deepline-ads-audiences

Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal email hashes', 'increase Facebook match rate', 'Google ads audience', 'Meta audience', 'FB audience', or any workflow that turns CRM/customer/contact data into paid ads upload lists. Skip for outbound prospecting sequences, cold email, or pure campaign copywriting.

Quality

90%

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

Quality

Content

81%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.

Highly actionable and well-sequenced with strong validation gates for a credit-spending batch workflow. Its weakness is conciseness: long prose essays and detailed empirical tables inflate the token budget, and some inline detail could be moved to the referenced files.

Suggestions

Move the measured 5,549-row hit-rate/spend tables and the six-layer coverage comparison into a referenced file (e.g. shared/measured-results.md), keeping only the decision-relevant takeaway inline.

Tighten the narrative essay sections ('Ask about suppression before targeting', 'Expect different lift per platform', 'Explain the shape before you spend') to a few bullets each so the operational judgment survives without the prose padding.

Extract the LinkedIn URL Backfill ladder (Step 3 sub-section) into its own referenced recipe, since it is a self-contained sub-workflow rather than core audience-build steps.

Dimension	Reasoning	Score
Conciseness	The body is ~490 lines with several prose essay sections ('Ask about suppression before targeting', 'Explain the shape before you spend') and detailed empirical tables (5,549-row measured results, six comparison layers) that, while accurate and domain-specific, could be tightened without losing signal.	3 / 5
Actionability	Provides copy-paste-ready, fully executable commands throughout — exact `deepline` CLI invocations, `deepline plays run` commands with complete JSON payloads, and concrete tool names with payload shapes covering the common upload cases.	5 / 5
Workflow Clarity	A clear 7-step Default Workflow expanded into Steps 1–6 with explicit validation checkpoints (account discovery before upload, Step 4 identifier audit, `deepline plays check` before run, approval/budget gates) and feedback loops for this batch/credit-spending operation.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references (Decision Matrix 'Read' column, '→ Read' pointers, Reading guide table) and clear section structure, but the main file carries heavy inline detail (empirical tables, the LinkedIn backfill ladder) that could be split into referenced files; the referenced bundle files are also not present in the package.	4 / 5
	Total	17 / 20 Passed

Description

100%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, specific description that names concrete actions, platforms, natural trigger phrases, and a clear negative boundary. It answers what, when, and what-not-to-use-for with minimal fluff.

Dimension	Reasoning	Score
Specificity	Names four concrete actions ('building, enriching, auditing, or uploading') and three specific platform targets (Google Customer Match, Meta/Facebook Custom Audiences, LinkedIn Matched Audiences), giving comprehensive coverage of concrete capabilities.	5 / 5
Completeness	Explicitly answers both what (build/enrich/audit/upload B2B paid ads audiences to named platforms) and when (concrete trigger phrases), and adds a negative 'Skip for...' boundary clause.	5 / 5
Trigger Term Quality	Lists many natural trigger phrases a user would actually say — '/deepline-ads-audience', 'upload this audience', 'increase Facebook match rate', 'Meta audience', 'FB audience' — plus synonyms and slash-command variants.	5 / 5
Distinctiveness Conflict Risk	Clear niche (B2B paid ads audience upload) with distinct triggers and an explicit exclusion ('Skip for outbound prospecting sequences, cold email, or pure campaign copywriting') that minimizes conflict with adjacent skills.	5 / 5
	Total	20 / 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-ads-audiences/SKILL.md
Commit: 3bb8968

Reviewed: 3 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.