Hashtag research
Research a hashtag or keyword — volume/popularity signals, top and recent content, and related hashtags — on TikTok, Douyin, Instagram, Xiaohongshu, and more. Use when the user asks "research #hashtag", "how big is this hashtag", "related tags", "best hashtags for X", or wants content ideas around a tag.From its SKILL.md
npx -y skills add TikHub/tikhub-plugin --skill hashtag-researchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.8 KB, as published. Nobody here has run it
Hashtag Research
Assess a hashtag/keyword and surface its top content and related tags.
Setup gate
[ -z "${TIKHUB_API_KEY:-}" ] && echo "Set TIKHUB_API_KEY first (see tikhub-onboarding)."
Workflow
- Pick platform(s) and the hashtag/keyword.
- Pull signals + content:
- TikTok:
ads/get_trends_hashtag_detail(hashtag_id) andads/get_trends_hashtag_list; pull videos under a hashtag withapp/v3/fetch_hashtag_video_list(ch_id). - Douyin:
search/fetch_general_search_v2(POST) for hashtag/keyword content. - Instagram:
v2/search_hashtags+v2/fetch_hashtag_posts. - Xiaohongshu:
app_v2/search_notes(keyword). - Discover exact paths:
tikhub-find-endpoint "hashtag" --platform <slug>.
- TikTok:
- Summarize: estimated popularity/volume, top posts (engagement), recent momentum, and a list of related/co-occurring hashtags pulled from the top posts.
- Recommend a tag set for the user's niche.
Cost awareness
Detail/list calls are 1 each; pulling top-posts pages multiplies calls. Cap and warn for deep pulls.
Verification gate
- Hashtag resolved (or clearly report "no data / low volume").
- Top posts are actually tagged with the hashtag.
- Related tags derived from real co-occurrence, not guessed.
Red flags
- Inventing volume numbers — only report what the API returns; otherwise say "not available".
- Recommending banned/irrelevant tags.