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

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, highly actionable instruction skill with a clear multi-step workflow, validation gates, and clean progressive disclosure to a real bundle file. The only slack is mild redundancy of the scope-guard/routing phrasing across several sections.

Suggestions

Consolidate the repeated scope-guard and next-skill routing (currently restated in Scope guard, Skill Contract, Reference Materials, and Next Best Skill) into one canonical section to save tokens.

The frontmatter carries both `when_to_use` and `description` with overlapping content; consider trimming one to avoid duplicated scope language.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation fluff, but the scope-guard and routing phrasing is restated across the Scope guard, Skill Contract, Reference Materials, and Next Best Skill sections, so it could be tightened.	2 / 3
Actionability	Concrete, specific guidance throughout — exact flag conditions (ALL-CAPS runs, '!!!', 'RE:'/'FWD:' fakery), the ~30-char mobile promise cut, the SUBJ-A/SUBJ-B id scheme, and an 8-step instruction list; appropriate for an instruction-only skill with no code expected.	3 / 3
Workflow Clarity	An explicitly numbered 8-step sequence with validation checkpoints — Decision Gates (stop/continue), a 'Quality bar before handoff' checklist, and 'fix it or report it in the handoff — do not ship silently' feedback loops.	3 / 3
Progressive Disclosure	Clear overview with one-level-deep, well-signaled references (the bundled references/spam-trigger-checklist.md is real and linked; co-owned subject-line-specs.md and shared humanizer-slop/send-benchmark references are listed in a dedicated Reference Materials section).	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 tight, third-person description that names concrete capabilities, surfaces natural trigger phrases, and disambiguates itself from three neighboring skills via explicit out-of-scope routing. Voice is correctly third person with no first/second-person slips.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'spam-trigger flags, length/truncation across desktop + mobile, emoji-count, and the inbox preview render (from-name + subject + preheader)' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('produces a labeled subject + preheader variant set and a per-variant heuristic pre-score card') and when ('Use when the user asks to...'), with explicit negative-scope triggers.	3 / 3
Trigger Term Quality	Quotes natural user phrasings — 'generate subject line variants', 'pre-score my subject lines', 'will this subject get truncated / trigger spam filters' — that a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Negative-scope clauses ('Not for the body copy...use email-creative-builder; not for the A/B test design...use send-experiment-designer; not for the...EQS...use email-quality-auditor') carve a clear niche unlikely to trigger sibling skills.	3 / 3
	Total	12 / 12 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: 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.