All skills
twitterlinkedinweb Cross-Platform Power Plays

Trend-to-Founder-to-Inbox

Catch a rising topic, find the B2B founders posting about it on LinkedIn and X, then surface their contact channel.

Run this skill with your agent
1. Connect the MCP server
https://apidirect.io/mcp?token=YOUR_API_KEY
2. Then ask your agent — name the skill so it runs this exact playbook
Use the trend-to-founder-to-inbox skill: Find what's trending around {topic}, the founders posting about it, and how I can reach them.
Naming the skill (trend-to-founder-to-inbox) makes your agent run this exact playbook instead of improvising its own searches. In clients that support MCP prompts (Claude Desktop, Claude Code, Cursor) it also appears as a prompt named trend-to-founder-to-inbox, and any agent can call get_skill(skill_id="trend-to-founder-to-inbox") directly.

What it does

A six-step chain across X, LinkedIn and the web: spot what's trending, find the founders riding it on LinkedIn and/or X (your choice), qualify them, dedupe, and resolve how to reach them — signal to inbox in one flow.

Who it's for: BD, partnerships, investors and founder-led sales.

Inputs

Input Required Description Example
topic Yes The theme/space you care about. AI voice agents
platforms No Comma-separated list of platforms to run — options: twitter, linkedin, web. Omit to run all of them; name specific platforms to limit the run. linkedin, twitter
region_woeid No WOEID for the X trends scan (1 = worldwide). 1
founder_sort No Sort order for the LinkedIn founder search: most_recent (freshest riders) or relevance. Maps to search_linkedin sort_by. Default most_recent. most_recent
depth No How many result pages to pull from the X and web searches — higher casts a wider net. Maps to the pages param. Default 2. 2

How your agent runs it

  1. 1
    twitter_trends(woeid={region_woeid})

    Pull live X trends; pick the ones adjacent to {topic}. Optional opener — skip if the topic is already clearly hot.

  2. 2
    search_twitter(query="{topic}", get_sentiment=true, sort_by=relevance, pages=2)

    Confirm the topic is active and commerce-shaped; note the loudest voices — often founders themselves.

  3. 3
    search_linkedin(author_title="Founder", query="{topic}", sort_by=most_recent)

    Only run if {platforms} includes linkedin: find founders posting about the topic. Collect author_url for each.

  4. 4
    linkedin_person_posts(url=<author_url>)

    Only run if {platforms} includes linkedin: qualify each LinkedIn founder's relevance and cadence.

  5. 5
    search_twitter_users(query="{topic}", pages=2)

    Only run if {platforms} includes twitter: find founders/builders on X whose bios match the topic; capture name + company from each profile.

  6. 6
    search_web(query="\"<founder name>\" <company> email", pages=2)

    Resolve a contact channel for every founder gathered in steps 3-5 — first dedupe by name+company so the same founder found on both LinkedIn and X is only looked up once. For founders with a storefront, use place_details emails_and_contacts instead.

Delivers: A deduped, ready-to-action list: trend → founders riding it (from LinkedIn and/or X) → qualification notes → a way to reach each.

Tools used

The full playbook

This is exactly what the MCP returns to your agent (via the trend-to-founder-to-inbox prompt or get_skill tool), with your inputs filled in.

SKILL: Trend-to-Founder-to-Inbox
A six-step chain across X, LinkedIn and the web: spot what's trending, find the founders riding it on LinkedIn and/or X (your choice), qualify them, dedupe, and resolve how to reach them — signal to inbox in one flow.

You are running this skill on API Direct via its MCP tools. Execute the steps below yourself by calling the named tools in order — values in <angle brackets> come from a previous step. Then deliver the result described at the end.

INPUTS:
  - topic (required): <topic — ASK THE USER>
      The theme/space you care about.
  - platforms (optional): (optional — e.g. linkedin, twitter)
      Comma-separated list of platforms to run — options: twitter, linkedin, web. Omit to run all of them; name specific platforms to limit the run.
  - region_woeid (optional): (optional — e.g. 1)
      WOEID for the X trends scan (1 = worldwide).
  - founder_sort (optional): most_recent (default — override if you like)
      Sort order for the LinkedIn founder search: most_recent (freshest riders) or relevance. Maps to search_linkedin sort_by. Default most_recent.
  - depth (optional): 2 (default — override if you like)
      How many result pages to pull from the X and web searches — higher casts a wider net. Maps to the pages param. Default 2.

PLATFORM SELECTION: some steps are gated with "Only run if {platforms} includes X". If the user supplied a `platforms` value, run only the steps whose platform is listed. If the user did NOT supply `platforms`, run ALL steps — every platform the skill supports.

STEPS:
  1. Tool `twitter_trends` — twitter_trends(woeid={region_woeid})
     Pull live X trends; pick the ones adjacent to {topic}. Optional opener — skip if the topic is already clearly hot.
  2. Tool `search_twitter` — search_twitter(query="{topic}", get_sentiment=true, sort_by=relevance, pages=2)
     Confirm the topic is active and commerce-shaped; note the loudest voices — often founders themselves.
  3. Tool `search_linkedin` — search_linkedin(author_title="Founder", query="{topic}", sort_by=most_recent)
     Only run if {platforms} includes linkedin: find founders posting about the topic. Collect author_url for each.
  4. Tool `linkedin_person_posts` — linkedin_person_posts(url=<author_url>)
     Only run if {platforms} includes linkedin: qualify each LinkedIn founder's relevance and cadence.
  5. Tool `search_twitter_users` — search_twitter_users(query="{topic}", pages=2)
     Only run if {platforms} includes twitter: find founders/builders on X whose bios match the topic; capture name + company from each profile.
  6. Tool `search_web` — search_web(query="\"<founder name>\" <company> email", pages=2)
     Resolve a contact channel for every founder gathered in steps 3-5 — first dedupe by name+company so the same founder found on both LinkedIn and X is only looked up once. For founders with a storefront, use place_details emails_and_contacts instead.

DELIVER: A deduped, ready-to-action list: trend → founders riding it (from LinkedIn and/or X) → qualification notes → a way to reach each.

Note: each underlying tool call is billed at its normal endpoint price; get_sentiment adds a small per-page surcharge. Page through results as needed but stop once you have enough to deliver the outcome.