Systems Lab

Agent skill

linkedin-influencer-discovery

Discover top LinkedIn influencers and voices by topic, industry, follower count, and country.

dormantNeeds a keyActs undeclared424 words

Filed under LinkedIn and social and Calls, demos and discovery.

From edupegoretti/fluidz-skills · 116 skills · 0 · pushed 2026-03-11

What it does when it runs

Discover top LinkedIn influencers and voices by topic, industry, follower count, and country. Use when you need to find the top 100 voices in a space, build influencer lists for outreach, or identify thought leaders on LinkedIn.

Read from the skill and the 2 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
  • APIFY_API_TOKEN
Hosts it reaches
  • api.apify.com
Tool permissions it declares
No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shellnetwork

Ask about linkedin-influencer-discovery

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/edupegoretti/fluidz-skills.git /tmp/fluidz-skills
git -C /tmp/fluidz-skills sparse-checkout set "skills/capabilities/linkedin-influencer-discovery"
mkdir -p ~/.claude/skills/linkedin-influencer-discovery
cp -R "/tmp/fluidz-skills/skills/capabilities/linkedin-influencer-discovery/." ~/.claude/skills/linkedin-influencer-discovery/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs APIFY_API_TOKEN, which you have to obtain separately.

Reproduced in full from edupegoretti/fluidz-skills/blob/a2cf697e2e8ec2ea517d85496e2d5c7f5dc44cd3/skills/capabilities/linkedin-influencer-discovery/SKILL.md, which is licensed MIT (repository). 424 words, 10 headings.

LinkedIn Influencer Discovery

Discover top LinkedIn influencers by topic, country, and follower count using the Apify powerai/influencer-filter-api-scraper actor. Queries a database of 3.6M+ influencer profiles filtered to those with LinkedIn presence.

Quick Start

Requires APIFY_API_TOKEN env var (or --token flag). Install dependency: pip install requests.

# Find top AI influencers with LinkedIn profiles
python3 skills/linkedin-influencer-discovery/scripts/discover_influencers.py \
  --topic "artificial intelligence" --max-results 50 --output summary

# Find SaaS influencers in the US
python3 skills/linkedin-influencer-discovery/scripts/discover_influencers.py \
  --topic "saas" --country "United States of America" --output summary

# Find marketing influencers with email available
python3 skills/linkedin-influencer-discovery/scripts/discover_influencers.py \
  --topic "marketing" --has-email --max-results 100

# Filter to a specific follower range
python3 skills/linkedin-influencer-discovery/scripts/discover_influencers.py \
  --topic "fintech" --min-followers 10000 --max-followers 500000 --output summary

CLI Reference

FlagDefaultDescription
--topicrequiredTopic to search (e.g. "artificial intelligence", "saas", "marketing")
--categorynoneCategory filter (e.g. "technology", "business", "lifestyle")
--countrynoneCountry (e.g. "United States of America", "United Kingdom")
--languageEnglishLanguage filter
--min-followers0Minimum follower count (client-side filter)
--max-followers0 (unlimited)Maximum follower count (client-side filter)
--has-emailfalseOnly return influencers with an email address
--max-results100Max influencers to discover (up to 1000)
--outputjsonOutput format: json or summary
--tokenenv varApify token (prefer APIFY_API_TOKEN env var)
--timeout600Max seconds to wait for Apify run

Cost

~$0.01 per result. 100 influencers ~ $1.00. The script prints a cost estimate before running.

Output Fields

Each influencer result includes (when available):

  • full_name - Display name
  • username - Social media handle
  • biography - Bio text
  • follower_count - Total followers (across platforms)
  • following_count - Following count
  • main_topic - Primary topic/niche
  • topics - List of associated topics
  • category_name - Category classification
  • linkedin_url - LinkedIn profile URL
  • has_email - Whether email is available
  • external_url - Website URLs
  • country, city - Location
  • is_verified - Verification status

Notes

  • Results are sorted by follower count (descending) by default
  • The actor queries a pre-indexed database, not live LinkedIn search
  • Follower counts are across all platforms, not LinkedIn-specific
  • The --min-followers and --max-followers flags filter client-side after results return
  • For detailed LinkedIn profile enrichment after discovery, chain with get-linkedin-profile
  • For post analysis, chain with linkedin-profile-post-scraper

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what linkedin-influencer-discovery does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.