Find Twitter Influencers with AI: 20 Results, Scored and Enriched 2026
Orthogonal's Find Twitter Influencers skill discovers and scores 20 ranked Twitter creators for any brand using Exa, Scrape Creators, and Fiber. Pay per call.
Orthogonal's Find Twitter Influencers skill runs a 9-step research pipeline that discovers, filters, scores, and enriches Twitter/X creators for any brand. It uses Exa web search for curated influencer lists, Scrape Creators for engagement data, and Fiber plus Hunter for contact enrichment, all under one Orthogonal API key. A full run consumes roughly 150-200 credits. New accounts get $10 free.
Orthogonal's Find Twitter Influencers skill is a multi-step AI workflow that discovers, scores, and enriches 20 Twitter/X influencers for a given brand. It combines Exa curated-list search, Scrape Creators for profile and tweet data, and Fiber plus Hunter for contact enrichment. A 5-factor scoring model ranks by relevance (40%), engagement rate (25%), and 3 other signals. Pricing is pay-per-call; a full run uses roughly 150-200 Orthogonal credits.
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), Exa findSimilar to expand from strong list URLs, 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 20 influencers with followers, engagement rate, top tweet URL, email, and LinkedIn. The skill is part of the orthogonal-sh/skills open-source repository, which covers 90+ integrations for AI agents. It is built by Orthogonal, a YC W26-backed company acting as a unified API gateway. 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 weighted by relevance to the target company (40%), engagement rate (25%), follower count log-scaled (15%), content quality (10%), and audience alignment (10%). 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. Each Exa search, Scrape Creators profile fetch, and enrichment call consumes credits separately. A single full influencer research run (5 Exa searches, 100 profile fetches, 40 tweet fetches, contact enrichment) may use 150-200 credits depending on candidate volume. New accounts receive $10 in free starting credits. No monthly subscription is required. Orthogonal was accepted into Y Combinator's W26 batch in 2026, founded by Christian Pickett and Bera Sogut. The skills repository was last updated in June 2026 and covers 90+ integrations including social media research, company intelligence, lead enrichment, and developer tools.
Key Features
- 3-Strategy Discovery Pipeline: Runs Exa curated-list search (5+ query variations across core and adjacent niches), Exa findSimilar to expand from strong list URLs, and Fiber natural-language profile search in parallel to maximize candidate coverage 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.
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. A full influencer research run (5 Exa searches + ~140 Scrape Creators calls + enrichment) consumes roughly 150-200 credits. New accounts get $10 in free credits.
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 consumes 150-200 Orthogonal credits, which depletes the free $10 starting credit after 1-2 complete research jobs depending on niche size.
- 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.
Frequently Asked Questions
What is Find Twitter Influencers (via Orthogonal) and what does it do?
Orthogonal's Find Twitter Influencers skill is a SKILL.md workflow that teaches AI agents how to discover, score, and contact-enrich Twitter/X influencers for a given brand or product. The skill runs a 9-step pipeline: parse the user's brand request, resolve company context via Brand.dev, run 3 parallel discovery strategies (Exa curated-list search, Exa findSimilar, Fiber profile search), extract and deduplicate Twitter handles from 100-150 candidates, fetch profiles and tweets via Scrape Creators, apply a 5-factor scoring model, enrich contact info (email, LinkedIn), and output a ranked markdown table of 20 influencers with followers, engagement rate, top tweet URL, and contact details. It is part of Orthogonal's 90+ skill open-source repository on GitHub (orthogonal-sh/skills), backed by YC W26 funding. The skill orchestrates 5 sub-APIs (Exa, Scrape Creators, Fiber, Hunter, Tomba) through a single Orthogonal API key, eliminating separate account setup for each service. All profile and tweet fetches are parallelized, reducing a full research run from 10+ sequential minutes to roughly 2-3 minutes.
How much does Find Twitter Influencers (via Orthogonal) cost in 2026?
Pricing is pay-per-call through the Orthogonal platform with no monthly subscription or minimum spend. A full influencer research run (5 Exa searches, ~100 Scrape Creators profile fetches, ~40 tweet fetches, Fiber and Hunter enrichment calls) consumes approximately 150-200 Orthogonal credits. New accounts receive $10 in free starting credits upon signup, which covers roughly 1-2 complete research runs depending on niche size and result count. Once the $10 credit balance is depleted, additional credits must be purchased through the Orthogonal dashboard at rates listed on orthogonal.com/pricing. The SKILL.md file itself is free and open source in the orthogonal-sh/skills GitHub repository, so the workflow instructions are freely readable without an Orthogonal account. There are no hidden fees beyond per-call credits; each Exa, Scrape Creators, Fiber, Hunter, and Tomba call deducts from the same Orthogonal credit pool.
What are the main features of Find Twitter Influencers (via Orthogonal)?
The skill provides 6 core capabilities across its 9-step pipeline. Discovery uses 3 parallel strategies: Exa web search for curated influencer list pages with 5+ query variations across core and adjacent niches, Exa findSimilar to expand from the best list URLs, and Fiber natural-language profile search for LinkedIn-heavy professionals. Profile and tweet data comes from Scrape Creators, which returns nested JSON with followers, bio, engagement counts (likes, retweets, replies inside the legacy object), and direct tweet URLs. Scoring uses a 5-factor composite: relevance (40%), engagement rate (25%), follower count log-scaled (15%), content quality (10%), and audience alignment (10%), with benchmarks of >3% engagement rate as excellent and <0.5% as a red flag. Hard filters remove accounts with fewer than 10,000 followers, no tweets in 30 days, off-niche bios, suspended accounts, and platform-migrated accounts. Contact enrichment runs a waterfall: Twitter bio email first (free), then Fiber kitchen-sink via LinkedIn URL, then Hunter email-finder, then Tomba LinkedIn-to-email. Output is a ranked markdown table of 20 influencers (default) with full plain-text URLs for every column.
Is Find Twitter Influencers (via Orthogonal) free to use?
The skill is not free beyond the initial $10 in starting credits that new Orthogonal accounts receive. A single complete influencer research run consumes roughly 150-200 Orthogonal credits, meaning the $10 credit balance covers approximately 1-2 full runs. After that, additional credits must be purchased to continue. The SKILL.md workflow instructions are open source and free to read in the orthogonal-sh/skills repository on GitHub, so you can understand the full pipeline without any cost. However, actually executing the skill requires an Orthogonal account and credits to call the underlying sub-APIs (Exa, Scrape Creators, Fiber, Hunter, Tomba). Each of those APIs charges Orthogonal per call, which Orthogonal passes through as credit consumption. There is no free tier for ongoing unlimited use.
What are the best alternatives to Find Twitter Influencers (via Orthogonal)?
SparkToro is a dedicated influencer research platform at $50-$300/month that discovers accounts by audience (what your customers read and follow) rather than by brand keyword, which is a more precise signal for most marketing campaigns. Modash is an influencer database platform at $99-$299/month covering Twitter, Instagram, TikTok, and YouTube with verified engagement rate data and a searchable filter interface, better for non-technical marketers. Scrape Creators used directly (without Orthogonal) gives raw Twitter profile and tweet data at a flat monthly rate, requiring you to build your own scoring and enrichment logic. Hypeauditor offers a paid API for influencer analytics with bot detection and audience quality scoring not included in Orthogonal's skill. The main advantage of Orthogonal's skill over these platforms is that it runs inside your agent (Claude Code, Cursor) and can be chained with other Orthogonal skills (Gmail, Google Sheets, Notion) to automate the full outreach workflow in one pipeline. Choose dedicated platforms for non-technical marketing teams; choose Orthogonal's skill for developer-led agents building end-to-end automation.
Who is Find Twitter Influencers (via Orthogonal) best for?
This skill is best for developers and growth engineers building AI agents in Claude Code or Cursor who need influencer research as one step in a larger automated pipeline (e.g., find influencers, then draft outreach in Gmail, then log results in Google Sheets). Growth marketers at early-stage startups who are comfortable with a CLI and want to run influencer research faster than manual Twitter browsing will get good value from the $10 free credit budget covering 1-2 full runs. Agencies that run repeatable influencer research across multiple client niches can use the skill as a documented, reproducible workflow. It is not appropriate for non-technical marketers who need a visual dashboard, filter UI, or saved influencer lists. B2C influencer campaigns targeting Instagram, TikTok, or YouTube are outside the skill's scope; it is Twitter/X only. Teams with a dedicated influencer marketing budget above $500/month will find specialized platforms like SparkToro or Modash more cost-effective for high-frequency research.
How do you get started with Find Twitter Influencers (via Orthogonal)?
Sign up at orthogonal.com to receive $10 in free starting credits. Install the orth CLI with `npm install -g @orth/cli` (requires Node 18+) and authenticate with `orth login`. Install the skill with `orth skills add orthogonal-find-twitter-influencers`, placing the SKILL.md file in your agent's skills directory. Open Claude Code or Cursor and ask your agent to find Twitter influencers for a specific company or product, providing the brand name and optionally a niche and desired result count (default 20). The agent will read the SKILL.md instructions and begin the 9-step pipeline: resolving brand context via Brand.dev, running parallel Exa searches, extracting handles, fetching Scrape Creators profiles and tweets, scoring, enriching contacts, and outputting a ranked table. Monitor credit consumption in the Orthogonal dashboard if running a large search; narrow B2B niches with many adjacent niche searches consume more credits. The first run takes 2-5 minutes with a well-parallelized agent.
How accurate and reliable are the influencer rankings from Find Twitter Influencers in 2026?
The ranking accuracy depends on the quality of Exa's curated list coverage for the target niche and the freshness of Scrape Creators data. For mainstream niches (fintech, SaaS, AI, beauty, fitness), Exa typically surfaces 5-10 high-quality curated list pages per query variation, yielding 80-150 candidate handles with good coverage. For narrow B2B niches (identity verification, regtech, industrial IoT), curated lists are sparse; the skill compensates by searching 2-3 adjacent niches, but may return only 10-15 qualified results instead of 20. Engagement rate calculations are accurate for any accounts where Scrape Creators successfully returns tweet data with the legacy.favorite_count field populated; some accounts return incomplete tweet objects, which the skill notes as a caveat. The contact enrichment step (email finding) has low match rates for influencers without LinkedIn profiles or personal domains, typically enriching 30-50% of the final list with verified emails. The hard filter for 30-day activity may miss recently returned accounts and may include accounts where all 30-day activity is low-quality retweets; reviewing the output is recommended before sending outreach.