ai-answer-gap
When the user wants to find the prompts where their brand should be cited in AI answers but isn't — and who owns the answer…
When a workflow needs public TikTok data through UnifAPI — creator profiles and engagement, videos and comments, hashtag and music feeds, or search. Also use on "find TikTok creators for," "pull videos for," "TikTok follower count," "search TikTok for," "rising hashtags," or
$ npx -y skills add unifapi-agent/agents --skill tiktok --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/tiktokContext preview
The summary Claude sees to decide when to auto-load this skill.
When a workflow needs public TikTok data through UnifAPI — creator profiles and engagement, videos and comments, hashtag and music feeds, or search. Also use on "find TikTok creators for," "pull videos for," "TikTok follower count," "search TikTok for," "rising hashtags," or
name: tiktok description: When a workflow needs public TikTok data through UnifAPI — creator profiles and engagement, videos and comments, hashtag and music feeds, or search. Also use on "find TikTok creators for," "pull videos for," "TikTok follower count," "search TikTok for," "rising hashtags," or when another skill (creator shortlist, audience fit, demand radar, local buzz) needs the deterministic TikTok read path. Connect via the `unifapi` skill first. Read-only research, never posts. license: MIT metadata: author: UnifAPI version: "1.0.0" homepage: https://unifapi.com/agents/tiktok source: https://github.com/unifapi-agent/agents
The deterministic read path for public **TikTok** data through UnifAPI. This is a **Data Skill**: it does not run a marketing job on its own — it names the concrete `tiktok/...` operations, response shapes, and gotchas so any creator- or trend-first workflow (shortlisting, audience-fit, demand radar, local buzz) reads from one known recipe instead of rediscovering the surface each time.
Read-only — **eyes, not hands**. It researches public TikTok data and returns cited records; it never posts, comments, or follows, and UnifAPI never holds TikTok credentials.
Connect once through the shared **`unifapi`** skill (OAuth MCP), then call the operations below. TikTok users and videos are keyed by **numeric id** — resolve a `@handle` or a video URL to its id first (see Gotchas). Keep any `billing` metadata so the output can state record cost.
Single-entity endpoints return the object in `data`:
{
"request_id": "unif_...",
"data": {},
"billing": { "records_charged": 1, "balance_remaining": 99 }
}List endpoints return an array in `data` plus `pagination`:
{
"request_id": "unif_...",
"data": [],
"pagination": { "has_more": false, "next_cursor": null },
"billing": { "records_charged": 1 }
}When `pagination.has_more` is true, pass `pagination.next_cursor` as the next request's `cursor` (`limit` sets page size). Always preserve `billing`.
| Need | Operation | | ----------------------------- | ------------------------------------------------------------- | | Resolve handle → id | `tiktok/users/resolve` (`?username=...`) | | Resolve video URL → id | `tiktok/videos/resolve` (`?url=...`) | | Search videos / users | `tiktok/search/videos` · `tiktok/search/users` (`?q=...`) | | Search hashtags / mixed | `tiktok/search/hashtags` · `tiktok/search` (`?q=...`) | | Creator profile | `tiktok/users/{id}` | | Creator videos | `tiktok/users/{id}/videos` | | Followers / following / likes | `tiktok/users/{id}/followers` · `.../following` · `.../likes` | | Video + reaction | `tiktok/videos/{id}` · `tiktok/videos/{id}/comments` | | Hashtag feed | `tiktok/hashtags/{id}` · `tiktok/hashtags/{id}/videos` | | Music feed | `tiktok/music/{id}` · `tiktok/music/{id}/videos` |
Need a field not listed here? Use the `unifapi` skill's `get_operation` to read the exact schema before calling — but pick the operation from this table, don't discover blind.
The deterministic recipes. Pick the one that matches the job; each names exactly what to call.
1. **Discover by topic.** Call `tiktok/search/videos?q=...`, `tiktok/search/users?q=...`, or `tiktok/search/hashtags?q=...` for the niche; use `tiktok/search?q=...` for a mixed result. 2. **Resolve a creator.** Call `tiktok/users/resolve?username=...` to get the numeric id, then `tiktok/users/{id}` for `follower_count`, `like_count`, and `video_count`. 3. **Read engagement.** Call `tiktok/users/{id}/videos`; each `Video` carries `view_count`, `like_count`, `comment_count`, and `share_count` — compute engagement per video. Page via `next_cursor`. 4. **Read a video and its reaction.** Call `tiktok/videos/{id}` (resolve a URL with `tiktok/videos/resolve?url=...` first), then `tiktok/videos/{id}/comments` for sentiment. 5. **Track trends.** Call `tiktok/hashtags/{id}` for `video_count`/`view_count` and `tiktok/hashtags/{id}/videos` (or `tiktok/music/{id}/videos`) for what's spreading on a tag or sound. 6. **Map a network.** Call `tiktok/users/{id}/followers`, `.../following`, or `.../likes` for reach and affinity work. 7. **Cite everything.** Every figure ties back to the video or profile it came from; report `billing.records_charged` (or estimate when billing metadata is absent).
`like_count`, `video_count`, `is_verified`, `is_private`, `region`.
`comment_count`, `share_count`, `duration`, `author`, `music`, `hashtags`, `create_time`.
`tiktok/users/resolve?username=...` and a video URL with `tiktok/videos/resolve?url=...` **before** any `tiktok/users/{id}/...` or `tiktok/videos/{id}/...` call.
hydrate many video ids at once.
`billing.truncated_due_to_balance` — when true the page is partial, so top up before trusting any count.
Return the records the calling workflow needs, each cited to its video or prof
Open-source marketing agents for Claude, ChatGPT, Codex, OpenClaw, Hermes, and any MCP client.
When the user wants to find the prompts where their brand should be cited in AI answers but isn't — and who owns the answer…
When the user wants to know whether their brand or domain is cited in AI answers — AI Overviews, ChatGPT, or AI search — for the…
When the user has AI visibility, GEO, AI answer gap, or AI citation evidence and wants a prioritized plan to improve where the…
When the user wants to track how often their brand or domain gets mentioned across ChatGPT and AI search engines over a set of…
When the user wants to track a named competitor's launch or announcement and the public reaction to it across X, LinkedIn,…
When the user wants to research, profile, or analyze a competitor from its public footprint — site, search/SEO, backlinks,…