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

80%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clear, checkpointed workflow, but it carries ecosystem/marketing boilerplate that hurts conciseness and relies on remote rather than bundled references for progressive disclosure. Trimming the scaffolding and localizing reference links would lift both weak dimensions.

Suggestions

Remove the library marketing line ('20 skills for SEO + GEO', ClawHub, skills.sh) and the System Mode/Skill Contract framing that do not advance the audit task, to improve token efficiency.

Convert the remote GitHub reference links to local bundle paths (e.g. references/core-eeat-benchmark.md) and ensure the full benchmark is bundled, so references are clearly signaled and one level deep.

Move the large inline report template into a references/example-report.md if it bloats the overview, keeping SKILL.md a concise pointer.

Dimension	Reasoning	Score
Conciseness	The body is well-structured but padded with ecosystem scaffolding (library marketing links, Skill Contract/State Mode framing, repeated cross-links) and some restated context that Claude does not need; it could be tightened to a leaner core.	2 / 3
Actionability	It supplies copy-paste-ready report templates, concrete scoring rules (Pass=10/Partial=5/Fail=0), the weighted-score formula, veto item IDs, and a worked N/A example — fully executable guidance.	3 / 3
Workflow Clarity	A clear four-step sequence (Preparation, CORE Audit, EEAT Audit, Scoring & Report) is paired with explicit validation checkpoints, a veto emergency brake, Decision Gates, and a Validation Checkpoints checklist with feedback loops.	3 / 3
Progressive Disclosure	References are one level deep and a local references/item-reference.md exists, but most links point to remote GitHub URLs rather than bundled local files and are not clearly signaled as local, leaving the overview-to-detail split only partly realized.	2 / 3
	Total	10 / 12 Passed

Description

82%

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, distinct, and rich in natural trigger terms, but it omits an explicit 'Use when...' guidance clause. Adding when-to-use phrasing would raise completeness from 2 to 3.

Suggestions

Append an explicit trigger clause such as 'Use when auditing content quality before publishing, or when the user asks for an E-E-A-T score or publish readiness check.'

Keep the concrete action list (audit, weighted scoring, veto checks, fix plan) but ensure the 'what' and 'when' halves are both present in the description itself rather than only in the body's when_to_use field.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — '80-item CORE-EEAT audit', 'weighted scoring', 'veto checks', and 'fix plan' — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' clause, so the trigger guidance is only implied; per the guidelines a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	It includes natural terms a user would say ('CORE-EEAT audit', 'publish-readiness', 'EEAT', 'content quality') plus multilingual variants, giving good coverage of natural trigger phrases.	3 / 3
Distinctiveness Conflict Risk	'CORE-EEAT' and 'publish-readiness gate' carve out a clear niche with distinct triggers unlikely to conflict with unrelated skills.	3 / 3
	Total	11 / 12 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: 3b319ce

Reviewed: about 14 hours 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.