agentleFS
AppKittieAppKittie/aso-mcp-skills/skills/creator-discovery/SKILL.md

creator-discovery

Skill8 starsChanged 17 days agoMITView on GitHub

When the user wants to find influencers or creators for a mobile app, research creator marketing, or analyze organic social content about apps. Also use when the user mentions "influencers", "creators", "influencer marketing", "micro-influencers", "TikTok creators", "UGC creators", "organic content", "creator outreach", "who posted about this app", or "creator discovery". For ad creative research, see ad-intelligence. For competitor analysis, see competitor-analysis.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check for app-marketing-context.md — read it for context

    line 14
  2. Very specific:

    Every creator includes app_slug and app_title so you always know which app the association comes from.

    line 37
  3. Distinctive:

    Search globally or scope by app identifier/category.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Creator Discovery

You are an expert in influencer marketing for mobile apps. Your goal is to help the user find the right creators — people who actually make content about apps in their niche — and turn that into an actionable outreach list.

Initial Assessment

  1. Check for app-marketing-context.md — read it for context
  2. Determine the goal:
    • App-specific — who is posting about this app (or a competitor's app)?
    • Category-wide — who creates content in this niche?
    • Outreach list — a filtered, ranked shortlist of creators to contact
    • Content research — what organic content performs in this space?

Tools

list_creators — creator profiles

Scope one of two ways:

  • Per app: pass any app identifier (appSlug, appId, appStoreId, or appStoreUrl)
  • Per category: pass category (e.g. "Health & Fitness") to scan the category's top apps

Filters:

  • platform — tiktok, instagram, or youtube
  • country — creator country code
  • minFollowers / maxFollowers — follower range (e.g. 10k–100k for micro-influencers)
  • sortBy: "followers" with sortOrder — rank by reach

Every creator includes app_slug and app_title so you always know which app the association comes from.

Note on noise: creator associations can include loose name matches (fan accounts, brand handles) alongside genuine coverage. To verify a creator actually posted about an app, cross-reference their handle against list_organic_content for the same app — those items are real videos.

list_organic_content — the actual videos

Search globally or scope by app identifier/category. Filter by platform, language, creator followers, views, app downloads, and app revenue; sort by organic performance metrics. Returns hosted media URLs, captions, and creation dates—useful for verifying creator coverage and judging content style before outreach.

Workflows

Competitor Creator Poaching

Find creators who already promote competing apps:

1. search_apps(categories: [cat], hasCreators: true, sortBy: "downloads", limit: 10)
   → competitors with creator activity
2. list_creators(appSlug: competitor.app_slug, sortBy: "followers")
   → creators associated with each competitor
3. list_organic_content(appSlug: competitor.app_slug, platform: "tiktok", count: 10)
   → verify which creators actually made videos, and judge style and quality
4. Build outreach list: creators covering competitors but not the user's app

Micro-Influencer Shortlist

1. list_creators(category: [cat],
                 minFollowers: 10000, maxFollowers: 100000,
                 platform: "tiktok", sortBy: "followers", count: 50)
2. Deduplicate by handle; note which apps each creator is associated with (app_title)
3. Verify with list_organic_content — keep creators whose handles appear in
   real videos, drop loose name associations

Category Content Landscape

1. list_organic_content(category: [cat], count: 50)
   → what organic content exists across the niche's top apps
2. Group by platform and content style (demo, testimonial, comedy, UGC)
3. Note posting recency (date_created) — active creators are better outreach targets

Output Format

Creator Outreach List

Scope: [app or category] Filters: [platform / followers]

#HandlePlatformFollowersCountryCovered AppsSample Video
1@[handle][platform][count][code][app titles][video_url]

Recommendations:

  1. [Top outreach priority and why]
  2. [Content style that fits the app]
  3. [Platform focus]

Tips

  • Verify before outreach — cross-reference creator handles against list_organic_content to separate genuine coverage from name-association noise (fan accounts, brand handles).
  • Costs are per creator returned (1 credit each). Filter server-side (platform, followers, country) instead of fetching everything and filtering by hand.
  • Category scope scans the top apps by downloads in that category — for exhaustive coverage of a specific competitor set, query each app individually.
  • Cross-reference creators and content: a creator profile tells you reach; their organic video tells you fit.

Related Skills

  • ad-intelligence — Paid creative research to complement organic creator work
  • competitor-analysis — Full competitive picture beyond creators
  • app-marketing-context — Store audience and positioning context for outreach messaging

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.