189,188,187,186,196,191,192,32,190,176,38,193,194,136,195],{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":209,"publishedAt":46},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[210,211,212,213,214,215,216,217,218,219,220,221,222],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":233,"publishedAt":46},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[229,230],{"categoryNo":159,"categoryName":160,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":231,"categoryName":232,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000037","律师与法务",[234,235,236,237,32,238,239,68,240,194,241,242,243,244,245,149,246,247,248],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]