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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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.

A highly actionable, well-sequenced operational skill with concrete commands, payloads, and error-recovery loops. Its weaknesses are repeated payload/sorting guidance across sections and a monolithic single-file structure where the internal-sources catalog and query contract would fit better as separate reference files.

Suggestions

Consolidate the repeated OPPORTUNITY payload example: keep it once in 'Semantic Query Contract' and have 'Fastest Metric Path' and 'Examples' reference or vary it, cutting duplicated JSON blocks.

Move the 'Deepline Internal Analytics Sources' table and dashboard source-of-truth list into a references/ file (e.g. references/internal-sources.md) linked one level deep, keeping SKILL.md as an overview.

Merge the label-plus-date-start sorting guidance from 'Fastest Metric Path' steps 5-6 into 'Latest Periods Are Not Row Limits' so the rule lives in one place.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific (CLI commands, payload contract, error table are all non-obvious), but the OPPORTUNITY payload shape is repeated across 'Fastest Metric Path', 'Semantic Query Contract', and 'Examples', the label/date-start sorting guidance is stated twice, and the internal-sources table carries long caveat prose that could be tightened.	3 / 5
Actionability	Fully executable throughout: exact CLI invocations with complete JSON payloads in both typed and legacy forms, a bad/good filter comparison, and an error-pattern-to-response table. Copy-paste ready for the common cases.	5 / 5
Workflow Clarity	The 'Standard Loop' is a clearly sequenced 6-step process with an explicit cheap-pilot validation checkpoint, and 'Error Handling' defines fix-and-rerun feedback loops ('fix the table/metric/dimension/filter and rerun before claiming an answer'), with a decision matrix up front. Operations are read-only, so no destructive-operation cap applies.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and everything — the internal analytics source catalog, the query contract, and the error catalog — is inlined in a ~280-line SKILL.md. Sections are well-headed, but substantial reference material that belongs in separate one-level-deep files is inlined with no navigation to them.	3 / 5
	Total	16 / 20 Passed

Description

81%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.

A strong description with excellent trigger coverage and explicit conflict-avoidance routing to deepline-gtm. Its main weakness is that capabilities are implied via triggers rather than stated as concrete actions.

Dimension	Reasoning	Score
Specificity	The description names the analytics domains ('business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse') and the exact tool IDs, but never states concrete actions as actions — the doing ('run semantic queries') is only implied through the trigger-phrase list, so it falls short of the several-explicit-actions anchor.	3 / 5
Completeness	The 'when' is explicit with concrete trigger phrases, and the 'what' is present but embedded inside the when-clause ('answering … questions with Deepline') rather than stated as a standalone capability statement, leaving it slightly less explicit than the anchor-5 example.	4 / 5
Trigger Term Quality	Concrete natural phrases a user would actually say — 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer' — plus exact tool names (snowflake_get_semantic_layer / snowflake_run_semantic_query) give comprehensive coverage with synonyms; nothing common is missing.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Deepline/Snowflake semantic-layer analytics) with an explicit routing boundary — 'Skip prospecting, enrichment, contact finding, outbound, or personalization workflows; use deepline-gtm for those' — minimizing wrong-skill triggers.	5 / 5
	Total	17 / 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: getaero-io/gtm-eng-skills
Path: skills/deepline-analytics/SKILL.md
Commit: a9b9731

Reviewed: 6 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.