gtm-enrichment-smart

Multi-provider waterfall lead enrichment. Takes an email (+ optional name) and returns person + company data by cross-referencing cheap APIs first, using expensive AI agents only as fallback. Cost-efficient (~$0.04-$0.10/lead) with confidence scoring and full error visibility.

Quality

65%

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/gtm-enrichment-smart/SKILL.md

Quality

Content

62%

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

The workflow is clearly sequenced with strong gating and error visibility, but actionability is undercut by malformed curl JSON bodies and the skill is a monolithic wall of text with no reference files. Tightening the redundant cost/example sections and splitting the output schema into a reference file would help.

Suggestions

Fix the malformed curl -d JSON in 1a, 3a, 3b, and 4a so the request bodies are valid, copy-paste-executable JSON objects.

Move the full Output Format JSON schema and/or the Cost Tracking table into a references/ file and link to it, reducing inline bulk.

Trim the Example 'Expected flow' section, which re-narrates phases already detailed above, to avoid redundancy with the Workflow section.

Dimension	Reasoning	Score
Conciseness	Content is mostly procedural and information-dense (curl commands, field paths, cost/latency), but repeats information already stated inline — the Cost Tracking table restates per-call costs, and the Example section re-narrates every phase — so it could be tightened.	2 / 3
Actionability	Field extraction lists, merge rules, and output schema are concrete, but several curl examples are malformed JSON and not copy-paste executable (e.g., Apollo people/match, Sixtyfour enrich-lead/company, and Brand.dev ai/products all close the -d object early then dangle fields outside it), matching the incomplete/pseudocode anchor.	2 / 3
Workflow Clarity	Phases 0-5 are explicitly sequenced with parallel/conditional gates, merge and confidence rules, and an error-visibility block requiring every call be logged with status — a clear sequence with checkpoints.	3 / 3
Progressive Disclosure	There are no bundle files (references/scripts/assets absent), so everything is inline in a ~418-line SKILL.md; the full JSON output schema, cost table, and per-call field lists are content that could be split into reference files, matching the some-structure-but-inline anchor.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 concrete and distinct, but lacks an explicit 'Use when...' trigger clause, which caps completeness at 2 and limits trigger-term coverage. It reads in correct third-person voice with no first/second-person penalties.

Suggestions

Add an explicit trigger clause, e.g. 'Use when enriching a lead from an email, looking up person/company info for a contact, or building a prospect list from email addresses.'

Surface natural user phrasings ('enrich this lead', 'look up this contact', 'find company info from an email') to raise trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Takes an email (+ optional name) and returns person + company data', 'cross-referencing cheap APIs first', 'expensive AI agents only as fallback', 'confidence scoring and full error visibility' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	The 'what' is clearly answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	'lead enrichment', 'email', 'person + company data' are reasonably natural, but there is no explicit trigger list and common phrasings a user would actually say (e.g., 'enrich this lead', 'look up this contact') are not surfaced, matching the some-relevant-keywords-but-missing-variations anchor.	2 / 3
Distinctiveness Conflict Risk	'Multi-provider waterfall lead enrichment' with cost/confidence framing carves a clear niche unlikely to trigger for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	10 / 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/capabilities/gtm-enrichment-smart/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.