content-refresher

Refresh outdated posts with current stats, new sections, freshness signals to restore rankings.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

Quality

76%

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

85%

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 sequenced workflow, validation checkpoints, and good progressive disclosure into real reference files. Its main weakness is conciseness — redundant introductory sentences and large inline placeholder tables that could be trimmed or pushed to references.

Suggestions

Remove the duplicated lead sentence in "When This Must Trigger" and tighten the opening paragraph, which restates the skill's purpose already covered by the description.

Move the large step 1–4 placeholder tables into refresh-templates.md alongside steps 5–9, keeping only the criteria and a compact example inline in SKILL.md.

Trim boilerplate around "System role" / "System Mode" that does not change Claude's behavior.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable templates, but the opening paragraph restates the obvious and the "When This Must Trigger" section repeats its lead sentence twice; steps 1–4 also embed large placeholder tables that could be tightened or moved to references.	2 / 3
Actionability	Concrete, specific guidance throughout — explicit refresh criteria ("Published more than 6 months ago"), ready-to-fill output tables, and itemized SEO/GEO update checklists — giving copy-paste-ready structure for an instruction skill.	3 / 3
Workflow Clarity	A clear 9-step sequence is paired with dedicated Input/Output Validation Checkpoints and a pre-republish gate check ("Run content-quality-auditor on refreshed content"), matching the anchor for explicit validation steps and feedback loops.	3 / 3
Progressive Disclosure	Detailed templates for steps 5–9 are offloaded to real one-level-deep references (refresh-templates.md, refresh-example.md, content-decay-signals.md, all present in ./references/) with clearly signaled links and a Reference Materials index.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 occupies a clear niche, but it omits an explicit "Use when..." trigger and has only moderate coverage of natural user phrasing. Adding an explicit trigger clause and broader natural-language keywords would raise completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when updating old articles, reviving pages with dropping traffic, or refreshing content for a new year."

Expand natural trigger keywords users actually say ("traffic is dropping", "rankings declined", "content decay", "update old blog post") rather than relying on the single phrase "outdated posts".

Move the Chinese gloss (内容更新/排名恢复) into the triggers/metadata and keep the description itself a clean third-person English sentence.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — "Refresh outdated posts with current stats, new sections, freshness signals to restore rankings" — matching the anchor that lists several specific actions rather than a single vague verb.	3 / 3
Completeness	It clearly states what the skill does but has no explicit "Use when..." clause; the trigger is only implied from "outdated posts," so per the rubric a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms like "refresh outdated posts" and "restore rankings" appear, plus a Chinese gloss (内容更新/排名恢复), but common variations a user would actually say (e.g. "traffic dropping", "content decay", "update old article") are missing.	2 / 3
Distinctiveness Conflict Risk	The SEO/GEO content-refresh niche is specific and unlikely to be confused with unrelated skills, fitting the "clear niche with distinct triggers" anchor.	3 / 3
	Total	10 / 12 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: 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.