ad-test-designer

Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试

Quality

89%

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

78%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-structured, actionable body for a complex statistical skill: concrete helper commands, a numbered workflow with binding-verification and decision-ownership checkpoints, and clean one-level-deep references to real bundle files. Minor redundancy between the Skill Contract and Instructions and placeholder-only command args keep it just short of top marks.

Suggestions

Collapse the overlap between the Skill Contract 'Done when' clause and the numbered Instructions so each criterion appears in only one place.

Add one fully worked numeric example invocation of experiment.py (real conv/n values) so the command is copy-paste runnable, not just placeholder-shaped.

Make the binding-verification step (9) an explicit validate→stop-or-proceed feedback loop mirroring the read-out gate, to lift workflow clarity to a 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no basic explanations of what an A/B test or p-value is — but the Skill Contract 'Done when' clause overlaps materially with the Instructions steps, which could be tightened.	4 / 5
Actionability	Provides a concrete, mostly copy-paste-ready command ('python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/experiment.py" proportion --control <conv> <n> --variant <conv> <n> ...') plus named subcommands (continuous, samplesize) and a decision matrix, but args remain placeholders without a fully worked numeric example.	4 / 5
Workflow Clarity	A clear 9-step sequence with explicit checkpoints (NEEDS_INPUT stop in step 1, binding verification in step 9, guardrail stop rules, UNDECIDED fallback), though it lacks a tight validate→fix→retry loop of the kind the 5-anchor exemplifies.	4 / 5
Progressive Disclosure	The SKILL.md is an overview that points one level deep to clearly signaled, real bundle files — references/test-design-guide.md and references/measurement-control.md both exist — with statistical procedures and the binding profile appropriately split out rather than inlined.	5 / 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, third-person description that states concrete capabilities, natural trigger phrases, and explicit scope boundaries against sibling skills. It fully satisfies both the 'what' and 'when' requirements with no vagueness or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (produces hypothesis/matrix/sizing plan/read-out) and when ('Use when the user asks to...') with concrete trigger phrases, matching the 5-anchor example.	5 / 5
Trigger Term Quality	Embeds natural phrases a user would actually say — 'design an A/B test', 'set up a creative/landing test', 'run an incrementality test', 'is this result statistically and practically material?' — covering synonyms across the design and read-out paths.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (experiment design + statistical interpretation) and explicitly fences off adjacent skills — 'Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop' — minimizing wrong-skill triggering.	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/orchestrate/ad-test-designer/SKILL.md
Commit: 5cd4a80

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.