on-page-seo-auditor

Audit on-page SEO: titles, headers, images, links with scored report and fix priorities. 页面SEO审计/排名诊断

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/on-page-seo-auditor/SKILL.md

Quality

Content

71%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.

The content is well-structured with strong progressive disclosure and actionable, template-driven guidance supported by real reference files. Main weakness is verbosity from repeated template patterns and duplicated reference links that could be consolidated.

Suggestions

Consolidate the repeated "Reference: See references/audit-templates.md" lines (steps 5-11) into a single block-pointing note to reduce token waste.

Trim the duplicated ✅/⚠️/❌ criterion tables for title/meta/headers by referencing a shared template once, keeping only element-specific criteria inline.

Add a brief error-recovery feedback loop (e.g., re-run a failed check after fixing) to push workflow_clarity toward the score-5 anchor.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the title/meta/header template blocks repeat the same ✅/⚠️/❌ table pattern and the "Reference: See references/audit-templates.md" link is repeated verbatim across steps 5-11, adding padding that could be tightened.	3 / 5
Actionability	Provides concrete, structured output templates with criteria tables, per-element scoring ("Title Score: [X]/10"), issue lists, and recommended rewrites, giving mostly executable guidance with only minor gaps appropriate to an instruction-only audit skill.	4 / 5
Workflow Clarity	A clear 11-step audit sequence is paired with an explicit "Validation Checkpoints" section covering both input and output validation; the operation is read-only/non-destructive so the destructive cap does not apply, though error-recovery feedback loops are lighter than the score-5 anchor.	4 / 5
Progressive Disclosure	SKILL.md acts as a concise overview with well-signaled, one-level-deep references to three real bundle files (audit-example.md, audit-templates.md, scoring-rubric.md), with steps 5-11 and the example appropriately deferred to those files, yielding easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

61%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.

The description is specific and well-scoped with good multilingual trigger coverage, but it lacks an explicit "Use when..." trigger clause in the description field itself, capping completeness. Tightening to add explicit when-guidance would raise it.

Suggestions

Add an explicit "Use when..." clause to the description (e.g., "Use when auditing a page's on-page SEO health or checking heading structure and keyword placement") to satisfy completeness.

Vary the action verbs beyond the repeated "audit" to better match the score-5 specificity anchor (e.g., "scores titles, checks header hierarchy, flags image alt-text gaps").

Include one or two natural user phrasings (e.g., "SEO score", "page optimization check") directly in the description rather than only in frontmatter triggers.

Dimension	Reasoning	Score
Specificity	Lists several concrete audited elements ("titles, headers, images, links") and concrete outputs ("scored report and fix priorities"), giving broad coverage, though the single repeated "audit" verb is less varied than the score-5 anchor's distinct actions.	4 / 5
Completeness	The description gives a clear "what" (audit on-page SEO elements with a scored report and fix priorities) but contains no explicit "Use when..." clause, which per the rubric caps completeness at 3 even though a separate when_to_use frontmatter field exists.	3 / 5
Trigger Term Quality	Includes natural terms ("on-page SEO", "titles, headers, images, links", "scored report", "fix priorities") plus CJK synonyms ("页面SEO审计/排名诊断"), with only a few common user phrasings absent from the description field itself.	4 / 5
Distinctiveness Conflict Risk	"On-page SEO" audit with "scored report and fix priorities" is a clear niche distinct from generic content skills, with only minor overlap risk against broader SEO/content-audit skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: MODSetter/SurfSense
Path: .cursor/skills/on-page-seo-auditor/SKILL.md
Commit: d96e29d

Reviewed: 8 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.