agentsclimarketplace

Trooly ai skill

Skill alphaparkinc/trooly-ai-skill

GenPark skill: Automate qualitative user research using Trooly.ai's Empathy Engine.

Install
npx -y skills add alphaparkinc/trooly-ai-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Qualitative Research Automator — Orchestrates AI-driven qualitative interviews at scale using Trooly.ai's Empathy Engine to gather, analyze, and synthesize user feedback.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.5 KB, 648 tokens by cl100k_base, as published. Nobody here has run it

Trooly.ai Qualitative Research Automation

Overview

The Trooly Qualitative Research Automator (Insight) is a specialized AI agent designed to execute end-to-end user research campaigns. By leveraging Trooly.ai's Empathy Engine, this skill enables the agent to act as an expert human moderator. It conducts 45-minute, dynamic, in-depth interviews with global participants, adapting its question flow based on emotional cues, tone, and spoken context. It synthesizes hours of qualitative data into actionable product and marketing insights within 24 hours.

Capabilities

  1. Automated Study Design & Recruitment: Translate high-level research goals into structured study parameters. The agent interfaces with Trooly's 180M+ global panel to recruit specific target personas across 25 countries in minutes.
  2. Empathic Interviewing: Deploy multimodal voice agents that conduct 45-minute interviews. The Empathy Engine allows the agent to detect frustration, delight, or confusion, prompting it to dynamically ask follow-up questions or pivot the conversation.
  3. Real-time Synthesis: Process video, audio, and transcript data in real-time. Identify recurring themes, categorize user sentiment, and extract verbatim quotes.
  4. Insight Reporting: Generate comprehensive, professional reports (Markdown/PDF/Slides) containing emotional heatmaps, high-level summaries, and actionable product recommendations.
  5. Data Transparency & Traceability: Link every generated insight back to the raw data, allowing stakeholders to view the specific video clip or transcript segment where the insight originated.

Usage Instructions

Provide: research_objectives (e.g., "Understand why users abandon the onboarding flow"), target_audience_criteria (e.g., "SaaS founders, US, aged 30-45"), and output_format (e.g., "Executive Summary PDF").

  • The agent returns:
    • study_design.json — The screening criteria and interview guide.
    • insight_report.md — The synthesized findings and recommendations.
    • raw_data_links.csv — Links to the video recordings and transcripts.

Safety Controls

  • Respondent Consent: Enforce strict opt-in consent protocols before beginning any recording or interview session.
  • PII Redaction: Automatically scrub Personally Identifiable Information (PII) such as full names, addresses, or payment details from transcripts and summaries.
  • Bias Mitigation: Ensure question phrasing remains neutral to avoid leading the interviewee, verified by a secondary LLM pass before deploying the interview guide.

Examples

  • "We are launching a new enterprise billing feature. Launch a Trooly study with 10 financial controllers in Europe to understand their current pain points. Give me the summary report by tomorrow." → Insight defines the study, recruits controllers, conducts the AI interviews, and delivers the report.
  • "Analyze the raw transcripts from the last Trooly campaign about our mobile app redesign. Highlight any negative emotional reactions related to the navigation menu." → Insight scans the Empathy Engine logs and transcripts, returning specific timestamps and quotes.

Agent

Owned by Insight — the dedicated User Research and Analytics agent of the Research Agent Group.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most research analysis skills give in 648 tokens

Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-07

  • Generate a markdown reportin 32 of 1063, across 23 files
  • Cite each claim's sourcein 30 of 1063, across 15 files
  • Define the ideal customer profilein 20 of 1063, across 2 files
  • Search for companies matching the criteriain 20 of 1063, across 2 files
  • Assign a fit score from one to tenin 20 of 1063, across 2 files
  • Analyze the codebase to understand the productin 19 of 1063, across 1 file
  • Ask clarifying questions about the value propositionin 19 of 1063, across 1 file
  • Look for signals of immediate needin 19 of 1063, across 1 file
  • Identify the target decision maker rolein 19 of 1063, across 1 file
  • Suggest a personalized contact strategyin 19 of 1063, across 1 file
  • Provide conversation starters for outreachin 19 of 1063, across 1 file
  • Format results in a scannable markdown templatein 19 of 1063, across 1 file

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.