TikTok user profile video scraper: input a TikTok username → output the user's profile info plus paginated video list with full metadata (engagement stats, music, video meta). Use when user mentions TikTok profile scraping, scrape TikTok user videos, get TikTok creator videos, extract TikTok profile data, TikTok user posts, TikTok account video collection, collect TikTok profile page videos, TikTok creator video list, TikTok creator data, TikTok profile scraper, tiktok user scraper, tiktok creator scraper. Also applies to influencer research, competitor analysis, content archiving for a specific TikTok creator, or extracting all posts from a TikTok account.
npx skills add https://github.com/browser-act/skills --skill tiktok-profile-videos
> TikTok username → user profile info + paginated video list with full metadata
All process output to user (progress updates, process notifications) follows the user's language.
Extract the video list and profile metadata for a given TikTok user using the /api/post/item_list/ endpoint triggered by navigating to their profile page.
https://www.tiktok.comIf browser-act has been confirmed available in the current session → skip this step.
Invoke browser-act via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.
> This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed to the user on the page, never bypassing authentication or access controls. JS code is encapsulated in Python files under the scripts/ directory, invoked via eval "$(python scripts/xxx.py {params})". $(...) is bash syntax; it is recommended to use the bash tool for execution.
/api/post/item_list/ requires TikTok's dynamic signing and the user's secUid (internal ID). Navigate to the profile page — TikTok's JS resolves the secUid and triggers the signed request automatically:
navigate https://www.tiktok.com/@{username}wait stablenetwork requests --type xhr,fetch --filter "post/item_list"network request <id>Endpoint characteristic: URL contains /api/post/item_list/ with secUid={secUid}&cursor=0
Note: The secUid is a long internal identifier (e.g., MS4wLjABAAAA-VASjiXTh7wDDyXvjk10VFhMWUAoxr8bgfO1kAL1-9s) visible in the captured request URL — record it for pagination requests.
Error handling: If no matching request appears, verify the profile page loaded (screenshot). Private accounts return an empty itemList. If the page shows a region block, switch to a non-HK proxy browser.
Output example:
{
"cursor": "1778468677570", // timestamp-based cursor for next page
"hasMore": true, // false when all videos loaded
"itemList": [
{
"id": "7212410220977392938",
"desc": "Daily Push Up Workout🚀#fitness",
"createTime": 1679270124,
"isAd": false,
"isPinned": false,
"isSponsored": false,
"locationCreated": "US",
"author": {
"id": "6803405475100181510",
"uniqueId": "marcusriosofficial",
"nickname": "Marcus Rios",
"verified": false,
"signature": "Former NFL Athlete 🏈\n📧[email protected]",
"bioLink": null,
"avatarThumb": "https://...",
"privateAccount": false
},
"authorStats": {
"followerCount": 423500,
"followingCount": 50,
"heart": 10000000,
"videoCount": 1277,
"diggCount": 869
},
"authorStatsV2": {
"followerCount": "423500",
"followingCount": "50",
"heart": "10000000",
"videoCount": "1277"
},
"stats": {
"diggCount": 367500,
"shareCount": 6041,
"playCount": 4500000,
"commentCount": 942,
"collectCount": 56691
},
"video": {
"duration": 48,
"height": 1280,
"width": 720,
"cover": "https://...",
"definition": "720p",
"format": "mp4"
},
"music": {
"id": "7176546707423889410",
"title": "Trap Money so Big (Remix)",
"authorName": "Iqbal12",
"original": false,
"coverMedium": "https://..."
},
"textExtra": [{"hashtagId": "9261", "hashtagName": "fitness"}],
"effectStickers": [],
"imagePost": null
}
]
}
To build the webVideoUrl for each item: https://www.tiktok.com/@{item.author.uniqueId}/video/{item.id}
Profile info is available from the first item's author and authorStats fields: followerCount, following, heart total, video count, bio, verified status.
After reading page 1, scroll down to load more videos:
scroll downwait stablenetwork requests --type xhr,fetch --filter "post/item_list"network request <id>Termination: hasMore is false in response, or itemList is empty.
DOM Pagination: Scroll triggers new post/item_list requests with timestamp-based cursor. Each page returns 16 items. Termination: hasMore === false or empty itemList.
itemList.length >= 1 and first item has non-null id, stats.playCount, author.uniqueId, authorStats.followerCount
post/item_list requires dynamic signing + secUid resolved by TikTok's JS — always use navigate + network captureitemListauthorStats.heartCount may overflow to negative for accounts with very high like counts — use authorStats.heart insteadfollowers/following lists are not available via this capability (separate scraper needed, requires login)Path: {working-directory}/browser-act-skill-forge-memories/tiktok-scraper-tiktok-profile-videos.memory.md
Before execution: If the file exists, read it first — it records unexpected situations from past executions; adjust strategy accordingly.
After execution: If an unexpected situation occurs (strategy failed, page redesigned, anti-scraping upgraded), append a line:
{YYYY-MM-DD}: {what happened} → {conclusion}
Normal execution does not write to the file.
Generates Instagram-ready product reels from any e-commerce product page URL. Scrapes product images, classifies by type, generates AI-animated clips via Higgsfield API, creates text overlays with style presets, and composes a 15-20 second reel with music. Supports model-based and product-only reels.
Use when fetching, searching, or analyzing transcripts from Lenny's Podcast, Dwarkesh Podcast, Cheeky Pint, 20VC, or A16z Podcast. Tier 2 (RSS+Groq Whisper) is the recommended approach -- fast, free, and most reliable. Also use when asked to "get transcript", "find episode", "summarize podcast", or "search podcast content". Do not use for general web scraping or non-podcast audio transcription.
Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed — the full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big text encoders (--cache-none), high-VRAM throughput (--gpu-only / --highvram), and attention-backend selection (--use-sage-attention for speed, --use-pytorch-cross-attention as the highest-quality / Z-Image-safe fallback). Also the acceleration-stack + Blackwell/RTX 5000 (sm_120) notes. Use when a graph OOMs (especially long video like LTX 2 / WAN), when the GPU spills into shared VRAM and slows to a crawl, when switching between models eats all RAM, when Z-Image produces black/garbled output under Sage, or when deciding which attention backend to launch with. Flag names verified against upstream comfy/cli_args.py — see Sources.
Bulk download images from login-protected gallery websites using an attached browser session. Use when asked to scrape, download, or save images from authenticated gallery pages, extract full-size images from thumbnails, or batch download from multi-page galleries.
| сайтмапы, переобход, ссылки, фиды, диагностика. Плюс scraping раздела Alice / Share of Voice (нет публичного API). вебмастер индексация, вебмастер запросы, вебмастер переобход, share of voice, sov, алиса, alice efficiency, конкуренты в алисе.
Scrape and download all images from a given URL. Takes a URL, extracts image URLs from the page, and downloads them. Uses python3/curl as primary method, falls back to browser automation if needed. Use when user provides a URL and wants to download images from that page.
Generate a photo-based rehab estimate for any property. Accepts photos from listing sites (Redfin/Zillow via Chrome), a local folder on your computer, or a shared Google Drive link. Use when a wholesaler needs repair cost estimates before making an offer, building a deal package, or validating their numbers. Grades property condition across 6 zones using the R.E.H.A.B.+F scoring framework and produces three-scenario rehab budgets (rental-ready, mid-range flip, full worst-case). Uses Chrome MCP for Redfin photo browsing, Perplexity for local contractor costs, and Firecrawl for finding listing URLs.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Take browser-act/tiktok-profile-videos from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.