[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M757YD32PVG9NQANSTAXF8F0":3,"skill-same:01M757YD32PVG9NQANSTAXF8F0":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M757YD32PVG9NQANSTAXF8F0","x-twitter",null,"Fetch X\u002FTwitter posts, threads, replies, profiles, and search results via the FxTwitter (FxEmbed) API and mirror domains. Use whenever an x.com or twitter.com link appears, or the user asks about X\u002FTwitter content. Direct scraping of x.com hits login walls and blocks.","gpdir16\u002FtabyAgent","gpdir16","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128959567?v=4","01M757XK49S9TP17F7GERWBRDT","Jaeone Jang","01M757XK4XDT7BT2PAW31DHDYG",18,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent\u002Fblob\u002Fmain\u002Fcodes\u002Fskills\u002Fx-twitter\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: x-twitter\ndescription: Fetch X\u002FTwitter posts, threads, replies, profiles, and search results via the FxTwitter (FxEmbed) API and mirror domains. Use whenever an x.com or twitter.com link appears, or the user asks about X\u002FTwitter content. Direct scraping of x.com hits login walls and blocks.\n---\n\n# X \u002F Twitter access\n\nDirect scraping of `x.com` \u002F `twitter.com` fails (login walls, blocks). Two working paths, in order:\n\n1. **FxTwitter REST API** (preferred). Unofficial JSON API, no auth, read-only. Base: `https:\u002F\u002Fapi.fxtwitter.com`\n2. **Mirror domains.** For full-page rendering or when the API is down\n\nCall endpoints with `terminal_run` + `curl` (or Python `httpx`\u002F`urllib`).\n\n## API rules\n\n- GET only. No API key, no login, no cookies. Guest public data only.\n- Always send a `User-Agent` (e.g. `-A \"tabyAgent\u002F1.0\"`). Empty UA gets blocked.\n- Timeout 20s. Retry only on `429` \u002F `502` \u002F `503`, max 3 tries, backoff 1s, 2s, 4s.\n- **Every response JSON has a `code` field. Check `code === 200`, not just the HTTP status.** HTTP 200 with `code !== 200` is a failure.\n- ~1000 req\u002Fmin per IP on paper; search gets throttled much earlier.\n- Public posts only. Protected\u002Fsuspended accounts and deleted posts return 401\u002F404.\n- `fxtwitter.com` the website is deprecated\u002Fgone; the `api.fxtwitter.com` subdomain still works.\n\n## Extract the tweet id\n\nSupported inputs: bare numeric id, or a status URL on `x.com`, `twitter.com`, `fxtwitter.com`, `fixupx.com`, `twittpr.com`.\n\n```\n(?:x\\.com|twitter\\.com|fxtwitter\\.com|fixupx\\.com|twittpr\\.com)\u002F[^\u002F]+\u002Fstatus\u002F(\\d+)\n```\n\nCapture group 1 is the `tweet_id`. The handle is not needed for lookups.\n\n## Endpoints\n\n| Need                                | Call                                                      |\n| ----------------------------------- | --------------------------------------------------------- |\n| Single post + metrics               | `GET \u002F2\u002Fstatus\u002F{id}`                                      |\n| Author's thread (upward self-chain) | `GET \u002F2\u002Fthread\u002F{id}`                                      |\n| Thread + other users' replies       | `GET \u002F2\u002Fconversation\u002F{id}?ranking_mode=likes\\|recency`    |\n| Keyword search                      | `GET \u002F2\u002Fsearch?q=...&feed=latest\\|top\\|media&count=1-100` |\n| Profile                             | `GET \u002F2\u002Fprofile\u002F{handle}`, `handle` or `id:\u003Cnumeric>`     |\n| User timeline                       | `GET \u002F2\u002Fprofile\u002F{handle}\u002Fstatuses?count=&cursor=`         |\n| User media only                     | `GET \u002F2\u002Fprofile\u002F{handle}\u002Fmedia`                           |\n| Quotes \u002F reposting users            | `GET \u002F2\u002Fstatus\u002F{id}\u002Fquotes` · `\u002F2\u002Fstatus\u002F{id}\u002Freposts`    |\n\nCommon query params: `lang` (translation target, e.g. `ko`), `cursor` (from prior `cursor.bottom`), `count` (1–100), `about_account=1`.\n\n```bash\ncurl -sS -A \"tabyAgent\u002F1.0\" \"https:\u002F\u002Fapi.fxtwitter.com\u002F2\u002Fstatus\u002F1548602399862013953?lang=ko\"\ncurl -sS -A \"tabyAgent\u002F1.0\" \"https:\u002F\u002Fapi.fxtwitter.com\u002F2\u002Fsearch?q=from%3Aelonmusk&feed=latest&count=20\"\ncurl -sS -A \"tabyAgent\u002F1.0\" \"https:\u002F\u002Fapi.fxtwitter.com\u002F2\u002Fconversation\u002F1548602399862013953?ranking_mode=recency\"\ncurl -sS -A \"tabyAgent\u002F1.0\" \"https:\u002F\u002Fapi.fxtwitter.com\u002F2\u002Fprofile\u002Felonmusk\"\n```\n\nSuccess is `code: 200` plus the root key (`status` \u002F `results` \u002F `user`).\n\n### Useful `status` fields\n\n`id`, `url`, `text`, `created_at`, `created_timestamp`, `likes`, `reposts`, `quotes`, `replies`, `views` (may be null), `lang`, `author.{name,screen_name,avatar_url}`, `replying_to`, `quote` (or tombstone), `poll`, `media.photos[]`, `media.videos[]`, `article` (X Articles).\n\n### Pagination & search notes\n\n- If `cursor.bottom` is present, request the same path with `?cursor=`. If it is null or empty, you are done. Keep to ~5 pages max.\n- `\u002F2\u002Fconversation` page 2+ can return HTTP 404. Known bug; return what was collected and stop.\n- Search `q` accepts X web operators (`from:`, `#tag`, `\"exact phrase\"`, `min_faves:`, `since:`). Best-effort, not guaranteed.\n- Search is recent\u002Fpopular results, **not** a full archive. It fails more than single-post lookups: on `502` \u002F `search_unavailable` say the search upstream failed, and fall back to `\u002F2\u002Fstatus\u002F{id}` if a URL\u002Fid is known.\n- User timeline extras: `with_replies` (truthy), `groupthreads`, `since` (unix ts; 204 = nothing new).\n- Default to one page (~20 items); fetch more only if the user asks.\n\n## Routing\n\n| User input                         | Endpoint                                                          |\n| ---------------------------------- | ----------------------------------------------------------------- |\n| URL or numeric id                  | `\u002F2\u002Fstatus\u002F{id}`                                                  |\n| \"thread \u002F 타래 \u002F 스레드\"           | `\u002F2\u002Fthread\u002F{id}`, then `\u002F2\u002Fconversation` if replies needed        |\n| \"replies \u002F 답글 \u002F 댓글\"            | `\u002F2\u002Fconversation\u002F{id}` (`ranking_mode=recency` for chronological) |\n| \"search \u002F 찾아 \u002F 최근글\" + keyword | `\u002F2\u002Fsearch`                                                       |\n| `@handle` or \"profile \u002F 프로필\"    | `\u002F2\u002Fprofile\u002F{handle}`                                             |\n| \"their posts \u002F 그 계정 글\"         | `\u002F2\u002Fprofile\u002F{handle}\u002Fstatuses`                                    |\n\n## Mirror domains (fallback \u002F page view)\n\nWhen the API can't help (need the rendered page, media embed, or API down), rewrite the host instead of browser-automating x.com:\n\n- Replace `x.com` with `fixupx.com` (or `xfixup.com`)\n- Replace `twitter.com` with `twittpr.com`\n- Further fallbacks: `fixvx.com`, `yt-dlp`, or the browser tools on a mirror page. Try the next when one 404s\u002Fblocks.\n\n## Don'ts\n\n- Never mix official `api.x.com` schemas with this API.\n- Never mix the legacy `\u002F{handle}\u002Fstatus\u002F{id}` form (root key `tweet`) with v2 `\u002F2\u002F...` (root key `status`). Use v2 only.\n- No bulk search crawling; no cookies or account credentials. This API only serves guest-public data.\n- Don't report success on `code !== 200` even when HTTP is 200.\n\n## Error mapping\n\n| code\u002FHTTP   | meaning               |\n| ----------- | --------------------- |\n| 400         | bad request           |\n| 401         | private or restricted |\n| 404         | not found             |\n| 429         | rate limited          |\n| 500\u002F502\u002F503 | upstream error        |\n\n## Limits: relay honestly to the user\n\n- Unofficial proxy; can break or shut down without notice.\n- Search is not a full archive; replies may be partial.\n- Protected accounts and deleted posts are unreachable.\n","# X \u002F Twitter access\n\nDirect scraping of `x.com` \u002F `twitter.com` fails (login walls, blocks). Two working paths, in order:\n\n1. **FxTwitter REST API** (preferred). Unofficial JSON API, no auth, read-only. Base: `https:\u002F\u002Fapi.fxtwitter.com`\n2. **Mirror domains.** For full-page rendering or when the API is down\n\nCall endpoints with `terminal_run` + `curl` (or Python `httpx`\u002F`urllib`).\n\n## API rules\n\n- GET only. No API key, no login, no cookies. Guest public data only.\n- Always send a `User-Agent` (e.g. `-A \"tabyAgent\u002F1.0\"`). Empty UA gets blocked.\n- Timeout 20s. Retry only on `429` \u002F `502` \u002F `503`, max 3 tries, backoff 1s, 2s, 4s.\n- **Every response JSON has a `code` field. Check `code === 200`, not just the HTTP status.** HTTP 200 with `code !== 200` is a failure.\n- ~1000 req\u002Fmin per IP on paper; search gets throttled much earlier.\n- Public posts only. Protected\u002Fsuspended accounts and deleted posts return 401\u002F404.\n- `fxtwitter.com` the website is deprecated\u002Fgone; the `api.fxtwitter.com` subdomain still works.\n\n## Extract the tweet id\n\nSupported inputs: bare numeric id, or a status URL on `x.com`, `twitter.com`, `fxtwitter.com`, `fixupx.com`, `twittpr.com`.\n\n```\n(?:x\\.com|twitter\\.com|fxtwitter\\.com|fixupx\\.com|twittpr\\.com)\u002F[^\u002F]+\u002Fstatus\u002F(\\d+)\n```\n\nCapture group 1 is the `tweet_id`. The handle is not needed for lookups.\n\n## Endpoints\n\n| Need                                | Call                                                      |\n| ----------------------------------- | --------------------------------------------------------- |\n| Single post + metrics               | `GET \u002F2\u002Fstatus\u002F{id}`                                      |\n| Author's thread (upward self-chain) | `GET \u002F2\u002Fthread\u002F{id}`                                      |\n| Thread + other users' replies       | `GET \u002F2\u002Fconversation\u002F{id}?ranking_mode=likes\\|recency`    |\n| Keyword search                      | `GET \u002F2\u002Fsearch?q=...&feed=latest\\|top\\|media&count=1-100` |\n| Profile                             | `GET \u002F2\u002Fprofile\u002F{handle}`, `handle` or `id:\u003Cnumeric>`     |\n| User timeline                       | `GET \u002F2\u002Fprofile\u002F{handle}\u002Fstatuses?count=&cursor=`         |\n| User media only                     | `GET \u002F2\u002Fprofile\u002F{handle}\u002Fmedia`                           |\n| Quotes \u002F reposting users            | `GET \u002F2\u002Fstatus\u002F{id}\u002Fquotes` · `\u002F2\u002Fstatus\u002F{id}\u002Freposts`    |\n\nCommon query params: `lang` (translation target, e.g. `ko`), `cursor` (from prior `cursor.bottom`), `count` (1–100), `about_account=1`.\n\n```bash\ncurl -sS -A \"tabyAgent\u002F1.0\" \"https:\u002F\u002Fapi.fxtwitter.com\u002F2\u002Fstatus\u002F1548602399862013953?lang=ko\"\ncurl -sS -A \"tabyAgent\u002F1.0\" \"https:\u002F\u002Fapi.fxtwitter.com\u002F2\u002Fsearch?q=from%3Aelonmusk&feed=latest&count=20\"\ncurl -sS -A \"tabyAgent\u002F1.0\" \"https:\u002F\u002Fapi.fxtwitter.com\u002F2\u002Fconversation\u002F1548602399862013953?ranking_mode=recency\"\ncurl -sS -A \"tabyAgent\u002F1.0\" \"https:\u002F\u002Fapi.fxtwitter.com\u002F2\u002Fprofile\u002Felonmusk\"\n```\n\nSuccess is `code: 200` plus the root key (`status` \u002F `results` \u002F `user`).\n\n### Useful `status` fields\n\n`id`, `url`, `text`, `created_at`, `created_timestamp`, `likes`, `reposts`, `quotes`, `replies`, `views` (may be null), `lang`, `author.{name,screen_name,avatar_url}`, `replying_to`, `quote` (or tombstone), `poll`, `media.photos[]`, `media.videos[]`, `article` (X Articles).\n\n### Pagination & search notes\n\n- If `cursor.bottom` is present, request the same path with `?cursor=`. If it is null or empty, you are done. Keep to ~5 pages max.\n- `\u002F2\u002Fconversation` page 2+ can return HTTP 404. Known bug; return what was collected and stop.\n- Search `q` accepts X web operators (`from:`, `#tag`, `\"exact phrase\"`, `min_faves:`, `since:`). Best-effort, not guaranteed.\n- Search is recent\u002Fpopular results, **not** a full archive. It fails more than single-post lookups: on `502` \u002F `search_unavailable` say the search upstream failed, and fall back to `\u002F2\u002Fstatus\u002F{id}` if a URL\u002Fid is known.\n- User timeline extras: `with_replies` (truthy), `groupthreads`, `since` (unix ts; 204 = nothing new).\n- Default to one page (~20 items); fetch more only if the user asks.\n\n## Routing\n\n| User input                         | Endpoint                                                          |\n| ---------------------------------- | ----------------------------------------------------------------- |\n| URL or numeric id                  | `\u002F2\u002Fstatus\u002F{id}`                                                  |\n| \"thread \u002F 타래 \u002F 스레드\"           | `\u002F2\u002Fthread\u002F{id}`, then `\u002F2\u002Fconversation` if replies needed        |\n| \"replies \u002F 답글 \u002F 댓글\"            | `\u002F2\u002Fconversation\u002F{id}` (`ranking_mode=recency` for chronological) |\n| \"search \u002F 찾아 \u002F 최근글\" + keyword | `\u002F2\u002Fsearch`                                                       |\n| `@handle` or \"profile \u002F 프로필\"    | `\u002F2\u002Fprofile\u002F{handle}`                                             |\n| \"their posts \u002F 그 계정 글\"         | `\u002F2\u002Fprofile\u002F{handle}\u002Fstatuses`                                    |\n\n## Mirror domains (fallback \u002F page view)\n\nWhen the API can't help (need the rendered page, media embed, or API down), rewrite the host instead of browser-automating x.com:\n\n- Replace `x.com` with `fixupx.com` (or `xfixup.com`)\n- Replace `twitter.com` with `twittpr.com`\n- Further fallbacks: `fixvx.com`, `yt-dlp`, or the browser tools on a mirror page. Try the next when one 404s\u002Fblocks.\n\n## Don'ts\n\n- Never mix official `api.x.com` schemas with this API.\n- Never mix the legacy `\u002F{handle}\u002Fstatus\u002F{id}` form (root key `tweet`) with v2 `\u002F2\u002F...` (root key `status`). Use v2 only.\n- No bulk search crawling; no cookies or account credentials. This API only serves guest-public data.\n- Don't report success on `code !== 200` even when HTTP is 200.\n\n## Error mapping\n\n| code\u002FHTTP   | meaning               |\n| ----------- | --------------------- |\n| 400         | bad request           |\n| 401         | private or restricted |\n| 404         | not found             |\n| 429         | rate limited          |\n| 500\u002F502\u002F503 | upstream error        |\n\n## Limits: relay honestly to the user\n\n- Unofficial proxy; can break or shut down without notice.\n- Search is not a full archive; replies may be partial.\n- Protected accounts and deleted posts are unreachable.\n",{"name":5,"description":7},"main","d351a29e6653b9f603e1fc202e15d3a2665557a1","codes\u002Fskills\u002Fx-twitter",4,"https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent","https:\u002F\u002Fgithub.com\u002Fgpdir16","https:\u002F\u002Fgpdir16.com","2026-11-04 23:10:36",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add gpdir16\u002FtabyAgent --skill x-twitter",{"tool":38,"command":39},"bunx","bunx skills add gpdir16\u002FtabyAgent --skill x-twitter",{"tool":41,"command":42},"pnpm","pnpm dlx skills add gpdir16\u002FtabyAgent --skill x-twitter","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent\u002Fblob\u002Fmain\u002Fcodes\u002Fskills\u002Fx-twitter\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M757YFQ1XVSMJW55SR30V9SV","xvfb","Linux GUI app automation on a virtual X display. Launch non-browser Linux GUI apps in Docker, see screenshots, and interact by pixel coordinates.","https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent\u002Fblob\u002Fmain\u002Fcodes\u002Fskills\u002Fxvfb\u002FSKILL.md",[],[],{"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":19},"01M757YA0DB791SAN1PS6J2CY1","visualization","Deploy interactive HTML visualizations (quiz, what-if explorer, decision tree, or custom) to a live URL via Cloudflare Workers. Use when the user needs an interactive, clickable visual aid such as choices, buttons, sliders, causal \"if this then that\" explorers, or step-by-step decision flows. Not for plain charts or static images.","https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent\u002Fblob\u002Fmain\u002Fcodes\u002Fskills\u002Fvisualization\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M757Y5NE9FYVFDYGBYT98V4M","todos","The shared todo store for the user's tasks (suggest\u002Fapprove only) and your own scheduled automations. Use for tasks, reminders, recurring checks, or \"tell me when X\".","https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent\u002Fblob\u002Fmain\u002Fcodes\u002Fskills\u002Ftodos\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M757Y2HQA29S7E0RKBPJJKP5","skill-authoring","Create or update agent skills under the user skills directory. Use when a non-trivial, repeatable workflow just succeeded and should be captured for future sessions, or when the user asks to write or fix a skill.","https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent\u002Fblob\u002Fmain\u002Fcodes\u002Fskills\u002Fskill-authoring\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M757XZ2DV5TPRPNKH6BG2GSQ","privacy","Privacy tools and alternatives to mainstream services with verified details on licensing, ads, and pricing.","https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent\u002Fblob\u002Fmain\u002Fcodes\u002Fskills\u002Fprivacy\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M757XW3AY45TVFQYC4PXZDK6","k-school","(한국 사용자 전용) 학교알리미와 컴시간을 이용하여 전국 학교 시간표와 급식을 가져옵니다. 이 스킬에는 브라우저를 이용한 웹 크롤링과 비공식 API 호출 방법 및 컴시간 난독화 우회 방법이 모두 포함되어 있습니다.","https:\u002F\u002Fgithub.com\u002Fgpdir16\u002FtabyAgent\u002Fblob\u002Fmain\u002Fcodes\u002Fskills\u002Fk-school\u002FSKILL.md",[],[]]