content-refresher

Refresh outdated posts with current stats, new sections, freshness signals to restore rankings. 内容更新/排名恢复

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/content-refresher/SKILL.md

Quality

Content

52%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 well-structured with a clear step sequence, validation checkpoints, and properly signaled one-level references to existing bundle files. Its main weakness is token efficiency: it is padded with repeated framing, conceptual restatement, and placeholder-heavy templates that assume little of Claude's competence.

Suggestions

Collapse the redundant framing across 'When This Must Trigger', 'What This Skill Does', 'System role', and 'Skill Contract' into a single concise section to cut padding.

Replace placeholder-only markdown templates with one concrete worked pattern per step, moving the remaining blank scaffolds entirely into refresh-templates.md.

Tighten the 'Data Sources' and 'Tips for Success' sections by removing explanatory prose Claude can already infer about SEO/GEO concepts.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: it restates the purpose across 'When This Must Trigger', 'What This Skill Does', 'System role', and 'Skill Contract', and much of the guidance is template scaffolding Claude could infer; there are several padded sections, matching the 'noticeably verbose' anchor.	2 / 5
Actionability	Provides structured markdown templates and explicit checklists for steps, but the core 'refresh' actions are mostly fill-in-the-blank placeholders rather than executable commands or concrete editorial procedures, leaving guidance incomplete.	3 / 5
Workflow Clarity	Steps 1-9 are clearly sequenced with named validation checkpoints ('Input Validation', 'Output Validation', 'Gate check recommended') and an error-recovery path; minor gaps remain in explicit validate-fix-retry loops between steps.	4 / 5
Progressive Disclosure	SKILL.md acts as an overview with one-level-deep references to real bundle files (refresh-templates.md, refresh-example.md, content-decay-signals.md) that are clearly signaled and exist in ./references/; organization is good with only minor inlining of template-heavy content.	4 / 5
	Total	13 / 20 Passed

Description

75%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 concise, action-oriented, third person, and covers both what the skill does and a plausible trigger context, with multilingual trigger terms adding breadth. It stops short of a 5 because it omits an explicit 'Use when...' clause and a few natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('current stats', 'new sections', 'freshness signals') plus the outcome 'to restore rankings', which matches the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Clearly states the 'what' (refresh posts with stats/sections/freshness signals) and implies the 'when' (outdated posts, declining rankings), but lacks an explicit 'Use when...' trigger clause, which the guidelines cap at no higher than mid-strong; it sits at 4 rather than 5 because the when is implicit.	4 / 5
Trigger Term Quality	Includes natural user-facing phrases ('refresh outdated posts', 'restore rankings') plus multilingual equivalents ('内容更新/排名恢复'); good coverage though missing common synonyms like 'content decay' or 'update old articles'.	4 / 5
Distinctiveness Conflict Risk	The refresh/ranking-recovery niche is mostly distinct with minimal conflict risk against adjacent SEO skills, though slight overlap remains with general SEO-optimization skills; fits the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	16 / 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/content-refresher/SKILL.md
Commit: 3448772

Reviewed: 5 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.