lead-qualification

Lead qualification engine with conversational intake. Asks structured questions to understand your qualification criteria, generates a reusable qualification prompt, then batch-enriches leads via Apify LinkedIn scraping and scores them with parallel processing. Outputs qualified/disqualified verdicts with confidence scores and reasoning to CSV or whatever output format the user prefers. Supports calibration mode for prompt refinement.

Quality

70%

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/capabilities/lead-qualification/SKILL.md

Quality

Content

73%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.

The skill body is a well-structured, actionable workflow with strong sequencing and explicit validation/feedback loops for a batch operation. Its main weaknesses are minor marketing-style padding that hurts conciseness and a monolithic structure that underuses progressive file-splitting.

Suggestions

Trim evaluative padding ('MUCH faster and cheaper', 'dramatically improving speed and consistency') to state facts plainly and recover token budget.

Move the 22-question intake bank and/or the parallelization protocol into a reference file (e.g. references/intake-questions.md) referenced from SKILL.md to improve progressive disclosure.

Convert the illustrative 'Task: ...' parallelization block into a concrete, copy-pasteable example of the actual Task tool call to lift actionability to fully executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly procedural and efficient (intake questions, parallelization protocol, output templates earn their place), but padded marketing lines like 'This is MUCH faster and cheaper...' and 'dramatically improving speed and consistency' plus some restated explanations keep it at the 'mostly efficient with some unnecessary explanation' anchor rather than lean.	3 / 5
Actionability	Concrete executable guidance is present throughout — the `python3 .../enrich_leads.py` invocation with flags, the full qualification-prompt markdown template, and the calibration table format — but the parallel Task-agent block is rendered as illustrative pseudocode rather than literal copy-paste commands, leaving minor gaps.	4 / 5
Workflow Clarity	The two-phase pipeline (Intake rounds 1-3, then Steps 1-5) is clearly sequenced with explicit validation checkpoints: the calibration approval loop ('Repeat until the user approves'), per-batch retry-on-failure, and the completeness invariant ('total qualified + disqualified + failed = total input leads'), satisfying the feedback-loop requirement for a batch operation.	5 / 5
Progressive Disclosure	Content is well organized into clearly headed phases and the one external reference (scripts/enrich_leads.py) is real and clearly signaled; it is not a 5 because the document is a monolithic ~360-line body where the intake-question bank or parallelization protocol could arguably live in separate reference files.	4 / 5
	Total	16 / 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 is rich in specific capabilities and has a clear, distinctive niche, but it lacks an explicit 'Use when...' trigger clause and slips into second-person voice ('your qualification criteria'), which caps completeness and lowers specificity per the rubric guidelines.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to qualify sales leads or prospects against custom criteria.'

Convert second-person phrasing to third person ('understand the user's qualification criteria') to avoid the voice penalty.

Add common synonyms/file extensions such as 'prospects', 'sales leads', and '.csv' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Asks structured questions', 'generates a reusable qualification prompt', 'batch-enriches leads via Apify LinkedIn scraping', 'scores them with parallel processing', 'Outputs qualified/disqualified verdicts with confidence scores and reasoning'), which would anchor at 5, but the second-person phrasing 'understand your qualification criteria' triggers the voice penalty that reduces specificity by 1.	4 / 5
Completeness	The 'what' is clearly and comprehensively stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3 with 'when' only weakly implied.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('lead qualification', 'leads', 'qualification criteria', 'LinkedIn scraping', 'Apify', 'CSV') that users would plausibly say, but missing common synonyms like 'prospects' or 'sales leads' and any file extensions, so it sits above the 'some relevant keywords' anchor but not at comprehensive.	4 / 5
Distinctiveness Conflict Risk	The Apify LinkedIn enrichment + confidence-scored lead qualification niche is mostly distinct with low overlap risk, but the absence of explicit trigger phrases leaves minor ambiguity versus other sales/prospect skills, placing it just below the clear-niche anchor.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gooseworks-ai/goose-skills
Path: skills/lead-generation/capabilities/lead-qualification/SKILL.md
Commit: 2523432

Reviewed: 7 days 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.