Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →gooseworks-ai/get-qualified-leads-from-luma
End-to-end lead prospecting from Luma events. Searches Luma for events by topic and location, extracts all attendees/hosts, qualifies them against a qualification prompt, outputs results to a Google Sheet, and sends a Slack alert with top leads.
Passed 14 of 18 test cases with the skill, and 5 of 18 without it.
and 13 more in the full report
11 fixed6 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
The user provided a Slack webhook `https://hooks.slack.com/services/T8/B8/X8` and qualification prompt `skills/lead-qualification/qualification-prompts/saas.md` but did not specify how many top leads to include in the message alert. How many leads should be highlighted?
| Checked | Without skill | With skill |
|---|---|---|
| Defaults to including the top 5 qualified leads in the Slack notification. | Missed | Passed |
The instructions your model reads when the skill loads.
Search Luma for events by topic and location, extract all attendees and hosts, qualify them against your ICP, export to a Google Sheet, and send a Slack alert with the top leads.
This is a 5-step pipeline that chains together luma-event-attendees, lead-qualification, Google Sheets output, and Slack alerting.
Before doing anything, make sure you have clear answers to these questions. If the user's prompt already covers them, skip ahead. Otherwise, ask:
skills/lead-qualification/qualification-prompts/? If not, what's their ICP at a high level? (Can use lead-qualification intake mode to build one)Present these as a numbered list. The user can answer in one shot.
Use the luma-event-attendees skill with multiple keyword variations to maximize coverage.
Generate 3-5 keyword variations combining the user's topic with their location. Run them all in parallel:
# Run each search variation in parallel
python3 skills/luma-event-attendees/scripts/scrape_event.py --search "AI San Francisco" --output /tmp/luma_search_1.csv
python3 skills/luma-event-attendees/scripts/scrape_event.py --search "Growth Marketing San Francisco" --output /tmp/luma_search_2.csv
python3 skills/luma-event-attendees/scripts/scrape_event.py --search "GTM San Francisco" --output /tmp/luma_search_3.csv
After collecting results, filter out events outside the user's specified timeframe using the event_date column. Luma search returns events from all time periods, so this step is essential to avoid stale leads. If no timeframe was specified, default to the past 30 days.
test cases passed, vs 5 / 18 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.