serp-markup-builder

Use when the user asks to "optimize meta tags", "write title tags / meta descriptions", "add Open Graph or Twitter cards", or "generate schema / JSON-LD" for FAQ, HowTo, Article, Product, or LocalBusiness rich-result candidates. Produces title/description options, an OG+Twitter block, and validated JSON-LD for the document head. Not for body copy — use content-writer; not for crawl/index technical issues — use technical-seo-checker. 标题优化/元描述/Schema标记/结构化数据

Quality

90%

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

81%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 skill body with strong workflow sequencing and validation feedback loops, and clean one-level-deep in-bundle references. The main gaps are framework-contract boilerplate that pads the token budget, and a set of out-of-bundle references (including a missing schema_lint.py script) that cannot be verified from this skill's file listing.

Suggestions

Trim the Skill Contract / Handoff Summary / Save Results / Next Best Skill boilerplate to the essentials, or fold them into a single short reference, to reduce token overhead (addresses conciseness).

Inline at least one minimal paste-ready OG/Twitter and one FAQPage JSON-LD block in the body so the core deliverables are executable without opening references (addresses actionability).

Resolve or remove the `scripts/connectors/schema_lint.py` reference (no scripts/ dir exists in the bundle) and verify the `../../../` and `../../tune/` cross-references, marking plugin-level links as external so navigation is unambiguous (addresses actionability and progressive_disclosure).

Dimension	Reasoning	Score
Conciseness	Mostly efficient — it does not explain concepts Claude already knows and offloads detail to references — but the Skill Contract (Reads/Writes/Promotes/Done when), Handoff Summary, Save Results, and Next Best Skill sections add framework boilerplate that could be trimmed. Not a 5 because these meta-sections earn only partial token justification; not a 3 because nothing is conceptually padded.	4 / 5
Actionability	Gives concrete specs (50-60 char titles, 150-160 char descriptions, enumerated OG properties, a full schema_lint.py command, and a DOM querySelector) and points to real template references. Not a 5 because the paste-ready HTML/JSON-LD code lives in references rather than inline, and the referenced `scripts/connectors/schema_lint.py` does not exist in the bundle, leaving one executable command unverifiable.	4 / 5
Workflow Clarity	Both modes are clearly sequenced with numbered steps, explicit validation checkpoints (C01/C02 rewrite loops in meta step 5; schema pre-flight + Rich Results Test + final checklist in schema step 3), a JS-injected false-negative guard, and Stop/Continue decision gates — matching the explicit-validation-with-feedback-loops anchor.	5 / 5
Progressive Disclosure	The in-skill structure is excellent: a concise SKILL.md overview with one-level-deep references/.md files, all real, each clearly signaled with its contents. Not a 5 because several referenced paths point outside the bundle (../../../references/skill-contract.md, ../../../CONNECTORS.md, ../../../SECURITY.md, ../../tune/ sibling skills, scripts/connectors/schema_lint.py) and cannot be resolved within the provided file listing, a minor navigation gap.	4 / 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.

An exemplary description: concrete deliverables, natural trigger phrasing with synonyms, explicit what-and-when guidance, and clear boundary statements against neighboring skills. The only nit is the trailing Chinese keyword string "标题优化/元描述/Schema标记/结构化数据", which duplicates content already conveyed and is mild padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — "title/description options", "an OG+Twitter block", and "validated JSON-LD for the document head" — covering both modes comprehensively, matching the multi-action comprehensive anchor.	5 / 5
Completeness	Explicitly states what it produces (head markup assets) and opens with a concrete "Use when the user asks to..." trigger clause, satisfying both what and when with concrete trigger phrases; also adds negative scope boundaries.	5 / 5
Trigger Term Quality	Embeds natural user phrasing with synonyms across both modes — "optimize meta tags", "write title tags / meta descriptions", "add Open Graph or Twitter cards", "generate schema / JSON-LD" — plus schema types (FAQ, HowTo, Article, Product, LocalBusiness), comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	Carves a clear document-head niche and explicitly disambiguates from siblings ("Not for body copy — use content-writer; not for crawl/index technical issues — use technical-seo-checker"), minimizing conflict risk.	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: 10 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: seo-geo/implement/serp-markup-builder/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.