influencer-discovery
Skill66 starsChanged 6 days agoMITView on GitHub
Find creators and influencers in a niche on TikTok, Instagram and YouTube, filter by follower range and real engagement, and export a shortlist. Use when the user wants micro-influencers, UGC creators, brand ambassadors or a creator list for a campaign. Uses the ScrapeIO API.
- Reads credentials
3 other projects use a version of this.
Adopted by
Most recently taken up by
- tigerless-labs/influencer-discoverytheir own version, first seen Oct 28, 2026
- XPOZpublic/xpoz-agent-skillstheir own version, first seen Sep 9, 2026
- Aditya923-c/xpoz-agent-skillstheir own version, first seen Feb 24, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- tigerless-labs/influencer-discovery★ 219same name
- XPOZpublic/xpoz-agent-skills★ 15same name
- Aditya923-c/xpoz-agent-skills★ 6same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ad-library-researchSkill
- comment-insightsSkill
- competitor-social-auditSkill
- creator-vettingSkill
- scrapeioSkill
- social-trend-researchSkill
- video-transcript-researchSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 42
With the
scrapeioMCP server: use the named tool when it exists (for example tiktok_profile).
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Influencer discovery
Turn "find creators for X" into a vetted shortlist with numbers and links.
Ask first (only if missing)
Niche or keywords, platforms, follower range (default 10k to 100k), how many creators (default 20), country or language if it matters.
Steps
- Search with 2 or 3 phrasings of the niche (for "espresso": "espresso", "home barista", "latte art").
- TikTok:
tiktok_search_users(/v1/tiktok/search/users,query) - Instagram:
instagram_search_profiles(/v1/instagram/search/profiles,query) - YouTube:
youtube_search(/v1/youtube/search,query, 2 credits), then take the channels
- TikTok:
- Profile each candidate:
tiktok_profile,instagram_profileoryoutube_channel(handle). Drop accounts outside the follower range and private accounts. - Recent posts:
tiktok_profile_videos,instagram_user_reelsoryoutube_channel_videos(handle). One page is enough. - Score each creator from the last 12 posts:
- median
plays - view rate = median plays / followers
- engagement rate = (likes + comments) / plays, median
- days since last post
- median
- Expand from the best 3:
instagram_similar_accounts(/v1/instagram/user/similar,handle) finds lookalikes for 1 credit. - Drop anyone with view rate under 5%, no post in 30 days, or engagement that looks bought (see the creator-vetting skill).
Output
A table sorted by engagement rate: handle, platform, followers, median plays, view rate, engagement rate, last post date, link to the best recent post (url). Offer a CSV. State the credits spent.
Cost
About 3 credits per creator checked (profile, posts, sometimes search). 20 kept creators usually costs 50 to 80 credits including the ones filtered out.
How to call ScrapeIO
Needs SCRAPEIO_API_KEY. If it is missing, ask the user to get a free key at https://scrapeio.com/login (100 credits, no card). Never print the key.
- With the
scrapeioMCP server: use the named tool when it exists (for exampletiktok_profile). For any other path, usecall_endpointwith{ "path": "/v1/...", "params": { ... } }. - Without MCP:
curl -s "https://scrapeio.com<path>?<params>" -H "x-api-key: $SCRAPEIO_API_KEY". - Answers are in
data; lists aredata.itemswithdata.cursoranddata.has_more. Fields are the same on every platform:handle,followers,plays,likes,comments,shares,created_at,url. - 403 (private) and 404 (not found) are free: skip and move on. Retry 502 once. 402 means the user needs credits (https://scrapeio.com/pricing).
- Watch
credits_remainingand tell the user before a step would spend more than they expect.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.