Influencer Discovery

Influencer Discovery

This skill helps you find the right influencers for your brand by searching across platforms, analyzing content and audience fit, and building curated lists of potential partners. It adapts traditional lead research methodology to the influencer marketing context.

Quick Start

Shortest invocation:

Find 20 influencers in [niche] for [brand/product]

Common scenario:

Find influencers who:
- Are in the [niche] space
- Have 50K-200K followers
- Post primarily on TikTok and Instagram
- Are based in [location]
- Have engagement rates above 4%
- Have worked with brands similar to [brand]

Skill Contract

• Reads: brand/product, niche or category, target platforms, follower range, engagement floor, location/language, audience demographics, exclusions; prior entity-optimizer brand profile and any audience-analyzer output if present in memory.
• Writes: discovery results to memory/influencer/influencer-discovery/YYYY-MM-DD-.md — search criteria, candidate pool stats, per-influencer profiles, tiered shortlist with fit scores.
• Promotes: durable facts (top-tier handles, confirmed niche/platform mix, competitor-saturated creators) to memory/hot-cache.md.
• Done when:
• A candidate pool exists with at least the requested count screened past follower, engagement, and brand-safety filters.
• Each shortlisted influencer has a profile with metrics, audience read, and a preliminary fit score.
• A tiered shortlist (must-reach / strong / consider) is compiled with next-step pointers.
• Primary next skill: [fit-scorer](../../map/fit-scorer/SKILL.md) — score and rank the discovered candidates with weighted criteria.

Handoff Summary

> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../references/skill-contract.md).

Data Sources

This family has no live integrations required (Tier 1): the skill works with only the inputs the user provides. Ask the user for niche, platforms, follower band, engagement floor, location, and exclusions, then reason over what they supply plus any public handles they share.

Where a tool could sharpen results, use ~~ connector placeholders:

• ~~influencer database — bulk discovery, follower/engagement metrics, audience demographics.
• ~~social platform analytics — native creator-marketplace data, trending sounds, related accounts.
• ~~CRM — import the shortlist and dedupe against existing partners.
• ~~audience overlap — estimate creator-audience vs. brand-audience match.

See [CONNECTORS.md](../../CONNECTORS.md) for the free/keyless recipe per category and the opt-in MCP layer. None are required — every step degrades to user-supplied inputs.

Instructions

When a user requests influencer discovery:

1. Define Search Criteria

```markdown ### Discovery Parameters

Brand/Product: [name] Campaign Goal: [awareness/consideration/conversion] Budget Range: [budget implications for influencer tier]

Search Criteria:

| Parameter | Requirement | Priority | |-----------|-------------|----------| | Niche/Category | [niche] | Required | | Platform(s) | [platforms] | Required | | Follower Range | [min-max] | Required | | Engagement Rate | [minimum %] | Required | | Location | [regions] | [Required/Preferred] | | Language | [languages] | [Required/Preferred] | | Content Type | [video/photo/etc.] | Preferred | | Posting Frequency | [minimum] | Preferred | | Audience Demographics | [age/gender/interests] | Preferred | | Brand Safety | [requirements] | Required |

Nice-to-Have:

• [Additional preference 1]
• [Additional preference 2]

Exclusions:

• [Competitor partnerships]
• [Content types to avoid]
• [Other exclusions]

```

1. Conduct Search

```markdown ## Search Strategy

### Primary Search Methods

1. Hashtag Research

• Core hashtags: #[hashtag1], #[hashtag2]
• Niche hashtags: #[hashtag3], #[hashtag4]
• Brand-adjacent: #[hashtag5]

1. Similar Accounts

• Starting from: @[known influencer]
• Platform suggestions: "Similar to" features

1. Competitor Mentions

• Check tagged posts on [competitor accounts]
• Monitor #[competitor hashtags]

1. Platform-Specific Discovery

• TikTok: Creator Marketplace, trending sounds
• Instagram: Explore page, Reels
• YouTube: Related channels, collaboration networks

1. Tool Queries (if available)

• [Platform]: [search query]

```

1. Initial Screening

```markdown ## Initial Candidate Pool

Total Candidates Found: [number] After Initial Screening: [number]

### Screening Criteria Applied

| Criterion | Filter | Eliminated | |-----------|--------|------------| | Follower range | [range] | [#] | | Engagement rate | >[%] | [#] | | Recent activity | 30 days ```

1. Build Influencer Profiles

For each qualified influencer:

```markdown ---

## Influencer #[X]: @[handle]

### Basic Information

| Attribute | Details | |-----------|---------| | Name | [name] | | Handle | @[handle] | | Platform | [primary platform] | | Other Platforms | [other handles] | | Location | [city, country] | | Language | [primary language] | | Niche | [category] |

### Metrics

| Platform | Followers | Engagement Rate | Avg. Views | |----------|-----------|-----------------|------------| | [Platform 1] | [count] | [%] | [views] | | [Platform 2] | [count] | [%] | [views] |

Growth Trend: [growing/stable/declining] ([%] last 90 days)

### Audience Analysis

| Demographic | Breakdown | Notes | |-------------|-----------|-------| | Gender | [%F / %M] | | | Age | [primary age range] | | | Location | [top countries/cities] | | | Interests | [categories] | |

Audience Quality Score: [X/10]

• Real followers estimate: [%]
• Audience-brand overlap: [High/Medium/Low]

### Content Analysis

Content Style:

• Primary format: [format]
• Posting frequency: [X posts/week]
• Aesthetic: [description]
• Tone: [description]

Top Performing Content:

1. [Content 1]: [engagement]
2. [Content 2]: [engagement]
3. [Content 3]: [engagement]

Brand Fit Assessment:

• Visual alignment: [High/Medium/Low]
• Value alignment: [High/Medium/Low]
• Audience alignment: [High/Medium/Low]

### Partnership History

Past Brand Partnerships: | Brand | Date | Content Type | Est. Performance | |-------|------|--------------|------------------| | [brand 1] | [date] | [type] | [performance] | | [brand 2] | [date] | [type] | [performance] |

Competitor Partnerships: [Yes/No - details]

### Contact Information

• Email: [if public]
• Agency/Manager: [if applicable]
• Contact Method: [best approach]

### Fit Score Summary

| Factor | Score (1-5) | |--------|-------------| | Audience match | [score] | | Content quality | [score] | | Brand alignment | [score] | | Engagement quality | [score] | | Authenticity | [score] | | Total | [X/25] |

Recommendation: ⭐ [Highly Recommended / Recommended / Consider / Pass]

Why They're a Good Fit: [2-3 sentences explaining the fit]

Potential Concerns:

• [Concern 1 if any]

--- ```

1. Compile Discovery List

```markdown # Influencer Discovery Results

Search Date: [date] Brand/Campaign: [name] Criteria Used: [summary]

## Summary Statistics

| Metric | Count | |--------|-------| | Total Candidates Reviewed | [#] | | Passed Initial Screening | [#] | | Highly Recommended | [#] | | Recommended | [#] | | To Consider | [#] |

### By Platform

| Platform | Count | Avg Followers | Avg ER | |----------|-------|---------------|--------| | Instagram | [#] | [avg] | [%] | | TikTok | [#] | [avg] | [%] | | YouTube | [#] | [avg] | [%] |

### By Tier

| Tier | Follower Range | Count | Est. Cost Range | |------|----------------|-------|-----------------| | Mega | 1M+ | [#] | [range] | | Macro | 100K-1M | [#] | [range] | | Micro | 10K-100K | [#] | [range] | | Nano | 5%) for key content

• 7 mid-tier for volume and variety
• 3 rising stars for early partnership potential

Next Steps: Run through fit-scorer for final ranking, begin outreach to top 5.

## Tips for Success

1. **Quality over quantity** - Better to have 10 perfect fits than 100 maybes
2. **Verify authenticity** - Check for fake followers, engagement pods
3. **Review recent content** - Ensure consistent quality and brand safety
4. **Consider past partnerships** - Learn from their collaboration history
5. **Look beyond followers** - Engagement quality matters more
6. **Check all platforms** - Multi-platform creators offer more value
7. **Save for later** - Build a pipeline, not just campaign lists

## Reference Materials

- [skill-contract.md](../../references/skill-contract.md) — shared contract and Handoff Summary format.
- [state-model.md](../../references/state-model.md) — memory tiers and save-path conventions.
- [CONNECTORS.md](../../CONNECTORS.md) — free/keyless data recipes and opt-in MCP layer.
- C3 benchmark at [references/c3/scoring-architecture.md](../../references/c3/scoring-architecture.md) — scoring framework that fit-scorer applies downstream.
- Siblings in the Map phase: [fit-scorer](../../map/fit-scorer/SKILL.md), [competitor-tracker](../../map/competitor-tracker/SKILL.md).

## Next Best Skill

**Primary**: [fit-scorer](../../map/fit-scorer/SKILL.md) — score and rank the discovered candidates with weighted criteria before outreach.

**Alternates (same IMPACT family)**:
- [competitor-tracker](../../map/competitor-tracker/SKILL.md) — when discovery surfaced competitor-saturated creators and you want to map the competitive field first.
- [audience-analyzer](../../insight/audience-analyzer/SKILL.md) — when the target audience is still fuzzy and criteria need sharpening before a re-search.

**Termination**: Maintain a visited-set. If a skill has already been invoked this session, stop and report chain-complete rather than re-invoking it. Max chain depth is 3 hops from the originating request; stop and summarize when reached.

## Related Skills

- [audience-analyzer](../../insight/audience-analyzer/SKILL.md) - Define who to reach
- [fit-scorer](../../map/fit-scorer/SKILL.md) - Score and rank discovered influencers
- [competitor-tracker](../../map/competitor-tracker/SKILL.md) - Find competitor influencers
- [outreach-manager](../../activate/outreach-manager/SKILL.md) - Contact discovered influencers

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [aaron-he-zhu](https://github.com/aaron-he-zhu)
- **Source:** [aaron-he-zhu/aaron-marketing-skills](https://github.com/aaron-he-zhu/aaron-marketing-skills)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.