content-quality-auditor

Publish-readiness gate: 80-item CORE-EEAT audit with weighted scoring, veto checks, and fix plan. 内容质量/EEAT评分

Quality

73%

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/content-quality-auditor/SKILL.md

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.

The body is a highly actionable, well-sequenced audit workflow with strong validation checkpoints and a real local reference file. Its main weakness is conciseness — repeated triggers and redundant prompt examples add tokens without adding guidance.

Suggestions

Collapse the four Quick Start prompt variations into one or two canonical examples plus a note that phrasing is flexible, removing the redundancy.

Remove or compress the 'When This Must Trigger' list since the same triggers already appear in the frontmatter metadata, keeping only the PostToolUse hook note that is unique to the body.

Trim the Tips for Success section to the items Claude could not infer (e.g., veto-first and GEO-First prioritization) and drop generic advice like 'use the weighted score, not just the raw average'.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete templates, but it carries redundancy — trigger conditions are repeated from the frontmatter, Quick Start lists four near-identical prompt variations, and the Tips for Success section explains points Claude could infer — so it could be tightened.	3 / 5
Actionability	It provides copy-paste-ready markdown templates, exact scoring rules (Pass=10/Partial=5/Fail=0), named veto items (T04, C01, R10), explicit thresholds (300/150 words), and a fully specified report structure covering the common audit cases.	5 / 5
Workflow Clarity	The four-step audit process is clearly sequenced with an emergency-brake veto check up front, explicit Input/Output Validation Checkpoints, decision-gate stop/ask rules, and a re-audit feedback loop for verifying improvements.	5 / 5
Progressive Disclosure	Structure is good with clearly signaled one-level-deep references to the real local bundle file references/item-reference.md, but the CORE-EEAT benchmark is pointed to via an external GitHub URL rather than a bundled local file, leaving a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

66%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 distinguishes a clear niche, but it lacks an explicit 'Use when...' trigger clause, leaving the activation condition only weakly implied. Adding concrete user-facing trigger phrases would lift completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when...' clause with natural trigger phrases such as 'Use when checking if content is ready to publish, grading an article, or running an E-E-A-T/content quality audit.'

Soften the technical emphasis by adding at least one casual user phrase (e.g., 'grade my article' or 'is this ready to publish') so the description mirrors what users actually say.

Tighten 'fix plan' to a more specific action like 'prioritized fix plan with weighted-impact ranking' to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — '80-item CORE-EEAT audit', 'weighted scoring', 'veto checks', and 'fix plan' — giving comprehensive coverage with only minor gaps such as the slightly generic 'fix plan'.	4 / 5
Completeness	The 'what' is clear and specific, but there is no explicit 'Use when...' trigger clause; the 'when' is only weakly implied by 'Publish-readiness gate', which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	It surfaces relevant keywords ('publish-readiness', 'CORE-EEAT audit', 'EEAT评分', 'content quality') but leans technical and omits casual user phrasings like 'is this ready to publish' that appear only in the body, not the description.	4 / 5
Distinctiveness Conflict Risk	The '80-item CORE-EEAT audit' and 'publish-readiness gate' niche is mostly distinct with minimal conflict risk, though it sits within a broader SEO/GEO skill library where slight overlap with sibling content skills is possible.	4 / 5
	Total	15 / 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: MODSetter/SurfSense
Path: .cursor/skills/content-quality-auditor/SKILL.md
Commit: 3448772

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.