subject-line-lab

Use when the user asks to "generate subject line variants", "pre-score my subject lines", or "will this subject get truncated / trigger spam filters"; produces a labeled subject + preheader variant set and a per-variant heuristic pre-score card — spam-trigger flags, length/truncation across desktop + mobile, emoji-count, and the inbox preview render (from-name + subject + preheader) — before any test is run. Not for the body copy or CTA — use email-creative-builder; not for the A/B test design or significance read — use send-experiment-designer; not for the profile-weighted EQS or the S1/S2/N1/D1 vetoes — use email-quality-auditor. 邮件主题行生成/主题行预打分/截断与垃圾词检查

Quality

92%

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

85%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, highly actionable instruction skill body: concrete 8-step workflow with validation checkpoints, decision gates, a quality-bar checklist, and appropriately split-out reference files. The main weakness is conciseness — the scope/non-goal boundaries are restated in three places and the framework jargon is heavy, so a tightening pass would improve token efficiency.

Suggestions

Consolidate the 'not for X — use Y' scope boundaries into one place (e.g. the Scope guard paragraph) and have the Instructions and Next Best Skill sections reference it rather than restate it.

Trim repeated SEND-framework shorthand (EQS / S1·S2·N1·D1 / 'E lever') where a single clear statement of ownership suffices.

The intro paragraph and the Scope guard paragraph overlap heavily — merge them to remove the duplication.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the scope boundaries ('not for X — use Y') are restated three times — in the intro scope guard, the Instructions, and the Next Best Skill section — and the SEND/EQS/S1·S2·N1·D1 framework vocabulary recurs heavily, so it could be tightened.	3 / 5
Actionability	Eight concrete numbered steps (count chars, compare to render limits, scan the spam-trigger patterns, count emoji, assemble from-name+subject+preheader, rank+cut), real referenced pattern tables, example Quick Start prompts, and a Quality bar checklist give Claude everything needed to execute directly.	5 / 5
Workflow Clarity	Clear 8-step sequence with explicit validation checkpoints — a 'Done when' contract, a 'Quality bar before handoff' checklist, and Decision Gates (Stop and ask vs Continue silently) — plus an error-recovery loop ('If any item fails, fix it or report it in the handoff — do not ship silently').	5 / 5
Progressive Disclosure	Well-structured overview with clearly signaled one-level-deep references — the spam-trigger pattern list is split into the verified references/spam-trigger-checklist.md, render limits/angle table into subject-line-specs.md, and a dedicated Reference Materials section makes navigation easy.	5 / 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 strong description: explicit 'Use when' trigger phrases, concrete multi-action capability list, and sharp boundary clauses that distinguish it from sibling skills. The only blemish is the redundant trailing Chinese summary echo ('邮件主题行生成/主题行预打分/截断与垃圾词检查'), which duplicates the summary field and adds tokens without new information.

Suggestions

Drop the trailing Chinese echo '邮件主题行生成/主题行预打分/截断与垃圾词检查' from description — it duplicates the summary field and pads the description without adding trigger or capability information.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produces a labeled subject + preheader variant set', 'per-variant heuristic pre-score card — spam-trigger flags, length/truncation across desktop + mobile, emoji-count, and the inbox preview render' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both: an explicit 'Use when the user asks to...' clause with concrete triggers (when) and a clear statement of the variant set + pre-score card output (what).	5 / 5
Trigger Term Quality	Quoted natural trigger phrases users would actually say — 'generate subject line variants', 'pre-score my subject lines', 'will this subject get truncated / trigger spam filters' — covering the core variations.	5 / 5
Distinctiveness Conflict Risk	Clear niche (pre-test subject/preheader pre-scoring) with explicit boundary clauses — 'Not for the body copy or CTA — use email-creative-builder; not for the A/B test design ... use send-experiment-designer; not for the profile-weighted EQS ... use email-quality-auditor' — minimizing wrong-skill triggers.	5 / 5
	Total	20 / 20 Passed

Validation

75%

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 — 12 / 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: 24 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: email/engage/subject-line-lab/SKILL.md
Commit: 64562bc

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.