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

87%

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

75%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 well-organized, mostly lean instruction body with concrete sequenced guidance, a Done-when checkpoint, and clear scope guarding. It would reach the top tier by trimming the re-echoed intro/contract redundancy and co-locating (or inlining a fallback for) the referenced repo-level files.

Suggestions

Remove the restated description in the opening paragraph and any content the Skill Contract duplicates from the Instructions, since the frontmatter already carries the summary.

Add an explicit validate-then-fix feedback loop (e.g., re-check NEEDS_INPUT flags and re-confirm the funnel map is platform-neutral before saving) to lift workflow_clarity.

Either co-locate the referenced files (skill-contract.md, roas-benchmark.md, CONNECTORS.md, SECURITY.md) inside the skill bundle or inline a one-line fallback so progressive disclosure does not depend on unverifiable external paths.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding explaining what an audience or CRM is — but the opening paragraph restates the description and the Skill Contract partially re-echos the instructions, leaving minor instances that could be trimmed. It sits above the score-3 anchor (efficient with light redundancy) but not fully at 5.	4 / 5
Actionability	Seven numbered steps give concrete, specific guidance with real examples (`repeat-buyers-90d`, `high-AOV`, 14–30 day exclusion windows, ROAS A weights 0.15/0.30/0.10); as an instruction-only planning skill this is actionable without code, though it stops short of copy-paste-ready artifacts, placing it at 4 rather than 5.	4 / 5
Workflow Clarity	A clearly sequenced 7-step process with an explicit "Done when" checklist serving as a validation checkpoint and NEEDS_INPUT flags for missing columns; this is a research/planning skill so the destructive-batch cap does not apply, but it lacks an explicit validate-then-fix feedback loop, holding it at 4.	4 / 5
Progressive Disclosure	Well-structured into clear sections with one-level-deep, clearly signaled references (skill-contract.md, roas-benchmark.md, CONNECTORS.md, SECURITY.md, sibling SKILL.md files); however no bundle files exist under references/scripts/assets and the referenced paths point outside the skill into a parent repo that cannot be verified here, a minor organization gap keeping it below 5.	4 / 5
	Total	16 / 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.

An exemplary description: third-person, concrete, with explicit "Use when" triggers and clear negative boundaries against sibling skills. Both the what and the when are answered with natural phrasing a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — "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" — covering the four output buckets comprehensively, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what (the four segment buckets produced) and when (a leading "Use when the user asks to..." clause with concrete trigger phrases), matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	Embeds natural quoted phrases a user would actually say — "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" — giving comprehensive natural-term coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche and names the boundaries — "Not for building account structure or match types — use campaign-architect; not for organic SERP intent — use keyword-research" — minimizing conflict risk with adjacent skills.	5 / 5
	Total	20 / 20 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: 888dd38

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.