deepline-analytics

Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline. Triggers on phrases like 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query', or any use of snowflake_get_semantic_layer / snowflake_run_semantic_query. Skip prospecting, enrichment, contact finding, outbound, or personalization workflows; use deepline-gtm for those.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 highly actionable, well-sequenced skill body with strong workflow guidance and error-handling feedback loops. Its main liabilities are payload repetition across sections and the absence of any progressive disclosure via reference files for a 250-line document.

Suggestions

Deduplicate the typed-metric payload JSON: keep one canonical example in the Semantic Query Contract and reference it from Fastest Metric Path and Examples instead of repeating it.

Split the longer reference material (Allowed Concepts, Custom SQL Knobs, Choosing Semantic Objects, Error Handling) into files under references/ and link to them from SKILL.md to improve progressive disclosure for a 250-line skill.

Collapse the overlap between the Standard Loop and the Fastest Metric Path into one canonical workflow, with the fast path as a short callout rather than a second full procedure.

Dimension	Reasoning	Score
Conciseness	The body is domain-specific and free of generic concept padding, but the same typed-metric payload JSON recurs roughly three times (Fastest Metric Path, Semantic Query Contract, Examples) and the Standard Loop overlaps the Fastest Metric Path, so it could be tightened.	2 / 3
Actionability	It provides exact install/CLI commands, complete copy-paste-ready payload JSON, and a concrete error-pattern-to-response table, leaving no ambiguity about what to run.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (numbered Standard Loop and Fastest Metric Path) with validation checkpoints (pilot the smallest query, inspect returned SQL) and an explicit feedback loop ('fix the table/metric/dimension/filter and rerun before claiming an answer').	3 / 3
Progressive Disclosure	The skill is a ~250-line monolith with no bundle files in references/scripts/assets and no file splitting; well-organized sections help, but content that could live in separate reference files (Allowed Concepts, Custom SQL Knobs, Error Handling) is inline, and the under-50-line exemption does not apply.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, well-scoped description with explicit trigger phrases, clear what/when guidance, and explicit disambiguation against a sibling skill. The only weakness is that concrete capabilities are expressed largely through trigger terms rather than a distinct enumerated action list.

Dimension	Reasoning	Score
Specificity	The description names a rich domain ('business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline') but the concrete action vocabulary is essentially a single one ('answering/querying'), with distinct actions appearing mainly as trigger phrases rather than enumerated capabilities.	2 / 3
Completeness	It explicitly answers both what ('Use this skill when answering ... questions with Deepline') and when (the 'Triggers on phrases like ...' clause), and adds negative scoping, satisfying the explicit-trigger bar.	3 / 3
Trigger Term Quality	It lists natural phrases users would say ('query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query') plus the exact tool IDs, giving good coverage of likely utterances.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (Deepline analytics over the Snowflake semantic layer) and explicitly redirects overlapping work ('Skip prospecting, enrichment, contact finding, outbound, or personalization workflows; use deepline-gtm for those'), making conflict unlikely.	3 / 3
	Total	11 / 12 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: getaero-io/gtm-eng-skills
Commit: 25492ee

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.