Best for developers who want an agent to build an influencer outreach list without manual Twitter scrolling, then chain it straight into other Orthogonal skills like Gmail or Sheets. It is one of 88 skills in Orthogonal's open-source GitHub repository and only covers Twitter/X, not Instagram, TikTok or YouTube.
Find Twitter Influencers is an Orthogonal SKILL.md workflow that runs 3 parallel discovery strategies (Exa search, similar-page expansion, Fiber natural-language search) to surface Twitter/X creators for a brand, then ranks them with a 5-factor composite scoring model before returning a contact-enriched shortlist.
Maker: Orthogonal · Protocol: MCP · Auth: api key
Compatible agents: Claude Code, Cursor, Any orth CLI-compatible agent, Any MCP-compatible client
Required runtime: Node >= 18 (for orth CLI), Orthogonal account with credits
About Find Twitter Influencers
The Find Twitter Influencers skill from Orthogonal is a multi-step workflow packaged as a SKILL.md file that teaches AI agents how to discover, score, and enrich Twitter/X influencers for a given company or product. Rather than a single API call, the skill orchestrates 3 research strategies in parallel: Exa web search for curated influencer list pages (Orthogonal's primary source since Twitter profiles are not indexed by Exa), a similar-page expansion step off the strongest list finds, and Fiber natural-language profile search to surface LinkedIn-heavy professionals. From these sources it extracts Twitter handles, fetches profiles and engagement metrics via Scrape Creators, applies scoring, and enriches contact information using Hunter, Tomba, and Fiber kitchen-sink lookups. The default output is a ranked table of influencers with followers, engagement rate, top tweet URL, email, and LinkedIn.
The skill is part of the orthogonal-sh/skills open-source repository, which now covers 88 integrations for AI agents after a repo restructure moved every skill under a shared skills/ subfolder (the 90+ figure listed when this page first published is out of date). It is built by Orthogonal, which closed a $4.3M seed round led by Pantera Capital in June 2026, with Y Combinator, Pioneer Fund, Decasonic, Blast, Outbound and Surreal also participating, on top of its earlier Y Combinator W26 acceptance. Agents invoke the skill by reading the SKILL.md instructions and then calling individual orth CLI commands (e.g., orth run exa /search, orth run scrapecreators /v1/twitter/profile) routed through the Orthogonal platform. This removes the need for the agent to manage API keys for Exa, Scrape Creators, Fiber, Hunter, or Tomba separately.
The workflow is designed for parallelism: profile fetches, tweet fetches, LinkedIn lookups, and email enrichment calls are all launched in parallel batches. Scoring uses a 5-factor composite model that weighs relevance, engagement rate, follower count, content quality, and audience alignment, broken down in the scoring feature below. The skill applies hard filters for minimum 10,000 followers, active posting in the last 30 days, and bio relevance to the target niche or adjacent niches.
Pricing is pay-per-call through Orthogonal's platform, with no monthly subscription. A single full influencer research run (parallel Exa searches, profile and tweet fetches, contact enrichment) draws credits proportional to candidate volume; exact per-call rates and the current free-credit balance are covered in the pricing FAQ below.
The skills repository's most recent commit landed June 17, 2026, and this specific skill's SKILL.md has been unchanged since February 27, 2026, though the sub-APIs it calls (Exa, Scrape Creators, Fiber, Hunter, Tomba) continue to update independently on their own vendors' schedules.
Key Features
- 3-Strategy Discovery Pipeline: Runs Exa curated-list search across 5+ query variations spanning core and adjacent niches, widens coverage by pulling pages similar to the strongest listicle finds, and layers in Fiber natural-language profile search, all in parallel before filtering.
- Scrape Creators Profile and Tweet Enrichment: Fetches structured Twitter profiles for all candidates (followers, bio, verification) and then tweets for the top 40 candidates, calculating average likes, retweets, replies, and engagement rate from the nested legacy.favorite_count fields.
- 5-Factor Composite Scoring: Ranks candidates using a weighted model: relevance to the brand (40%), engagement rate (25%), follower count log-scaled (15%), original content quality (10%), and estimated audience alignment (10%).
- Contact Enrichment Waterfall: Finds LinkedIn URLs via Exa site:linkedin.com searches, then enriches contacts via Fiber kitchen-sink (LinkedIn URL as profileIdentifier), Hunter email-finder (domain + name), and Tomba LinkedIn-to-email in that priority order.
- Hard Filter Application: Removes candidates with fewer than 10,000 followers, no tweets in the last 30 days, empty or off-niche bios, suspended accounts, and accounts that have migrated to Mastodon, Bluesky, or Threads.
- Ranked Markdown Table Output: Delivers a ranked table of 20 influencers by default (configurable) with full plain-text URLs for Twitter profile, top tweet, email, and LinkedIn, plus a summary of candidate pool size, filter drop-off, and niche coverage.
- Optional Deep-Dive Enrichment: For any influencer needing more detail, an optional step layers in Nyne for an async full tweet-history newsfeed and Sixtyfour for AI-powered lead research (work email, audience size, collab history) beyond the default ranked table.
Use Cases
- Building an influencer outreach list for a product launch: An agent takes a brand name and niche, runs the full discovery-to-contact pipeline, and returns 20 ranked influencers with email and LinkedIn ready for an outreach draft.
- Chaining influencer research into a full outreach pipeline: Because the skill runs inside Claude Code or Cursor, its output can feed directly into other Orthogonal skills like Gmail or Google Sheets to draft and log outreach without leaving the agent.
- Repeatable research across multiple client niches: Agencies run the same documented 9-step pipeline against different client niches, getting a consistent ranked table instead of manual Twitter browsing each time.
Install
npm install -g @orth/cli && orth login && orth skills add orthogonal-find-twitter-influencersRequirements
- Node >= 18 for the orth CLI (@orth/cli on npm)
- An Orthogonal account with credits (orthogonal.com/dashboard/balance)
- No separate Exa, Scrape Creators, Fiber, Hunter or Tomba accounts needed — Orthogonal routes and keys all of them
Actions
Resolve Company Context
Looks up a brand's domain, industry, description and target-audience keywords via Brand.dev so every later search query is grounded in real company context.
orth run brand-dev /v1/brand/retrieve-by-name --query 'name=Acme Corp'name(string): Company name to resolve (use this or domain).domain(string): Company domain to resolve directly.
Discover Curated Influencer Lists
Runs Exa web search for listicle and blog pages naming Twitter/X influencers in a niche, returning full page text so handles can be extracted.
orth run exa /search --body '{"query": "best fintech Twitter accounts to follow", "numResults": 10, "contents": {"text": {"maxCharacters": 5000}}}'query(string) — required: Search query, e.g. 'best {niche} Twitter accounts to follow'.numResults(integer): Results per query.
Expand From a Strong List
Given one high-quality curated-list URL, finds similar pages via Exa findSimilar to widen candidate coverage beyond the initial keyword searches.
orth run exa /findSimilar --body '{"url": "https://example.com/top-fintech-twitter-influencers", "numResults": 5, "contents": {"text": {"maxCharacters": 5000}}}'url(string) — required: URL of a known-good curated list page.numResults(integer): Number of similar pages to return.
Fetch Twitter Profile and Engagement Data
Pulls structured Twitter/X profile data for every candidate, then recent tweets for the top prospects, to compute follower counts, bios and engagement rate.
orth run scrapecreators /v1/twitter/profile --query 'handle=examplehandle'
orth run scrapecreators /v1/twitter/user-tweets --query 'handle=examplehandle'handle(string) — required: Twitter/X handle without the @ symbol.
Enrich Contact Details
Runs the contact waterfall for shortlisted influencers: LinkedIn URL discovery, then Fiber kitchen-sink, then Hunter email-finder, then Tomba LinkedIn-to-email, in priority order.
orth run fiber /v1/kitchen-sink/person --body '{"profileIdentifier": "https://linkedin.com/in/janesmith"}'
orth run hunter /v2/email-finder --query 'domain=janesmithcreative.com' --query 'first_name=Jane' --query 'last_name=Smith'profileIdentifier(string): LinkedIn URL for Fiber kitchen-sink lookup (preferred, best match rate).domain(string): Company domain for Hunter's name+domain fallback.
Optional Deep-Dive Enrichment
For influencers needing more than the default table, fetches full tweet history asynchronously via Nyne and runs AI-powered lead research via Sixtyfour for work email, audience size and collab history.
orth run -X POST nyne /person/newsfeed -d '{"social_media_url": "https://x.com/TARGET"}'
orth run sixtyfour /enrich-lead --body '{"lead_info": {"first_name": "Jane", "linkedin_url": "https://linkedin.com/in/janesmith"}}'social_media_url(string): X/Twitter profile URL for Nyne's async newsfeed fetch.lead_info(object): Known identifiers (name, LinkedIn URL) passed to Sixtyfour for deep enrichment.
How to Invoke
Agent follows SKILL.md instructions, calling `orth run exa /search`, `orth run scrapecreators /v1/twitter/profile`, and enrichment endpoints in parallel via the orth CLI
Pricing
Pay-per-call via Orthogonal, no subscription. A full influencer research run (5 Exa searches, ~140 Scrape Creators calls, contact enrichment) uses roughly 150-200 credits, priced per-API from $0.001 to $1.00 per call depending on tier. New accounts get $5 in free credits, enough for about one full run, and credits can also be paid with USDC via x402 or MPP instead of a prepaid balance.
Strengths
- Combines 5 sub-APIs (Exa, Scrape Creators, Fiber, Hunter, Tomba) under one Orthogonal key, eliminating separate accounts and API key management for each service.
- Adjacent niche search (2-3 related verticals) expands coverage in narrow B2B niches where only 10-20 primary influencers exist on Twitter/X.
- Fully parallelized API calls (profile fetches, tweet fetches, LinkedIn lookups) reduce a full research run from 10+ minutes to 2-3 minutes when the agent follows the parallel batching guidance.
Weaknesses
- A full run's credit cost depletes the free starting credit after about one complete research job, and searches across more adjacent niches cost more.
- Exa does not index Twitter/X profiles, so discovery depends on third-party curated list pages (listicles, blog posts); influencers absent from such lists will be missed.
- Contact enrichment match rates are low for influencers who do not have LinkedIn profiles or personal domains discoverable via Exa or Fiber.
- This skill does not appear in the orthogonal-sh/skills repository's own README catalog table, which lists 184 other skills, even though its SKILL.md and hosted skill page both remain live.
Frequently Asked Questions
What does Find Twitter Influencers actually cost?
A single complete research run, covering the parallel discovery searches, the bulk profile and tweet fetches, and the contact-enrichment waterfall, costs roughly 150-200 credits total on Orthogonal's pay-per-call platform. The $5 credit new accounts start with typically covers about one such run. There is no monthly subscription.
Can you use Find Twitter Influencers without paying?
New Orthogonal accounts receive $5 in free credits, no credit card required, which covers roughly one complete influencer research run before it runs out. The SKILL.md workflow itself is open source and free to read on GitHub regardless of account status. Beyond the free credit, every Exa search, Scrape Creators call and enrichment lookup draws from the same paid credit pool.
What are the closest competitors to Find Twitter Influencers?
SparkToro is a dedicated audience-research platform that finds accounts by what a brand's customers already follow, a different signal than keyword-and-listicle discovery. Modash is an influencer database covering Twitter, Instagram, TikTok and YouTube with a searchable filter interface built for non-technical marketers. HypeAuditor adds bot-detection and audience-quality scoring this skill's pipeline does not include. Pick this skill when the research needs to run inside an agent alongside other automated steps.
How does Find Twitter Influencers compare to SparkToro in 2026?
SparkToro runs as a standalone monthly subscription and ranks accounts by shared audience overlap, a different signal than this skill's keyword-and-listicle discovery. Find Twitter Influencers has no subscription; cost scales with usage through Orthogonal's pay-per-call credits instead. SparkToro ships its own dashboard and saved lists, while this skill hands a markdown table back to whatever agent called it, meant to be chained into further steps like outreach drafting.
How do you set up Find Twitter Influencers?
Install the CLI with `npm install -g @orth/cli`, run `orth login`, then add the skill with `orth skills add orthogonal-find-twitter-influencers` so the SKILL.md lands in the agent's skills directory. Open Claude Code or Cursor and ask the agent to find Twitter influencers for a brand, giving it a company name and optionally a niche and result count. The agent runs the pipeline itself, typically finishing in 2-5 minutes.