audience-segment-builder

Use when the user asks to "build audience segments from my customer list", "make value-based / lookalike seed lists", "set up exclusion / suppression segments", or "map audiences to funnel stages across platforms"; turns the user's OWN customer/CRM/GA4 export into seed audiences, value-based lookalike SEED lists, exclusion/suppression segments, and a cross-platform funnel-stage targeting map, informing the ROAS A (Audience) dimension. Not for building account structure or match types — use campaign-architect; not for organic SERP intent — use keyword-research. 付费广告受众分群/种子人群/排除人群/相似人群种子

Quality

92%

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

85%Weight 40%Scale 1-3

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

A well-structured, actionable instruction skill with a clear sequenced workflow, explicit completion checklist, and well-signaled external references. Its only weakness is repetition of the scope boundary and ROAS-A framing, which keeps it from peak conciseness.

Suggestions

Collapse the campaign-architect / SERP-intent scope boundary into a single authoritative statement (e.g. keep only the 'Scope guard' section) and remove its restatement in the intro paragraph and Next Best Skill.

State ROAS A relevance and the profile weights (0.15/0.30/0.10) once in Step 1 and reference them from Step 7 rather than re-explaining the A dimension in the intro, Skill Contract, and Step 7.

Consider moving the per-step 'informing the ROAS A dimension' framing into the 'Done when' checklist so the instructions stay focused on the action.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but the campaign-architect/SERP-intent scope boundary is restated three times (intro, scope guard, and Next Best Skill) and ROAS-A relevance repeats across several sections, so it could be tightened.	2 / 3
Actionability	Provides a concrete numbered 7-step workflow with specific example segment names (repeat-buyers-90d, high-AOV), numeric windows (14–30 days), ROAS A profile weights (0.15/0.30/0.10), and copy-paste save paths — actionable guidance even without executable code.	3 / 3
Workflow Clarity	A clearly sequenced 7-step process with an explicit 'Done when' checklist and NEEDS_INPUT gating checkpoints; no destructive or batch operations are involved, so no validate-fix-retry loop is required.	3 / 3
Progressive Disclosure	Well-organized into clear sections with clearly signaled, one-level-deep references (skill-contract.md, roas-benchmark.md, CONNECTORS.md, SECURITY.md), each annotated with its purpose; no bundle files exist to verify against, but navigation is easy.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that pairs natural trigger phrases with concrete capabilities and explicit boundary-setting against neighboring skills. It fully satisfies specificity, trigger quality, completeness, and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — turning a customer/CRM/GA4 export into seed audiences, value-based lookalike SEED lists, exclusion/suppression segments, and a cross-platform funnel-stage targeting map — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (the four output buckets produced from the user's own export) and 'when' via an explicit 'Use when the user asks to...' clause, satisfying the anchor for clear what-and-when with explicit triggers.	3 / 3
Trigger Term Quality	Uses natural user-voiced triggers ('build audience segments from my customer list', 'make value-based / lookalike seed lists', 'set up exclusion / suppression segments', 'map audiences to funnel stages across platforms') that a user would actually say, with good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche and explicitly disambiguates ('Not for building account structure or match types — use campaign-architect; not for organic SERP intent — use keyword-research'), making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 13 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/research/audience-segment-builder/SKILL.md
Commit: 4a77c48

Reviewed: 9 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.