find-twitter-influencers
Find Twitter/X influencers to promote a product or brand. Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list.
npx skills add gooseworks-ai/goose-skills --skill find-twitter-influencers --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Find Twitter/X influencers to promote a product or brand. Uses Brand.dev context to identify company details, then runs parallel discovery strategies (exhaustive influencer list extraction from curated pages, similar pages, and Fiber NL searches) to build a candidate pool. It parses handles from text content, then fetches profiles and tweets in parallel, applies hard filters, computes engagement metrics and a composite score, and selects top candidates for enrichment (emails, LinkedIn, websites). It emphasizes parallel execution to speed up profile and tweet fetching, and includes steps to deduplicate handles and extract contact information.
How it works
- Setup credentials from ~/.gooseworks/credentials.json and use Bearer authentication for all API calls.
- Step 1: Parse the request including company name/domain, niche, size, and max results.
- Step 2: Resolve the company via Brand.dev to obtain domain, industry, description, and keywords; build a company context string for queries.
- Step 3: Discover candidates using three parallel strategies:
- Strategy A (Exa search for curated influencer lists): run multiple EXA queries for core and adjacent niches to obtain pages with text content containing Twitter handles.
- Strategy B (Exa findSimilar): from strong listicles, find additional pages via findSimilar to surface more lists.
- Strategy C (Fiber natural-language-search): query NL profiles for core and adjacent niches, cross-referencing with LinkedIn URLs.
- Step 4: Extract and deduplicate usernames from the text content and Fiber results, filtering clearly non-relevant or brand accounts; target ~100-150 unique handles.
- Step 5: Get Twitter profiles and engagement via Scrape Creators in parallel:
- Step 1 fetch profiles for all candidates (in parallel)
- Step 2 fetch tweets for top candidates (in parallel)
- For each candidate, identify top 3 tweets by engagement, calculate averages and engagement rate, infer post frequency, and identify content themes.
- Apply additional filters (inactive for 30 days, protected, no niche relevance, etc.).
- Step 6: Score & rank candidates with a composite model (Relevance 40%, Engagement rate 25%, Follower count 15%, Content quality 10%, Audience alignment 10%), then select top N (default 20).
- Step 7: Enrich contacts by collecting emails and LinkedIn profiles. Prioritize LinkedIn URLs, perform Exa searches for LinkedIn profiles in parallel, then use Fiber kitchen-sink with LinkedIn URLs for best matches, followed by Hunter if possible.
When to use it
Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list. It relies on company context to tailor searches and on parallel data gathering for speed.
What it can touch
- Tools: claude-code, codex, cursor are declared for use.
- Endpoints and commands used include: Brand.dev API calls, /v1/proxy/orthogonal/run, /search, /findSimilar, /v1/natural-language-search/profiles, /v1/twitter/profile, /v1/twitter/user-tweets, /v1/proxy/orthogonal/run with various api parameters, /v1/kitchen-sink/person, /v2/email-finder, etc.
- Data elements touched include Twitter/X handles, bios, follower counts, tweet text, engagement metrics, profile URLs, LinkedIn URLs, emails, and websites.
Caveats
- Requires parallel API calls; failure of any parallel batch should not be assumed complete without retries.
- Filtering thresholds (e.g., minimum followers, inactivity window) are described as defaults in the steps and may be adjustable by user input.
- The process emphasizes avoiding brand accounts and ensuring relevance to niche; these rules are hard-filtered after data collection.
- Data freshness and availability depend on external services (Brand.dev, Exa, Fiber, Scrape Creators, Hunter) and may vary.
- Licensing: MIT per repository.
# Find Twitter Influencers ## Setup Read your credentials from ~/.gooseworks/credentials.json: ```bash export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])") export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))") ``` If ~/.gooseworks/credentials.json does not exist, tell the user to run: `npx gooseworks login` All endpoints use Bearer auth: `-H "Authorization: Bearer $GOOSEWORKS_API_KEY"` Discover, score, and enrich Twitter/X influencers relevant to a company, product, or niche. Returns a ranked list with engagement metrics, relevance reasoning, and contact info. ## Workflow ### 1. Parse the Request Extract from the user's query: - **Company name or domain** (required) — the brand seeking influencers - **Niche/vertical** (optional) — e.g., "fintech Twitter", "AI/ML creators", "DTC beauty" - **Size preference** (optional) — mid-tier (10K-100K), macro (100K+), or mixed (default: 10K+ minimum) - **Max results** (optional, default 20 — scale up or down if the user asks) ### 2. Resolve the Company Use Brand.dev to
- Setup
- Workflow
- 1. Parse the Request
- 2. Resolve the Company
- 3. Discover Candidates
- 4. Extract & Deduplicate Usernames
- 5. Get Twitter Profiles + Engagement
- 6. Score & Rank
- 7. Enrich Contacts
- 8. Present Results
- 9. Optional Deep Dive
- Tips
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
Query 1: Core niche — curated lists
Query 2: Core niche — different phrasing
Query 3: Core niche — thought leaders
Query 4: Adjacent niche 1 (e.g., if niche is "identity verification", try "fraud prevention")
Query 5: Adjacent niche 2 (e.g., "cybersecurity", "regtech", "biometrics")
Core niche
Adjacent niche — broader coverageWhat does the find-twitter-influencers skill do?
Find Twitter/X influencers to promote a product or brand. Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list.
How do I install it?
Run `npx skills add gooseworks-ai/goose-skills --skill find-twitter-influencers --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From gooseworks-ai/goose-skills, a repository with 1,091 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.