event-prospecting-pipeline

Find attendees at conferences/events, research their companies, qualify against ICP, and launch outreach

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/lead-generation/playbooks/event-prospecting-pipeline/SKILL.md

Quality

Content

86%Weight 40%Scale 1-5

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

This is a well-structured orchestration playbook: terse, correctly routed to named sub-skills, with explicit human validation checkpoints before risky stages. Its only weaknesses are the absence of concrete invocation examples for the sub-skills and any error-handling guidance when a pipeline stage comes up empty.

Suggestions

Add one concrete invocation example per step (e.g., how to call luma-event-attendees in Apify search mode) so guidance is copy-paste executable rather than capability-level.

Add error-recovery branches for common failures — empty attendee lists, no matching events for a topic, or no email found by company-contact-finder — to close the workflow clarity gap.

Specify the Step 6 export mechanics (sheet naming, sharing, or CSV path) and the Step 7 approval mechanism so the final stages match the concreteness of Steps 1–5.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero padding: every line is a routing rule, output spec, or step instruction (e.g., "Skip if user just wants a raw attendee list"), with no explanations of concepts Claude already knows.	5 / 5
Actionability	Each step names the exact sub-skill to use with decision rules for choosing between them, plus a concrete output column spec; however, no invocation examples are given, and Step 2 ("Capability: Web search") and Step 6 ("Google Sheets or CSV export") stay at the capability level without specifics, leaving minor gaps.	4 / 5
Workflow Clarity	A clear 7-step sequence with an explicit Human Checkpoints section that validates the risky batch outreach operation ("After Step 6: Review final list and email copy before launching outreach"), satisfying the batch-operation validation requirement; it falls short of a 5 because there are no error-recovery loops for failure cases like an empty attendee list or unfound contacts.	4 / 5
Progressive Disclosure	The body is a compact overview that appropriately delegates all detail to named sub-skills, includes one clearly signaled one-level-deep pointer to a sibling skill, and is organized into clean When to Use / Steps / Human Checkpoints sections with no content that should be split into bundle files.	5 / 5
	Total	18 / 20 Passed

Description

66%Weight 40%Scale 1-5

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

The description communicates a concrete, well-scoped pipeline in third person with good domain keywords, but it entirely lacks a 'when to use' trigger clause and drops two pipeline stages (decision-maker contact finding, deduplication). Adding explicit trigger guidance and natural synonyms like 'leads' and 'prospecting' would raise it substantially.

Suggestions

Append a trigger clause such as 'Use when the user wants leads, prospects, or contacts from a conference, meetup, or event URL' to fix the missing 'when' that caps completeness at 3.

Include natural synonyms users would say — 'leads', 'prospecting', 'speakers', 'contact info' — to improve trigger term coverage from good to comprehensive.

Mention the contact-finding and deduplication stages (e.g., 'find decision-maker emails and deduplicate against prior outreach') so the described pipeline matches the skill's actual scope.

Dimension	Reasoning	Score
Specificity	"Find attendees at conferences/events, research their companies, qualify against ICP, and launch outreach" lists four concrete pipeline actions, but omits contact-finding and dedup that the body treats as core steps, so coverage has minor gaps rather than being comprehensive.	4 / 5
Completeness	The 'what' is clear (a four-stage pipeline), but there is no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural domain terms are present ("attendees", "conferences", "events", "ICP", "outreach"), but common variations users would say — "leads", "prospecting", "speakers", "contact info" — are missing, matching the 'good coverage, a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The event-attendee framing carves a distinct niche with distinct triggers, but the generic "research... qualify... outreach" tail overlaps with general lead-generation skills (a sibling Luma pipeline skill exists), so overlap risk is minor rather than minimal.	4 / 5
	Total	15 / 20 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/playbooks/event-prospecting-pipeline/SKILL.md
Commit: a9f4676

Reviewed: 24 minutes 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.