[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71EXWSRKM5CKKNE2G88P04P":3,"skill-same:01M71EXWSRKM5CKKNE2G88P04P":88},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":81},"01M71EXWSRKM5CKKNE2G88P04P","download-media",null,"Download video, audio, playlists, clips or subtitles from a supported URL using yt-dlp. Use when the user wants media files on disk; use MarkItDown for text extraction and the loop skills for local loop editing.","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\u002Fdownload-media\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"download media","download","Media","streaming","transcript","disk","Bash","URL","when","loop","files","only","local","dlp","authentication","re","neither","Audio","playlist","Video","2026-11-10 10:12:30",false,"---\nname: download-media\ndescription: Download video, audio, playlists, clips or subtitles from a supported URL using yt-dlp. Use when the user wants media files on disk; use MarkItDown for text extraction and the loop skills for local loop editing.\nwhen_to_use: When the user has a media URL and wants the file on disk — video, audio-only, playlist, clip, or subtitles. Keywords — download video, yt-dlp, youtube, save video, extract audio, mp3, rip, playlist, clip, subtitles, 1080p. Skip when the user wants the transcript or text content (\u002Fmarkitdown), wants to loop or re-encode a local file (\u002Fvideo-loop, \u002Faudio-loop), or targets DRM-protected streaming services (Netflix, Disney+, Spotify…) — yt-dlp does not bypass DRM and neither does this skill.\nargument-hint: \"[-a] [-b] [-p] [-i] [-c A-B] [-u langs] [-r height] [-d dir] \u003Curl> [yt-dlp args]\"\nallowed-tools: Bash(bash *) Bash(yt-dlp *) Bash(command *) Read\nlicense: MIT\ncompatibility: \"Requires bash and an installed yt-dlp CLI. FFmpeg is required for audio extraction, clipping and applicable merges; some extractors require additional documented runtimes or authentication.\"\nmetadata:\n  author: coroboros\n  sources: \"github.com\u002Fyt-dlp\u002Fyt-dlp\"\n---\n\n# Download Media\n\nDownload video or audio from any [yt-dlp-supported site](https:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp\u002Fblob\u002Fmaster\u002Fsupportedsites.md) using the [`yt-dlp`](https:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp) CLI. The skill validates the input, composes the right flags for the intent, downloads under `~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fdownload-media\u002F\u003Cslug>\u002F` (or a `-d` destination), and reports the final file paths — fully expanded, no tilde, no magic.\n\nThe deterministic work — install checks, slug derivation, destination, flag composition, final-path capture — happens in `scripts\u002Fdownload-media.sh`. The skill parses `$ARGUMENTS`, hands them to the script, and turns the script's `RESULT:` lines into a human report.\n\n## Scope\n\nPersonal and authorized use: public content, the user's own uploads, Creative Commons and licensed material. yt-dlp cannot bypass DRM and this skill never attempts to; decline requests to rip paid streaming catalogs (Netflix, Disney+, Spotify…) or to evade a site's paywall. Downloading may still be restricted by a site's terms of service and local copyright law — when a request is plainly about piracy, say so and stop.\n\n## Install\n\n```bash\nbrew install yt-dlp        # macOS\npipx install yt-dlp        # any platform\nbrew install ffmpeg        # strongly recommended — merging, mp3 extraction, clipping\n```\n\nBinaries for other setups: [yt-dlp releases](https:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp\u002Freleases\u002Flatest). For full YouTube support yt-dlp also wants a JavaScript runtime (deno recommended) — see the [EJS wiki](https:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp\u002Fwiki\u002FEJS). Extractors break when sites change; a failing download is often fixed by updating: `brew upgrade yt-dlp` or `pipx upgrade yt-dlp`.\n\n## Parameters\n\n| Flag | Default | Effect |\n|------|---------|--------|\n| `-a` | off | Audio only, mp3 (yt-dlp preset `-t mp3`; needs ffmpeg; rejects the video flags `-r`\u002F`-b`) |\n| `-b` | off | Best native quality — skip the mp4 compatibility preset |\n| `-p` | off | Full playlist into a `\u003Cplaylist title>\u002F` subfolder, files named `NNN - title [id].ext` (default: single video) |\n| `-i` | off | Inspect only — list available formats, no download; wins over the download flags |\n| `-c A-B` | — | Clip a time range, e.g. `-c 10:15-12:30` (needs ffmpeg) |\n| `-u \u003Clangs>` | — | Subtitles as sidecar files, e.g. `-u \"en.*,fr\"` (includes auto-generated) |\n| `-r \u003Cheight>` | — | Cap resolution, e.g. `-r 1080` |\n| `-d \u003Cdir>` | convention path | Destination directory |\n\nEverything after the URL passes to yt-dlp verbatim — the escape hatch to the full CLI (see Recipes).\n\nDefault download: `-t mp4` preset — h264\u002Faac preferred, remuxed to mp4, plays everywhere. `-b` keeps yt-dlp's native best (often webm\u002Fmkv, higher fidelity, less compatible).\n\n## Workflow\n\n1. Resolve the media URL from arguments or unambiguous session context. Ask only when it is missing or ambiguous.\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\u002Fdownload-media.sh -a 'https:\u002F\u002Fexample.com\u002Fwatch?v=123&list=456'\n   ```\n\n   Parse arguments as data and quote each URL, path and flag value separately. Never splice raw `$ARGUMENTS` into shell code or use `eval`; URL metacharacters such as `&` must remain literal.\n\n3. The script emits `RESULT: key=value` lines — one `path` per downloaded file, then `files`, `dest`, `slug` (order not guaranteed; parse by key). With `-i` it prints yt-dlp's format table instead.\n4. Parse the `RESULT:` lines and produce the report below.\n5. `ERR: yt-dlp not installed` (exit 127) or `ERR: -a and -c need ffmpeg` (exit 3) → print the matching command from `## Install` and stop. Never auto-install on the user's behalf.\n6. Any other `ERR:` (exit 2 — missing or non-URL input, unknown flag, missing flag value, invalid `-r`, conflicting flags) → relay the message verbatim and stop. A non-zero exit *with* `RESULT:` lines means a partial playlist success — report the downloaded files and the failure. A yt-dlp extraction failure → surface its stderr and suggest updating yt-dlp first (see Install).\n\n## Output\n\n```\ndownloaded: \u003Cn> file(s) → \u003Cdest>\n  \u003Cpath>            # one line per file\n```\n\nSubtitle sidecars (`-u`) sit next to the media file but are not listed in `RESULT:` lines — mention they are in `dest`.\n\n## Examples\n\n```bash\n\u002Fdownload-media https:\u002F\u002Fyoutu.be\u002FdQw4w9WgXcQ                 # video, mp4, best compatible\n\u002Fdownload-media -a https:\u002F\u002Fyoutu.be\u002FdQw4w9WgXcQ              # mp3\n\u002Fdownload-media -r 1080 \u003Curl>                                 # cap at 1080p\n\u002Fdownload-media -p \u003Cplaylist-url>                             # whole playlist\n\u002Fdownload-media -c 10:15-12:30 \u003Curl>                          # clip a segment\n\u002Fdownload-media -u \"en.*\" \u003Curl>                               # video + English subtitles\n\u002Fdownload-media -i \u003Curl>                                      # list formats, download nothing\n\u002Fdownload-media -d ~\u002FDownloads \u003Curl>                          # custom destination\n\u002Fdownload-media \u003Curl> --embed-thumbnail --embed-metadata      # passthrough after the URL\n```\n\n## Recipes — passthrough after the URL\n\n| Intent | Append after the URL |\n|--------|---------------------|\n| Logged-in \u002F member content | `--cookies-from-browser firefox` (or `chrome`, `safari`…) |\n| Strip sponsor segments | `--sponsorblock-remove sponsor` (needs ffmpeg) |\n| Incremental playlist sync | `--download-archive \u003Cdir>\u002Farchive.txt` |\n| Split by chapters | `--split-chapters` |\n| Embed thumbnail + metadata | `--embed-thumbnail --embed-metadata` |\n| Only playlist items 3–7 | `-I 3:7` (with `-p`) |\n| Frame-accurate clip cuts | `--force-keyframes-at-cuts` (with `-c`; slow, re-encodes) |\n| Gentle on rate limits | `-t sleep` (preset: spaced requests) |\n| Site needs TLS impersonation | `--extractor-args` per site, or install `curl_cffi` |\n\nCompose other yt-dlp flags the same way when an intent is not covered — the full option surface is `yt-dlp --help`.\n\n## Notes\n\n- **Final paths are captured, not guessed** — the script uses `--print-to-file after_move:filepath` so the reported paths are the real ones after merge\u002Fremux (`--print` would silence download progress).\n- **Playlist URLs holding a `v=` too** (watch-page URLs) download the single video by default; `-p` switches to the whole playlist.\n- **Unavailable playlist entries don't lose the run** — yt-dlp skips them and exits non-zero; the script still reports every downloaded file, then propagates the exit code.\n- **`-c` takes a time range only** (`START-END`, `HH:MM:SS` or seconds). Chapter-regex sections go through passthrough: `--download-sections \"intro\"`.\n- **Custom `-o` output templates** passed through work, but an absolute `-o` makes yt-dlp ignore the destination dir (`-P`) — prefer `-d` for relocation.\n- **No silent overwrites** — yt-dlp skips already-downloaded files by default and the slug-namespaced destination keeps runs predictable.\n\n## Why the wrapper\n\n`yt-dlp` is already a superb CLI; this skill exists to (a) put downloads under the repo's global output convention with the final paths reported deterministically, (b) translate \"get me the audio\" into the right preset without the user remembering `-t mp3` vs `-x --audio-format`, and (c) keep the full flag surface reachable through verbatim passthrough instead of re-wrapping ~200 options.\n","# Download Media\n\nDownload video or audio from any [yt-dlp-supported site](https:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp\u002Fblob\u002Fmaster\u002Fsupportedsites.md) using the [`yt-dlp`](https:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp) CLI. The skill validates the input, composes the right flags for the intent, downloads under `~\u002F.agents\u002Foutput\u002F\u003Cproject>\u002Fdownload-media\u002F\u003Cslug>\u002F` (or a `-d` destination), and reports the final file paths — fully expanded, no tilde, no magic.\n\nThe deterministic work — install checks, slug derivation, destination, flag composition, final-path capture — happens in `scripts\u002Fdownload-media.sh`. The skill parses `$ARGUMENTS`, hands them to the script, and turns the script's `RESULT:` lines into a human report.\n\n## Scope\n\nPersonal and authorized use: public content, the user's own uploads, Creative Commons and licensed material. yt-dlp cannot bypass DRM and this skill never attempts to; decline requests to rip paid streaming catalogs (Netflix, Disney+, Spotify…) or to evade a site's paywall. Downloading may still be restricted by a site's terms of service and local copyright law — when a request is plainly about piracy, say so and stop.\n\n## Install\n\n```bash\nbrew install yt-dlp        # macOS\npipx install yt-dlp        # any platform\nbrew install ffmpeg        # strongly recommended — merging, mp3 extraction, clipping\n```\n\nBinaries for other setups: [yt-dlp releases](https:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp\u002Freleases\u002Flatest). For full YouTube support yt-dlp also wants a JavaScript runtime (deno recommended) — see the [EJS wiki](https:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp\u002Fwiki\u002FEJS). Extractors break when sites change; a failing download is often fixed by updating: `brew upgrade yt-dlp` or `pipx upgrade yt-dlp`.\n\n## Parameters\n\n| Flag | Default | Effect |\n|------|---------|--------|\n| `-a` | off | Audio only, mp3 (yt-dlp preset `-t mp3`; needs ffmpeg; rejects the video flags `-r`\u002F`-b`) |\n| `-b` | off | Best native quality — skip the mp4 compatibility preset |\n| `-p` | off | Full playlist into a `\u003Cplaylist title>\u002F` subfolder, files named `NNN - title [id].ext` (default: single video) |\n| `-i` | off | Inspect only — list available formats, no download; wins over the download flags |\n| `-c A-B` | — | Clip a time range, e.g. `-c 10:15-12:30` (needs ffmpeg) |\n| `-u \u003Clangs>` | — | Subtitles as sidecar files, e.g. `-u \"en.*,fr\"` (includes auto-generated) |\n| `-r \u003Cheight>` | — | Cap resolution, e.g. `-r 1080` |\n| `-d \u003Cdir>` | convention path | Destination directory |\n\nEverything after the URL passes to yt-dlp verbatim — the escape hatch to the full CLI (see Recipes).\n\nDefault download: `-t mp4` preset — h264\u002Faac preferred, remuxed to mp4, plays everywhere. `-b` keeps yt-dlp's native best (often webm\u002Fmkv, higher fidelity, less compatible).\n\n## Workflow\n\n1. Resolve the media URL from arguments or unambiguous session context. Ask only when it is missing or ambiguous.\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 \"$SKILL_DIR\"\u002Fscripts\u002Fdownload-media.sh -a 'https:\u002F\u002Fexample.com\u002Fwatch?v=123&list=456'\n   ```\n\n   Parse arguments as data and quote each URL, path and flag value separately. Never splice raw `$ARGUMENTS` into shell code or use `eval`; URL metacharacters such as `&` must remain literal.\n\n3. The script emits `RESULT: key=value` lines — one `path` per downloaded file, then `files`, `dest`, `slug` (order not guaranteed; parse by key). With `-i` it prints yt-dlp's format table instead.\n4. Parse the `RESULT:` lines and produce the report below.\n5. `ERR: yt-dlp not installed` (exit 127) or `ERR: -a and -c need ffmpeg` (exit 3) → print the matching command from `## Install` and stop. Never auto-install on the user's behalf.\n6. Any other `ERR:` (exit 2 — missing or non-URL input, unknown flag, missing flag value, invalid `-r`, conflicting flags) → relay the message verbatim and stop. A non-zero exit *with* `RESULT:` lines means a partial playlist success — report the downloaded files and the failure. A yt-dlp extraction failure → surface its stderr and suggest updating yt-dlp first (see Install).\n\n## Output\n\n```\ndownloaded: \u003Cn> file(s) → \u003Cdest>\n  \u003Cpath>            # one line per file\n```\n\nSubtitle sidecars (`-u`) sit next to the media file but are not listed in `RESULT:` lines — mention they are in `dest`.\n\n## Examples\n\n```bash\n\u002Fdownload-media https:\u002F\u002Fyoutu.be\u002FdQw4w9WgXcQ                 # video, mp4, best compatible\n\u002Fdownload-media -a https:\u002F\u002Fyoutu.be\u002FdQw4w9WgXcQ              # mp3\n\u002Fdownload-media -r 1080 \u003Curl>                                 # cap at 1080p\n\u002Fdownload-media -p \u003Cplaylist-url>                             # whole playlist\n\u002Fdownload-media -c 10:15-12:30 \u003Curl>                          # clip a segment\n\u002Fdownload-media -u \"en.*\" \u003Curl>                               # video + English subtitles\n\u002Fdownload-media -i \u003Curl>                                      # list formats, download nothing\n\u002Fdownload-media -d ~\u002FDownloads \u003Curl>                          # custom destination\n\u002Fdownload-media \u003Curl> --embed-thumbnail --embed-metadata      # passthrough after the URL\n```\n\n## Recipes — passthrough after the URL\n\n| Intent | Append after the URL |\n|--------|---------------------|\n| Logged-in \u002F member content | `--cookies-from-browser firefox` (or `chrome`, `safari`…) |\n| Strip sponsor segments | `--sponsorblock-remove sponsor` (needs ffmpeg) |\n| Incremental playlist sync | `--download-archive \u003Cdir>\u002Farchive.txt` |\n| Split by chapters | `--split-chapters` |\n| Embed thumbnail + metadata | `--embed-thumbnail --embed-metadata` |\n| Only playlist items 3–7 | `-I 3:7` (with `-p`) |\n| Frame-accurate clip cuts | `--force-keyframes-at-cuts` (with `-c`; slow, re-encodes) |\n| Gentle on rate limits | `-t sleep` (preset: spaced requests) |\n| Site needs TLS impersonation | `--extractor-args` per site, or install `curl_cffi` |\n\nCompose other yt-dlp flags the same way when an intent is not covered — the full option surface is `yt-dlp --help`.\n\n## Notes\n\n- **Final paths are captured, not guessed** — the script uses `--print-to-file after_move:filepath` so the reported paths are the real ones after merge\u002Fremux (`--print` would silence download progress).\n- **Playlist URLs holding a `v=` too** (watch-page URLs) download the single video by default; `-p` switches to the whole playlist.\n- **Unavailable playlist entries don't lose the run** — yt-dlp skips them and exits non-zero; the script still reports every downloaded file, then propagates the exit code.\n- **`-c` takes a time range only** (`START-END`, `HH:MM:SS` or seconds). Chapter-regex sections go through passthrough: `--download-sections \"intro\"`.\n- **Custom `-o` output templates** passed through work, but an absolute `-o` makes yt-dlp ignore the destination dir (`-P`) — prefer `-d` for relocation.\n- **No silent overwrites** — yt-dlp skips already-downloaded files by default and the slug-namespaced destination keeps runs predictable.\n\n## Why the wrapper\n\n`yt-dlp` is already a superb CLI; this skill exists to (a) put downloads under the repo's global output convention with the final paths reported deterministically, (b) translate \"get me the audio\" into the right preset without the user remembering `-t mp3` vs `-x --audio-format`, and (c) keep the full flag surface reachable through verbatim passthrough instead of re-wrapping ~200 options.\n",{"name":5,"license":15,"metadata":52,"description":7,"when_to_use":54,"allowed-tools":55,"argument-hint":56,"compatibility":57},{"author":9,"sources":53},"github.com\u002Fyt-dlp\u002Fyt-dlp","When the user has a media URL and wants the file on disk — video, audio-only, playlist, clip, or subtitles. Keywords — download video, yt-dlp, youtube, save video, extract audio, mp3, rip, playlist, clip, subtitles, 1080p. Skip when the user wants the transcript or text content (\u002Fmarkitdown), wants to loop or re-encode a local file (\u002Fvideo-loop, \u002Faudio-loop), or targets DRM-protected streaming services (Netflix, Disney+, Spotify…) — yt-dlp does not bypass DRM and neither does this skill.","Bash(bash *) Bash(yt-dlp *) Bash(command *) Read","[-a] [-b] [-p] [-i] [-c A-B] [-u langs] [-r height] [-d dir] \u003Curl> [yt-dlp args]","Requires bash and an installed yt-dlp CLI. FFmpeg is required for audio extraction, clipping and applicable merges; some extractors require additional documented runtimes or authentication.","main","5ff268fdc77fdf345ffe3ba808e74c82023839f8","skills\u002Fdownload-media",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":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add coroboros\u002Fagent-skills --skill download-media",{"tool":74,"command":75},"bunx","bunx skills add coroboros\u002Fagent-skills --skill download-media",{"tool":77,"command":78},"pnpm","pnpm dlx skills add coroboros\u002Fagent-skills --skill download-media","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdownload-media\u002FSKILL.md",true,[82],{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fdownload-media.sh","SCRIPT","脚本",5044,"https:\u002F\u002Fgithub.com\u002Fcoroboros\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdownload-media\u002Fscripts\u002Fdownload-media.sh",[89,103,113,146,168,191],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":47},"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",[],[91,96,97,98,99,100,101,102],"fixture skill","repo","classifier","for","kind","tests","fixture",{"skillNo":104,"name":91,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":47},"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",[],[91,109,110,99,111,112,102],"detection","tooling","compound","npm",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":128,"publishedAt":47},"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",[119,122,123],{"categoryNo":120,"categoryName":121,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[129,130,131,132,133,38,39,134,135,136,137,138,139,140,141,142,143,144,33,145],"clear","README","write clear readme","write","writing","project","creation","ls","access","verification","references","libraries","project readme","browser","code","preview","markdown preview",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":153,"publishedAt":47},"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",[152],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[46,36,154,155,33,156,157,138,158,159,160,161,162,163,164,165,166,44,167,35],"video loop","hero","architecture","command","loops","optimize","transition","work","inspection","continuity","fix","end","crossfade","processing",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":47},"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",[174],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[170,176,177,134,178,165,179,180,181,182,183,184,185,186,187,35,188,189,38,190],"ponytail","select","model","apex","capability","context","Tools","at","result","self","review","workflow","forge","host","delegation",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":201,"publishedAt":47},"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",[197,198,199,200],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":120,"categoryName":121,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},[202,203,204,205,206,207,208,209,210,211,212,213,188,36,133,189,214,39,215,44],"produce","suno","suno produce","lyric","website","mv","artifact","track","create","guides","information","song","question","Meta"]