send-experiment-designer

Use when the user asks to "design an email A/B test", "set up a multivariate subject/CTA test", "run a send-time test", "build a hold-out group", or "is this email result statistically and practically material?"; produces a falsifiable hypothesis, one-variable-per-cell matrix, sample-size/MDE/duration/power plan, and an effect/uncertainty read from own ESP data. Applies only a precommitted owner-approved action rule; the helper never chooses a business action. Not for EQS/vetoes or writing the email. 邮件AB测试设计/多变量测试/发送时间测试/留出组/显著性判定

Quality

94%

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

88%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 strong, expert-grade instruction skill: executable compute path, a sequenced workflow with decision/validation checkpoints, and well-structured reference navigation. Minor conciseness and progressive-disclosure tightening would lift it to top marks.

Suggestions

Move the ±1pt/±2pt/±3pt/±5pt sample-size reference table into a referenced file (e.g. references/sample-size.md) and keep only the `experiment.py samplesize` call inline, reducing body tokens and deepening progressive disclosure.

Trim didactic restatements like 'A subject-line winner that lifts opens but spikes unsubscribes is a guardrail breach, not a win' — the guardrail definition already implies it — to improve conciseness.

Confirm the outbound reference paths (e.g. ../../../references/measurement-protocol.md, ../../../CONNECTORS.md) resolve within the installed plugin so the 'one level deep' navigation claim is verifiable.

Dimension	Reasoning	Score
Conciseness	Dense and efficient — mode tables, a reference sample-size table, and the executable `experiment.py` command earn their tokens. A few explanatory sentences (e.g. defining a subject-line winner vs guardrail breach) edge toward over-explanation but stay justified; not a 5 because some prose could be trimmed.	4 / 5
Actionability	Provides a fully executable, copy-paste-ready command with exact flags (`python3 .../experiment.py proportion --control <events> <n> --variant <events> <n> --alpha <alpha> --min-lift <relative-bar>`), concrete formulas (duration = recipients/cell × cells ÷ sendable/day), and a worked reference table — covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced 9-step workflow with explicit validation checkpoints: NEEDS_INPUT on missing inputs, the no-peeking rule, receipt/hash binding with `binding_status: incomplete`, Bonferroni adjustment for multiple cells, and `decision: UNDECIDED` when the owner/rule is missing.	5 / 5
Progressive Disclosure	Well-organized into Quick Start, Skill Contract, Data Sources, Instructions, Reference Materials, and Next Best Skill with clearly signaled one-level references. Not a 5 because the body inlines several reference details (sample-size table, statistical-method notes) and the referenced paths resolve outside the bundle with no in-bundle `references/` files to confirm.	4 / 5
	Total	18 / 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 high-quality description: third-person voice, concrete capabilities, natural trigger phrases, and an explicit negative-scope boundary. It fully answers what the skill does and when to invoke it with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produces a falsifiable hypothesis, one-variable-per-cell matrix, sample-size/MDE/duration/power plan, and an effect/uncertainty read from own ESP data' — giving comprehensive, specific coverage rather than vague verbs.	5 / 5
Completeness	Explicitly answers both 'what' (the hypothesis/matrix/plan/read outputs) and 'when' (a clear 'Use when the user asks to...' clause with concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Uses natural quoted trigger phrases users would actually say ('design an email A/B test', 'set up a multivariate subject/CTA test', 'run a send-time test', 'build a hold-out group', 'is this email result statistically and practically material?') with strong synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (email experiment design + significance read) and explicitly carves out boundaries with 'Not for EQS/vetoes or writing the email', minimizing overlap with sibling 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: 17 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: email/deliver/send-experiment-designer/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.