Influencer Discovery logo

Influencer Discovery

Community
superamped
influencer-discovery

Use this skill to discover and score relevant influencers across YouTube, X, blogs, newsletters, podcasts, and Instagram. Trigger it when building a sponsorship, affiliate, co-marketing, outreach, PR, or audience-research list for a defined market.

Overview

Publishersuperamped
Repositoryai-marketing-skills
Skill nameinfluencer-discovery
Stars
73
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by superamped on GitHub. Read the source before you install it.

Installation

Install the Influencer Discovery AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/superamped/ai-marketing-skills/tree/main/skills/research/influencer-discovery
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/superamped/ai-marketing-skills.git /tmp/ai-marketing-skills
mkdir -p .claude/skills
cp -r /tmp/ai-marketing-skills/skills/research/influencer-discovery .claude/skills/influencer-discovery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Influencer Discovery in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Influencer Discovery on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Influencer Discovery is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Influencer Discovery

Usage

Use when finding influencers to partner with for sponsorships, affiliate deals, or co-marketing. Also useful for identifying thought leaders your target audience already follows, building a media list for outreach or PR, or understanding who shapes opinion in your niche before creating content.

Process

Step 1: Gather Inputs

Ask the user for:

  1. Industry/niche — the topic domain (e.g., "B2B SaaS marketing", "personal finance for millennials", "indie game development")
  2. Target audience — who follows these influencers, framed as the buyer (e.g., "SaaS founders", "freelance developers", "e-commerce store owners")
  3. Platform focus (optional) — prioritize specific platforms (YouTube, X/Twitter, Newsletters, Podcasts, Instagram). Default: search all.
  4. Minimum follower count (optional) — exclude influencers below a threshold. Default: no minimum (micro-influencers included).

Extract from inputs:

  • Niche keywords: The 3-5 topic terms that define the industry
  • Audience profile: Who the target audience is (role, stage, problem domain)
  • Platform priorities: Which platforms to weight more heavily

Step 2: Generate Search Queries

Generate 10 search queries to surface influencers across platform types and discovery angles:

"Top influencers" list queries:

  • "top [niche] influencers [current year]"
  • "best [niche] creators to follow"
  • "top [audience] thought leaders"

Platform-specific queries:

  • "top [niche] youtube channels"
  • "[niche] youtube [subscribers OR creators]"
  • "best [niche] newsletter substack"
  • "top [niche] podcast"
  • "[niche] twitter thought leaders"

Cross-platform discovery:

  • "[niche] conference speakers [current year]"
  • "who sponsors [niche] newsletters"
  • "[niche] podcast guest list"

Step 3: Search YouTube

Search YouTube for top channels in the niche:

  • Use queries: "top [niche] YouTube channels", "[audience] YouTube", "[niche keyword] tutorial/advice channel"
  • For each channel found, collect: Channel name, URL, subscriber count, content focus
  • Aim for 20-30 YouTube channels across macro (500k+), mid-tier (50k-500k), and micro (<50k) tiers

Step 4: Search X/Twitter

Search for thought leaders on X/Twitter:

  • Use queries: "[niche] twitter", "best [niche] accounts to follow", "[identity/role] twitter"
  • Check "listicles" — blog posts titled "Best [niche] accounts to follow on Twitter/X" often list 10-20 accounts at once
  • Include both prolific posters (daily content) and respected practitioners (less frequent but high-quality takes)

Step 5: Search Blogs, Newsletters, and Podcasts

Blogs
  • Search: "top [niche] blogs", "best [niche] blog to read", "[niche] writers"
  • Look for independent writers with their own sites
Newsletters
  • Search: "best [niche] newsletter", "[niche] substack", "[niche] email newsletter"
  • Check Substack's discover page for the niche if applicable
Podcasts
  • Search: "top [niche] podcast", "best [niche] podcast", "[audience] podcast"
  • Check Apple Podcasts and Spotify charts if accessible

Step 6: Search Meta (Facebook and Instagram)

  • Search: "[niche] facebook page", "[identity] instagram", "[niche] instagram creator"
  • Focus on public profiles and pages
  • Meta is lower priority for most B2B niches — if the niche skews consumer or visual, prioritize more heavily

Step 7: Mine Cross-Platform Discovery Sources

Conference Speaker Lists
  • Search: "[niche] conference [current year] speakers", "[niche] summit speakers"
  • Conference keynote and session speakers are pre-vetted as recognized voices
  • Extract speaker names → find their primary platform
Podcast Guest Cross-References
  • Search: "[top podcast in niche] guests", "most popular [niche] podcast episodes"
  • Repeat guests on multiple podcasts = high-credibility signal
Newsletter Curator Lists
  • Search: "who sponsors [niche] newsletters", "[niche] newsletter sponsors"
  • Companies sponsoring newsletters indicate which newsletters have a commercially valuable audience

Step 8: Normalize All Results

Compile all discovered influencers into a single list. For each entry, record:

FieldDescription
NamePerson or brand name
Primary PlatformThe platform where they have the largest/most active presence
X/Twitter URLProfile URL or "—"
YouTube URLChannel URL or "—"
Newsletter/Blog URLURL or "—"
Podcast URLURL or "—"
Instagram/Facebook URLURL or "—"
Primary Follower CountCount on their primary platform
Content TypeWhat they primarily create (tutorials, opinion/takes, case studies, interviews, tools)
SourceWhere they were discovered

Deduplication: If the same person appears from multiple discovery sources, merge into one entry. Multiple discovery sources = stronger relevance signal.

Step 9: Score Each Influencer

Score every influencer on Relevance (1–5):

ScoreSignal
5Content is directly about the target audience's core problems — almost every post/video is on-target
4Strong match — most content is relevant, occasional tangents
3Adjacent — their niche overlaps meaningfully but isn't a perfect match
2Loose match — some relevant content but audience is broader or different
1Tangential — topic surface-level overlap but different audience
Audience Overlap Rating
RatingCriteria
HighRelevance ≥ 4
MediumRelevance = 3
LowRelevance ≤ 2

Step 10: Sort and Finalize

Sort the full list:

  1. Primary: Audience Overlap rating (High → Medium → Low)
  2. Secondary: Primary follower count (largest first within each tier)

Include micro-influencers (1K–50K followers) alongside macro — do not exclude them.

Output Format

# Influencer Discovery: [Industry/Niche]

**Date:** [current date]
**Industry/Niche:** [description]
**Target Audience:** [description]
**Influencers found:** [count] across [X] platforms
**Audience Overlap breakdown:** High: [X] | Medium: [X] | Low: [X]

---

## High Overlap Influencers

| # | Name | Primary Platform | Followers | X/Twitter | YouTube | Newsletter/Blog | Podcast | Instagram/FB | Content Type | Discovery Source |
|---|------|-----------------|-----------|-----------|---------|-----------------|---------|-------------|-------------|-----------------|
| 1 | [name] | [platform] | [count] | [url or —] | [url or —] | [url or —] | [url or —] | [url or —] | [type] | [source] |

---

## Medium Overlap Influencers
[Same table structure]

---

## Low Overlap Influencers
[Same table structure]

---

## Platform Coverage Summary

| Platform | Count | High Overlap | Notes |
|----------|-------|-------------|-------|
| X/Twitter | X | X | [observation] |
| YouTube | X | X | |
| Newsletter/Blog | X | X | |
| Podcast | X | X | |
| Instagram/Facebook | X | X | |

---

## Observations
[2-3 bullet points: where this niche's influencer ecosystem is concentrated, tier distribution, notable patterns]

## Partnership Opportunities
[Top 3-5 influencers worth prioritizing for sponsorship or collaboration, with a 1-sentence reason each]

## Recommended Next Steps
1. [e.g., "Reach out to top 3 High Overlap newsletter authors — newsletter sponsorships often have fastest lead time"]
2. [e.g., "Monitor [top X/Twitter account] for mentions of problems your product solves"]

Rules

  • Aim for 100+ influencers total. For narrow B2B niches, 50 is acceptable — flag it.
  • Never invent influencer accounts or inflate follower counts — only include verified results from search.
  • Never exclude micro-influencers (1K–50K) — they are often the highest-value partnerships for niche B2B audiences.
  • Never focus only on one platform — cross-platform coverage is a core output requirement.
  • Discovery source matters: an influencer found via conference speakers + podcast guest + YouTube search is more credible than one found via a single listicle.
  • Follower counts are best-effort estimates — verify before outreach.
  • If fewer than 30 influencers are found, try broader synonyms for the niche or audience.

Frequently asked questions

What does the Influencer Discovery AI skill do?

Use this skill to discover and score relevant influencers across YouTube, X, blogs, newsletters, podcasts, and Instagram. Trigger it when building a sponsorship, affiliate, co-marketing, outreach, PR, or audience-research list for a defined market.

Why use Influencer Discovery on TypingMind?

Because you install it once and use it with any model. Influencer Discovery is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Influencer Discovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/superamped/ai-marketing-skills/tree/main/skills/research/influencer-discovery. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Influencer Discovery?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Influencer Discovery?

As many as you like. As long as a model supports skills, you can use Influencer Discovery with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Influencer Discovery AI skill free?

Yes. It is published on GitHub by superamped under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇