[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJ22ACA9P40FSNNYS7WVV0":3,"skill-same:01M6MJ22ACA9P40FSNNYS7WVV0":71},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6MJ22ACA9P40FSNNYS7WVV0","automating-the-browser",null,"Use when extracting a page needs scripted interaction first — click, type, press a key, scroll, wait, screenshot, or run JS before capturing the DOM. Covers `kreuzcrawl interact \u003Curl> --actions` with the real action schema, result shape, limits, and external-CDP options.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzcrawl\u002Fskills\u002Fautomating-the-browser\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"browser","automating the browser","when","run","limits","kreuzcrawl","result","dom","action","URL","extracting","with","wait","interaction","click","type","options","cdp","schema","use","page","actions","screenshot","2026-11-10 10:12:30",false,"---\nname: automating-the-browser\ndescription: >-\n  Use when extracting a page needs scripted interaction first — click, type,\n  press a key, scroll, wait, screenshot, or run JS before capturing the DOM.\n  Covers `kreuzcrawl interact \u003Curl> --actions` with the real action schema,\n  result shape, limits, and external-CDP options.\n---\n\n# Automating the browser\n\n`kreuzcrawl interact \u003Curl> --actions '[...]'` drives a real headless browser\nthrough an ordered list of actions, then captures the resulting page. Reach for\nit when a static scrape is not enough: the content lives behind a \"Load more\"\nbutton, an infinite scroll, a form submission, or JS that only runs on\ninteraction.\n\n## Quick recipe\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com \\\n  --actions '[{\"type\":\"click\",\"selector\":\"#load-more\"},\n              {\"type\":\"wait\",\"milliseconds\":500},\n              {\"type\":\"scrape\"}]'\n```\n\nActions run in order. The result wraps the final page state under\n`interaction` (see Output below).\n\n## Flag surface\n\n| Flag                 | Default | Purpose                                                      |\n| -------------------- | ------- | ------------------------------------------------------------ |\n| `--actions`          | —       | Required. JSON array of action objects (see below).          |\n| `--format`           | `json`  | `json` (full result) or `markdown` (final HTML only).        |\n| `--timeout`          | `30000` | Per-request timeout in ms.                                   |\n| `--browser-mode`     | `auto`  | `auto`, `always`, `never`. Interaction needs a browser.      |\n| `--browser-endpoint` | —       | External CDP `ws:\u002F\u002F` or `wss:\u002F\u002F` URL.                        |\n| `--config`           | —       | Inline JSON or `@file.json` for the full `CrawlConfig`.      |\n\nThere is no `--respect-robots-txt` flag on `interact`; it targets the one URL\nyou point it at.\n\n## Action schema\n\nEach action is a JSON object tagged by `type` (camelCase). Unknown fields are\nrejected, so match the shapes exactly:\n\n| `type`        | Fields                                                          | Notes                                                            |\n| ------------- | -------------------------------------------------------------- | --------------------------------------------------------------- |\n| `click`       | `selector`                                                     | Click the element matching the CSS selector.                    |\n| `type`        | `selector`, `text`                                             | Type `text` into the input matching `selector`.                 |\n| `press`       | `key`                                                          | Press a key, e.g. `\"Enter\"`, `\"Tab\"`, `\"Escape\"`.               |\n| `scroll`      | `direction` (`\"up\"`\u002F`\"down\"`), `selector?`, `amount?`         | Scroll the page, or a scrollable element if `selector` is set.  |\n| `wait`        | `milliseconds?`, `selector?`                                   | Wait a fixed time, or until `selector` appears (`selector` wins). |\n| `screenshot`  | `fullPage?`                                                    | Capture the viewport, or the full scrollable page if `true`.    |\n| `executeJs`   | `script`                                                       | Run arbitrary JS in the page context. Trusted scripts only.     |\n| `scrape`      | —                                                             | Capture the current page HTML into the result.                  |\n\nThere is no `select` action and no `wait_for_selector` action: to wait for an\nelement, use `wait` with a `selector` field. Scroll direction is `up` or\n`down` only.\n\n### Limits (enforced — exceeding them errors)\n\n- Max 100 actions per call.\n- Single `wait`: max 300000 ms; total wait across all `wait` actions: max 300 s.\n- `selector` max 4096 bytes; `text` and `executeJs` `script` max 1 MB each.\n- `scroll` `amount` max 100000 px (absolute).\n\n## Output\n\n### JSON mode (default)\n\nThe result is wrapped under an `interaction` key. It carries the final page\nHTML (`interaction.final_html`) and a per-action record under\n`interaction.action_results[...]` — including screenshot data and `executeJs`\nreturn values where applicable.\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com \\\n  --actions '[{\"type\":\"type\",\"selector\":\"#q\",\"text\":\"rust\"},\n              {\"type\":\"press\",\"key\":\"Enter\"},\n              {\"type\":\"wait\",\"selector\":\".results\"},\n              {\"type\":\"scrape\"}]' \\\n  --format json | jq '.interaction.final_html | length'\n```\n\n### Markdown mode\n\nPrints `interaction.final_html` directly — the raw final DOM, not converted\nMarkdown. Use JSON mode and feed `final_html` to a scrape step when you need\nclean Markdown.\n\n## Patterns\n\n### Expand lazy content, then capture\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com\u002Ffeed \\\n  --actions '[{\"type\":\"scroll\",\"direction\":\"down\"},\n              {\"type\":\"wait\",\"milliseconds\":800},\n              {\"type\":\"scroll\",\"direction\":\"down\"},\n              {\"type\":\"wait\",\"milliseconds\":800},\n              {\"type\":\"scrape\"}]'\n```\n\n### Capture a full-page screenshot after login\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fapp.example.com \\\n  --actions '[{\"type\":\"type\",\"selector\":\"#email\",\"text\":\"me@example.com\"},\n              {\"type\":\"type\",\"selector\":\"#password\",\"text\":\"...\"},\n              {\"type\":\"click\",\"selector\":\"button[type=submit]\"},\n              {\"type\":\"wait\",\"selector\":\".dashboard\"},\n              {\"type\":\"screenshot\",\"fullPage\":true}]'\n```\n\nNever hardcode credentials — pass them from the environment or a secrets store.\n\n### Point at an external Chrome\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com \\\n  --browser-endpoint ws:\u002F\u002Fbrowser.internal:9222\u002Fdevtools\u002Fbrowser\u002F\u003Cid> \\\n  --actions '[{\"type\":\"click\",\"selector\":\"#go\"},{\"type\":\"scrape\"}]'\n```\n\nSee the `headless-fallback` skill for CDP endpoints, wait strategies, and\npersistent browser profiles set via `--config`.\n\n## When to reach for scrape or crawl instead\n\nIf the page yields its content on a plain fetch (or via `--browser-mode\nalways`) with no clicking or typing, use `kreuzcrawl scrape` — see\n`scraping-html-to-markdown`. Use `interact` only when ordered actions must run\nbefore the content exists.\n","# Automating the browser\n\n`kreuzcrawl interact \u003Curl> --actions '[...]'` drives a real headless browser\nthrough an ordered list of actions, then captures the resulting page. Reach for\nit when a static scrape is not enough: the content lives behind a \"Load more\"\nbutton, an infinite scroll, a form submission, or JS that only runs on\ninteraction.\n\n## Quick recipe\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com \\\n  --actions '[{\"type\":\"click\",\"selector\":\"#load-more\"},\n              {\"type\":\"wait\",\"milliseconds\":500},\n              {\"type\":\"scrape\"}]'\n```\n\nActions run in order. The result wraps the final page state under\n`interaction` (see Output below).\n\n## Flag surface\n\n| Flag                 | Default | Purpose                                                      |\n| -------------------- | ------- | ------------------------------------------------------------ |\n| `--actions`          | —       | Required. JSON array of action objects (see below).          |\n| `--format`           | `json`  | `json` (full result) or `markdown` (final HTML only).        |\n| `--timeout`          | `30000` | Per-request timeout in ms.                                   |\n| `--browser-mode`     | `auto`  | `auto`, `always`, `never`. Interaction needs a browser.      |\n| `--browser-endpoint` | —       | External CDP `ws:\u002F\u002F` or `wss:\u002F\u002F` URL.                        |\n| `--config`           | —       | Inline JSON or `@file.json` for the full `CrawlConfig`.      |\n\nThere is no `--respect-robots-txt` flag on `interact`; it targets the one URL\nyou point it at.\n\n## Action schema\n\nEach action is a JSON object tagged by `type` (camelCase). Unknown fields are\nrejected, so match the shapes exactly:\n\n| `type`        | Fields                                                          | Notes                                                            |\n| ------------- | -------------------------------------------------------------- | --------------------------------------------------------------- |\n| `click`       | `selector`                                                     | Click the element matching the CSS selector.                    |\n| `type`        | `selector`, `text`                                             | Type `text` into the input matching `selector`.                 |\n| `press`       | `key`                                                          | Press a key, e.g. `\"Enter\"`, `\"Tab\"`, `\"Escape\"`.               |\n| `scroll`      | `direction` (`\"up\"`\u002F`\"down\"`), `selector?`, `amount?`         | Scroll the page, or a scrollable element if `selector` is set.  |\n| `wait`        | `milliseconds?`, `selector?`                                   | Wait a fixed time, or until `selector` appears (`selector` wins). |\n| `screenshot`  | `fullPage?`                                                    | Capture the viewport, or the full scrollable page if `true`.    |\n| `executeJs`   | `script`                                                       | Run arbitrary JS in the page context. Trusted scripts only.     |\n| `scrape`      | —                                                             | Capture the current page HTML into the result.                  |\n\nThere is no `select` action and no `wait_for_selector` action: to wait for an\nelement, use `wait` with a `selector` field. Scroll direction is `up` or\n`down` only.\n\n### Limits (enforced — exceeding them errors)\n\n- Max 100 actions per call.\n- Single `wait`: max 300000 ms; total wait across all `wait` actions: max 300 s.\n- `selector` max 4096 bytes; `text` and `executeJs` `script` max 1 MB each.\n- `scroll` `amount` max 100000 px (absolute).\n\n## Output\n\n### JSON mode (default)\n\nThe result is wrapped under an `interaction` key. It carries the final page\nHTML (`interaction.final_html`) and a per-action record under\n`interaction.action_results[...]` — including screenshot data and `executeJs`\nreturn values where applicable.\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com \\\n  --actions '[{\"type\":\"type\",\"selector\":\"#q\",\"text\":\"rust\"},\n              {\"type\":\"press\",\"key\":\"Enter\"},\n              {\"type\":\"wait\",\"selector\":\".results\"},\n              {\"type\":\"scrape\"}]' \\\n  --format json | jq '.interaction.final_html | length'\n```\n\n### Markdown mode\n\nPrints `interaction.final_html` directly — the raw final DOM, not converted\nMarkdown. Use JSON mode and feed `final_html` to a scrape step when you need\nclean Markdown.\n\n## Patterns\n\n### Expand lazy content, then capture\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com\u002Ffeed \\\n  --actions '[{\"type\":\"scroll\",\"direction\":\"down\"},\n              {\"type\":\"wait\",\"milliseconds\":800},\n              {\"type\":\"scroll\",\"direction\":\"down\"},\n              {\"type\":\"wait\",\"milliseconds\":800},\n              {\"type\":\"scrape\"}]'\n```\n\n### Capture a full-page screenshot after login\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fapp.example.com \\\n  --actions '[{\"type\":\"type\",\"selector\":\"#email\",\"text\":\"me@example.com\"},\n              {\"type\":\"type\",\"selector\":\"#password\",\"text\":\"...\"},\n              {\"type\":\"click\",\"selector\":\"button[type=submit]\"},\n              {\"type\":\"wait\",\"selector\":\".dashboard\"},\n              {\"type\":\"screenshot\",\"fullPage\":true}]'\n```\n\nNever hardcode credentials — pass them from the environment or a secrets store.\n\n### Point at an external Chrome\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com \\\n  --browser-endpoint ws:\u002F\u002Fbrowser.internal:9222\u002Fdevtools\u002Fbrowser\u002F\u003Cid> \\\n  --actions '[{\"type\":\"click\",\"selector\":\"#go\"},{\"type\":\"scrape\"}]'\n```\n\nSee the `headless-fallback` skill for CDP endpoints, wait strategies, and\npersistent browser profiles set via `--config`.\n\n## When to reach for scrape or crawl instead\n\nIf the page yields its content on a plain fetch (or via `--browser-mode\nalways`) with no clicking or typing, use `kreuzcrawl scrape` — see\n`scraping-html-to-markdown`. Use `interact` only when ordered actions must run\nbefore the content exists.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzcrawl\u002Fskills\u002Fautomating-the-browser",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill automating-the-browser",{"tool":63,"command":64},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill automating-the-browser",{"tool":66,"command":67},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill automating-the-browser","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzcrawl\u002Fskills\u002Fautomating-the-browser\u002FSKILL.md",true,[],[72,80,87,94,120,144],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":79},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":79},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":79},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":42},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[101,102,103,104,105,106,107,108,109,110,111,21,112,113,114,115,116,117,118,119],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","you","done","reviewer","io","change","cli","merge","past",{"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":126,"publishedAt":42},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[127,128,129,115,30,130,131,132,133,134,135,136,137,138,106,139,140,141,142,143],"deja reflect","reflect","review","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":161,"publishedAt":42},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[150,155,158],{"categoryNo":151,"categoryName":152,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":156,"categoryName":157,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":159,"categoryName":160,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000010","后端与接口",[146,28,162,163,164,165,166,140,167,107,168,169,170,171,21,172,173,174,175,176],"Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]