[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71EYM5953XVK31NW6JF0WXF":3,"skill-same:01M71EYM5953XVK31NW6JF0WXF":95},{"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":34,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":65,"commitSha":66,"skillDirectory":67,"forksCount":68,"repositoryHtmlUrl":69,"repositoryHomepageUrl":70,"ownerHtmlUrl":71,"ownerBlogUrl":72,"ownerDescription":73,"updatedAt":74,"install":75,"resources":88},"01M71EYM5953XVK31NW6JF0WXF","markitdown",null,"Extract document text as Markdown with Microsoft's MarkItDown CLI. Use for file conversion or YouTube transcripts; image OCR and audio transcription require verified optional backends and their data-transfer permissions.","coroboros\u002Fagent-skills","coroboros","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F276246903?v=4","01M71EW9FC462PB6BEAC5P9JK1","Coroboros","01M71EW9G1KB3SQM769D2JMXXZ",5,"MIT","https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmarkitdown\u002FSKILL.md",[18,23,26,29],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[5,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"xlsx","text","transcript","conversion","Bash","image","URL","when","only","clean","parse","read pdf","pptx","Audio","processing","PDF","clean text","docx","ocr","2026-11-10 10:12:30",false,"---\nname: markitdown\ndescription: Extract document text as Markdown with Microsoft's MarkItDown CLI. Use for file conversion or YouTube transcripts; image OCR and audio transcription require verified optional backends and their data-transfer permissions.\nwhen_to_use: When the user has a non-Markdown file (PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, EPub, ZIP, image, audio) or a YouTube URL and wants the contents as Markdown — for reading, summarising, feeding to an LLM, or saving as a clean text file. Keywords — convert to markdown, extract text, ocr, transcribe, read pdf, parse document, youtube transcript, markitdown, doc to md. Skip when the file is already Markdown, when the user wants visual rendering instead of text extraction, or when only a tiny snippet is needed and the Read tool is faster.\nargument-hint: \"[-s] [-S] [-d] [-p] [-k] [-l] \u003Cfile-or-url>\"\nallowed-tools: Bash(bash *) Bash(markitdown *) Bash(command *) Read\nlicense: MIT\ncompatibility: \"Requires bash and an installed MarkItDown CLI with the converter extras needed by the input. Audio\u002FOCR\u002Fplugin backends can use external services; verify configuration and authorized data transfer before processing.\"\nmetadata:\n  author: coroboros\n  sources: \"github.com\u002Fmicrosoft\u002Fmarkitdown\"\n---\n\n# MarkItDown\n\nConvert a document, image, audio file, or YouTube URL to Markdown using Microsoft's [`markitdown`](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fmarkitdown) CLI. The skill validates the input, composes the right flags, optionally saves the result under `~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fmarkitdown\u002F\u003Cslug>\u002F`, and reports a one-line summary with the fully-expanded absolute path (no tilde, no magic).\n\nThe deterministic work — install check, validation, slug derivation, save path, command composition — happens in `scripts\u002Fmarkitdown.sh`. The skill parses `$ARGUMENTS`, hands them to the script, and turns the script's `RESULT:` lines into a human report.\n\n## Install\n\n```bash\npip install 'markitdown[all]'\n```\n\nFor a smaller install, pick only what you need:\n\n| Group | Adds |\n|-------|------|\n| `[pdf]` | PDF parsing |\n| `[docx]` | Word documents |\n| `[pptx]` | PowerPoint |\n| `[xlsx]` `[xls]` | Excel |\n| `[outlook]` | Outlook `.msg` |\n| `[audio-transcription]` | MP3\u002FWAV transcription; the current converter sends audio to Google recognition |\n| `[youtube-transcription]` | YouTube transcripts |\n| `[az-doc-intel]` | Azure Document Intelligence backend |\n\nFor Azure Document Intelligence, also export `MARKITDOWN_DOCINTEL_ENDPOINT=https:\u002F\u002F\u003Cresource>.cognitiveservices.azure.com\u002F` before invoking with `-d`.\n\n## Parameters\n\n| Flag | Default | Effect |\n|------|---------|--------|\n| `-s` | off | Save Markdown to `~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fmarkitdown\u002F\u003Cslug>\u002F\u003Cstem>.md` |\n| `-S` | off | Force no-save (override an ambient save mode) |\n| `-d` | off | Use Azure Document Intelligence (needs `MARKITDOWN_DOCINTEL_ENDPOINT`) |\n| `-p` | off | Enable installed third-party `markitdown` plugins |\n| `-k` | off | Keep data URIs (base64 images) inline in the output |\n| `-l` | — | List installed plugins and exit |\n\nOutput saved under `~\u002F.agents\u002Foutput\u002F{project}\u002Fmarkitdown\u002F{slug}\u002F`, where `{project}` is the kebab-cased basename of the git toplevel (else cwd) and `{slug}` is a kebab of the input basename (≤5 words). Pipeline-friendly — typical downstream: `\u002Fforge -s -f \u003Cpath>` decomposes the extracted content into workstreams; `\u002Fapex -f \u003Cpath>` implements from it; any skill accepting `-f` can consume.\n\n## Workflow\n\n1. Resolve the target from arguments or unambiguous session context. Ask only when the target is missing or ambiguous. Before audio, OCR, Azure or plugin conversion, verify the installed backend and required data-transfer authorization; an optional dependency group does not imply local processing.\n2. Run the helper:\n\n   `$SKILL_DIR` = this skill's folder — `${CLAUDE_SKILL_DIR}` in Claude Code, the directory containing this SKILL.md elsewhere.\n\n   ```bash\n   bash \"$SKILL_DIR\"\u002Fscripts\u002Fmarkitdown.sh -s '\u002Fabsolute\u002Fpath\u002Freport.pdf'\n   ```\n\n   Parse arguments as data and pass each flag\u002Fvalue separately with shell quoting. Never splice raw `$ARGUMENTS` into shell code or use `eval`.\n\n3. The script emits `RESULT: key=value` lines — keys: `bytes`, `slug`, `saved`, plus `path` when saving (order is not guaranteed; parse by key) — followed either by the converted Markdown (no-save mode, after a `---` separator) or nothing (save mode — the file is on disk).\n4. Parse the `RESULT:` lines and produce the report below.\n5. If the script exits with `ERR: markitdown not installed` (exit 127) → print the install command from `## Install` and stop. Never auto-install on the user's behalf.\n6. If the script exits with another `ERR:` (file not found, missing endpoint, unknown flag) → relay the message verbatim and stop.\n\n## Output\n\n```\nmarkitdown: \u003Cinput> → \u003Cbytes> bytes of Markdown\nsaved: \u003Cpath>      # only when -s\n```\n\nWhen saving, report the actual file path. For long output, choose save mode when consistent with the request or capture stdout once in an authorized temporary file, then provide a bounded preview and the retained result. Do not repeat a costly conversion merely to truncate its display.\n\n## Examples\n\n```bash\n\u002Fmarkitdown ~\u002FDownloads\u002Freport.pdf            # convert, print to terminal\n\u002Fmarkitdown -s ~\u002FDownloads\u002Freport.pdf         # convert + save under ~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fmarkitdown\u002Freport\u002F\n\u002Fmarkitdown -s -p deck.pptx                   # use third-party plugins (e.g. markitdown-ocr)\n\u002Fmarkitdown -d invoice.pdf                    # Azure Document Intelligence\n\u002Fmarkitdown -k brand.html                     # keep base64 images inline\n\u002Fmarkitdown https:\u002F\u002Fyoutu.be\u002FdQw4w9WgXcQ      # YouTube transcript\n\u002Fmarkitdown -l                                # list installed plugins, then exit\n```\n\n## Notes\n\n- **YouTube URLs** are detected by the `https?:\u002F\u002F` prefix and passed straight to `markitdown`. The slug is derived from the URL's last path segment, so saved paths look like `~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fmarkitdown\u002Fdqw4w9wgxcq\u002FdQw4w9WgXcQ.md`.\n- **Audio transcription** in the verified 0.1.7 converter calls `recognize_google`; it is not local Whisper. Inspect the installed implementation and [Microsoft's source](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fmarkitdown\u002Fblob\u002Fmain\u002Fpackages\u002Fmarkitdown\u002Fsrc\u002Fmarkitdown\u002Fconverters\u002F_transcribe_audio.py) before processing. A local\u002Fprivate-only request needs an actually local configured tool; do not send audio externally under a local-processing promise.\n- **Image OCR** requires a configured capable backend. The [Microsoft OCR plugin instructions](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fmarkitdown#markitdown-ocr-plugin) require an `llm_client` and model; installing the plugin and passing `-p` alone is insufficient. Report unavailable OCR explicitly and use the documented integration only when its configuration and transport are authorized.\n- **Saved-output collisions** fail before conversion if the destination already exists. Use another destination\u002Finput identity or obtain authorization to replace the existing output; slug naming alone does not preserve files.\n\n## Why the wrapper\n\n`markitdown` is already a great CLI; this skill exists to (a) follow the repo's `-s\u002F-S\u002F-f` convention so other skills can chain on the output, (b) translate \"extract this pdf\" into the right invocation without forcing the user to remember `-x`, `-m`, `-d`, `-e`, and (c) emit a uniform one-line report so terminals don't render multi-MB Markdown by accident.\n","# MarkItDown\n\nConvert a document, image, audio file, or YouTube URL to Markdown using Microsoft's [`markitdown`](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fmarkitdown) CLI. The skill validates the input, composes the right flags, optionally saves the result under `~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fmarkitdown\u002F\u003Cslug>\u002F`, and reports a one-line summary with the fully-expanded absolute path (no tilde, no magic).\n\nThe deterministic work — install check, validation, slug derivation, save path, command composition — happens in `scripts\u002Fmarkitdown.sh`. The skill parses `$ARGUMENTS`, hands them to the script, and turns the script's `RESULT:` lines into a human report.\n\n## Install\n\n```bash\npip install 'markitdown[all]'\n```\n\nFor a smaller install, pick only what you need:\n\n| Group | Adds |\n|-------|------|\n| `[pdf]` | PDF parsing |\n| `[docx]` | Word documents |\n| `[pptx]` | PowerPoint |\n| `[xlsx]` `[xls]` | Excel |\n| `[outlook]` | Outlook `.msg` |\n| `[audio-transcription]` | MP3\u002FWAV transcription; the current converter sends audio to Google recognition |\n| `[youtube-transcription]` | YouTube transcripts |\n| `[az-doc-intel]` | Azure Document Intelligence backend |\n\nFor Azure Document Intelligence, also export `MARKITDOWN_DOCINTEL_ENDPOINT=https:\u002F\u002F\u003Cresource>.cognitiveservices.azure.com\u002F` before invoking with `-d`.\n\n## Parameters\n\n| Flag | Default | Effect |\n|------|---------|--------|\n| `-s` | off | Save Markdown to `~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fmarkitdown\u002F\u003Cslug>\u002F\u003Cstem>.md` |\n| `-S` | off | Force no-save (override an ambient save mode) |\n| `-d` | off | Use Azure Document Intelligence (needs `MARKITDOWN_DOCINTEL_ENDPOINT`) |\n| `-p` | off | Enable installed third-party `markitdown` plugins |\n| `-k` | off | Keep data URIs (base64 images) inline in the output |\n| `-l` | — | List installed plugins and exit |\n\nOutput saved under `~\u002F.agents\u002Foutput\u002F{project}\u002Fmarkitdown\u002F{slug}\u002F`, where `{project}` is the kebab-cased basename of the git toplevel (else cwd) and `{slug}` is a kebab of the input basename (≤5 words). Pipeline-friendly — typical downstream: `\u002Fforge -s -f \u003Cpath>` decomposes the extracted content into workstreams; `\u002Fapex -f \u003Cpath>` implements from it; any skill accepting `-f` can consume.\n\n## Workflow\n\n1. Resolve the target from arguments or unambiguous session context. Ask only when the target is missing or ambiguous. Before audio, OCR, Azure or plugin conversion, verify the installed backend and required data-transfer authorization; an optional dependency group does not imply local processing.\n2. Run the helper:\n\n   `$SKILL_DIR` = this skill's folder — `${CLAUDE_SKILL_DIR}` in Claude Code, the directory containing this SKILL.md elsewhere.\n\n   ```bash\n   bash \"$SKILL_DIR\"\u002Fscripts\u002Fmarkitdown.sh -s '\u002Fabsolute\u002Fpath\u002Freport.pdf'\n   ```\n\n   Parse arguments as data and pass each flag\u002Fvalue separately with shell quoting. Never splice raw `$ARGUMENTS` into shell code or use `eval`.\n\n3. The script emits `RESULT: key=value` lines — keys: `bytes`, `slug`, `saved`, plus `path` when saving (order is not guaranteed; parse by key) — followed either by the converted Markdown (no-save mode, after a `---` separator) or nothing (save mode — the file is on disk).\n4. Parse the `RESULT:` lines and produce the report below.\n5. If the script exits with `ERR: markitdown not installed` (exit 127) → print the install command from `## Install` and stop. Never auto-install on the user's behalf.\n6. If the script exits with another `ERR:` (file not found, missing endpoint, unknown flag) → relay the message verbatim and stop.\n\n## Output\n\n```\nmarkitdown: \u003Cinput> → \u003Cbytes> bytes of Markdown\nsaved: \u003Cpath>      # only when -s\n```\n\nWhen saving, report the actual file path. For long output, choose save mode when consistent with the request or capture stdout once in an authorized temporary file, then provide a bounded preview and the retained result. Do not repeat a costly conversion merely to truncate its display.\n\n## Examples\n\n```bash\n\u002Fmarkitdown ~\u002FDownloads\u002Freport.pdf            # convert, print to terminal\n\u002Fmarkitdown -s ~\u002FDownloads\u002Freport.pdf         # convert + save under ~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fmarkitdown\u002Freport\u002F\n\u002Fmarkitdown -s -p deck.pptx                   # use third-party plugins (e.g. markitdown-ocr)\n\u002Fmarkitdown -d invoice.pdf                    # Azure Document Intelligence\n\u002Fmarkitdown -k brand.html                     # keep base64 images inline\n\u002Fmarkitdown https:\u002F\u002Fyoutu.be\u002FdQw4w9WgXcQ      # YouTube transcript\n\u002Fmarkitdown -l                                # list installed plugins, then exit\n```\n\n## Notes\n\n- **YouTube URLs** are detected by the `https?:\u002F\u002F` prefix and passed straight to `markitdown`. The slug is derived from the URL's last path segment, so saved paths look like `~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fmarkitdown\u002Fdqw4w9wgxcq\u002FdQw4w9WgXcQ.md`.\n- **Audio transcription** in the verified 0.1.7 converter calls `recognize_google`; it is not local Whisper. Inspect the installed implementation and [Microsoft's source](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fmarkitdown\u002Fblob\u002Fmain\u002Fpackages\u002Fmarkitdown\u002Fsrc\u002Fmarkitdown\u002Fconverters\u002F_transcribe_audio.py) before processing. A local\u002Fprivate-only request needs an actually local configured tool; do not send audio externally under a local-processing promise.\n- **Image OCR** requires a configured capable backend. The [Microsoft OCR plugin instructions](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fmarkitdown#markitdown-ocr-plugin) require an `llm_client` and model; installing the plugin and passing `-p` alone is insufficient. Report unavailable OCR explicitly and use the documented integration only when its configuration and transport are authorized.\n- **Saved-output collisions** fail before conversion if the destination already exists. Use another destination\u002Finput identity or obtain authorization to replace the existing output; slug naming alone does not preserve files.\n\n## Why the wrapper\n\n`markitdown` is already a great CLI; this skill exists to (a) follow the repo's `-s\u002F-S\u002F-f` convention so other skills can chain on the output, (b) translate \"extract this pdf\" into the right invocation without forcing the user to remember `-x`, `-m`, `-d`, `-e`, and (c) emit a uniform one-line report so terminals don't render multi-MB Markdown by accident.\n",{"name":5,"license":15,"metadata":59,"description":7,"when_to_use":61,"allowed-tools":62,"argument-hint":63,"compatibility":64},{"author":9,"sources":60},"github.com\u002Fmicrosoft\u002Fmarkitdown","When the user has a non-Markdown file (PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, EPub, ZIP, image, audio) or a YouTube URL and wants the contents as Markdown — for reading, summarising, feeding to an LLM, or saving as a clean text file. Keywords — convert to markdown, extract text, ocr, transcribe, read pdf, parse document, youtube transcript, markitdown, doc to md. Skip when the file is already Markdown, when the user wants visual rendering instead of text extraction, or when only a tiny snippet is needed and the Read tool is faster.","Bash(bash *) Bash(markitdown *) Bash(command *) Read","[-s] [-S] [-d] [-p] [-k] [-l] \u003Cfile-or-url>","Requires bash and an installed MarkItDown CLI with the converter extras needed by the input. Audio\u002FOCR\u002Fplugin backends can use external services; verify configuration and authorized data transfer before processing.","main","5ff268fdc77fdf345ffe3ba808e74c82023839f8","skills\u002Fmarkitdown",0,"https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills","https:\u002F\u002Fcoroboros.com","https:\u002F\u002Fgithub.com\u002Fcoroboros","https:\u002F\u002Fcoroboros.com\u002F","Branch-stable systems.","2026-11-11 14:33:57",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add coroboros\u002Fagent-skills --skill markitdown",{"tool":81,"command":82},"bunx","bunx skills add coroboros\u002Fagent-skills --skill markitdown",{"tool":84,"command":85},"pnpm","pnpm dlx skills add coroboros\u002Fagent-skills --skill markitdown","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmarkitdown\u002FSKILL.md",true,[89],{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fmarkitdown.sh","SCRIPT","脚本",3230,"https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmarkitdown\u002Fscripts\u002Fmarkitdown.sh",[96,110,120,154,177,200],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":54},"01M71EZVB829YQPX3AM9ETPJYE","foo","Fixture skill for repo-kind classifier tests.","https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Fcode-ultrareview\u002Ffixtures\u002Fclassify\u002Fskills\u002Fskills\u002Ffoo\u002FSKILL.md",[],[98,103,104,105,106,107,108,109],"fixture skill","repo","classifier","for","kind","tests","fixture",{"skillNo":111,"name":98,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":54},"01M71EZSPGWRBJ9JGT0Y5F7YGX","Fixture for compound skills + npm tooling detection.","https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Fcode-ultrareview\u002Ffixtures\u002Fclassify\u002Fmixed-skills-npm\u002Fskills\u002Ffoo\u002FSKILL.md",[],[98,116,117,106,118,119,109],"detection","tooling","compound","npm",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":135,"publishedAt":54},"01M71EZN3JR87PJ1BBHRG24M39","write-clear-readme","Author, restructure, audit or polish a project README for clarity and scannability. Reads repository truth, preserves anchors and code, and verifies rendering. Explicit author\u002Fpolish requests apply local changes; audit\u002Fpropose stays read-only. Use for README creation, wording, structure and navigation, including skill collections and CLI\u002FSDK docs.","https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-clear-readme\u002FSKILL.md",[126,129,132],{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":133,"categoryName":134,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000036","内容创作者",[136,137,138,139,140,43,141,142,143,144,145,146,147,148,149,150,151,152,39,153],"clear","README","write clear readme","write","writing","local","project","creation","ls","access","verification","references","libraries","project readme","browser","code","preview","markdown preview",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":54},"01M71EZGFF8C081XJVPGJ11AG7","video-loop","Prepare a background video loop for a website with optional crossfade, MP4\u002FWebM encoding and poster extraction. Use for loop joins or web delivery of an existing clip.","https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-loop\u002FSKILL.md",[160],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[162,163,164,165,39,166,167,146,168,169,170,171,172,173,174,175,176,48,49,42],"Video","loop","video loop","hero","architecture","command","loops","optimize","transition","work","inspection","continuity","fix","end","crossfade",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":184,"publishedAt":54},"01M71EZCS60P8DK9Y34PHGK1R3","ultrapex","Adaptive implementation when the user explicitly selects \u002Fultrapex or asks for this adaptive workflow. Establish accepted outcomes, implement, and verify the final result. Generic implementation requests use \u002Fapex; use \u002Fforge for decisions only and \u002Foneshot for small focused changes.","https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fultrapex\u002FSKILL.md",[183],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},[179,185,186,142,187,175,188,189,190,191,192,193,194,195,196,42,197,198,43,199],"ponytail","select","model","apex","capability","context","Tools","at","result","self","review","workflow","forge","host","delegation",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":210,"publishedAt":54},"01M71EZ5Y1QZWEV5K69JT7QK1D","suno-produce","Create and revise Suno v5.5 prompt artifacts from a song, track or album brief. Produces TRACK.md, ALBUM.md for explicit multi-track work, and optional ARTIST.md identity. Validates prompt fields and preserves supplied lyrics. Artifact-only; audio generation stays in Suno. Pure lyric writing and audio post-production use other skills.","https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsuno-produce\u002FSKILL.md",[206,207,208,209],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":127,"categoryName":128,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":133,"categoryName":134,"taxonomyType":32,"taxonomyTypeDesc":33},[211,212,213,214,215,216,217,218,219,220,221,222,197,163,140,198,223,141,224,48],"produce","suno","suno produce","lyric","website","mv","artifact","track","create","guides","information","song","question","Meta"]