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. Use this skill whenever someone wants to find qualified leads from events, prospect event attendees, or run an event-based lead gen workflow. Also triggers for "find people at events and qualify them" or "who's attending X events that matches our ICP."

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-sequenced, highly actionable pipeline with concrete executable code and good validation checkpoints. It loses points on conciseness from inferable asides and a leftover run-specific artifact, and on progressive disclosure because it is a single large file with no split-out references.

Suggestions

Remove inferable justifications and the hardcoded '195 results' artifact (e.g., '/tmp/all_qual_results.json — all 195 results') to tighten conciseness.

Move the Cost Estimate, Example Prompts, and Troubleshooting sections into a separate reference file (e.g., TROUBLESHOOTING.md) and link to them, so the body stays a lean overview.

Confirm whether referenced scripts like skills/luma-event-attendees/scripts/scrape_event.py exist in a bundle, or add a note that they belong to a separate skill, to make the cross-skill dependencies explicit.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and tight step headings, but includes explanatory asides Claude could infer ('because writing large datasets to Sheets mid-process is slow and error-prone', 'Luma search can return events from months or years ago, so always confirm a timeframe') and a stray hard-coded run-size artifact ('all 195 results') that pad the body.	2 / 3
Actionability	Provides copy-paste-ready executable bash and python with real flags and file paths, a concrete CSV column table, Slack block JSON, and specific Rube tool names (RUBE_SEARCH_TOOLS, SLACK_SEND_MESSAGE), meeting the level-3 anchor for fully executable guidance.	3 / 3
Workflow Clarity	A clearly sequenced Step 0-5 pipeline with validation checkpoints (timeframe filter, case-insensitive dedup, parallel batch qualification merge/sort, chunked Sheet writes with retry-once, CSV fallback) and explicit error-recovery troubleshooting, matching the level-3 anchor.	3 / 3
Progressive Disclosure	No bundle files (references/scripts/assets) exist, and the SKILL.md is a single ~230-line monolith containing cost tables, troubleshooting, and example prompts inline rather than split out — well-organized into sections but not using one-level-deep references, matching the level-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what the skill does and when to use it, with natural trigger phrases in third-person voice. It is slightly verbose but every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — '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' — matching the level-3 anchor of several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (the chained pipeline of search, extract, qualify, Sheet output, Slack alert) and when via 'Use this skill whenever someone wants to find qualified leads from events... Also triggers for...', satisfying the level-3 anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would actually say: 'find qualified leads from events', 'prospect event attendees', 'run an event-based lead gen workflow', plus the quoted triggers 'find people at events and qualify them' and "who's attending X events that matches our ICP," giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	The niche is clear and specific — Luma event attendee prospecting with qualification and Sheet/Slack output — with distinctive triggers ('Luma events', 'event attendees', 'event-based lead gen') unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/lead-generation/composites/get-qualified-leads-from-luma/SKILL.md
Commit: 8866b2a

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.