CtrlK
BlogDocsLog inGet started
Tessl Logo

content-refresher

Use when the user asks to "update old content", "refresh content", "content is outdated", "improve declining rankings", "revive old blog posts", "this post is outdated", "traffic is declining on this page", or "rankings dropped for this article". Identifies and updates outdated content to restore and improve search rankings. Analyzes content freshness, adds new information, updates statistics, and optimizes for current SEO and GEO best practices. For writing new content from scratch, see seo-content-writer. For auditing without rewriting, see on-page-seo-auditor.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 and actionable with a strong worked example and validation checkpoints, but it is long and redundant: several reference-style tables are inlined when they belong in (or overlap with) the single reference file. Tightening would raise conciseness and progressive disclosure.

Suggestions

Move the inline "Content Decay Signal Taxonomy", "Content Lifecycle Model", and "Update Strategy by Content Type" tables into references/content-decay-signals.md (or a new reference file) and link to them, removing the duplication that currently hurts both conciseness and progressive_disclosure.

Collapse the repeated placeholder template blocks (steps 1–9) into one compact scaffold plus the worked example; the near-duplicate table structures inflate token cost without adding guidance.

Upgrade the Validation Checkpoints from static completeness lists into explicit feedback loops (e.g. "if a recommendation lacks a cited data point, re-pull from ~~search console / ~~analytics before reporting") to push workflow_clarity to the top anchor.

DimensionReasoningScore

Conciseness

The body is ~750 lines of large placeholder template tables with notable redundancy — e.g. the inline "Content Decay Signal Taxonomy" duplicates material that lives in references/content-decay-signals.md, and several reference-style tables (lifecycle model, strategy by content type) could be tightened or moved out.

3 / 5

Actionability

Provides concrete markdown templates and a fully worked cloud-hosting example covering the common refresh case, with only minor placeholder ([X]) gaps in the scaffolded blocks keeping it from the top anchor.

4 / 5

Workflow Clarity

A clear 9-step sequence is paired with an explicit Validation Checkpoints section (Input/Output), but the checkpoints are completeness lists rather than validate→fix→retry feedback loops, leaving a minor gap.

4 / 5

Progressive Disclosure

A single clearly signaled one-level reference (./references/content-decay-signals.md, which exists) with good section structure, but large reference-style material is inlined in the body with some overlap to that reference file — a minor organization gap.

4 / 5

Total

15

/

20

Passed

Description

100%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 exemplary: third-person voice, a concrete trigger clause with many natural user phrases, a comprehensive action list, and explicit routing away from sibling skills. It hits the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "Identifies and updates outdated content", "Analyzes content freshness, adds new information, updates statistics, and optimizes for current SEO and GEO best practices" — covering the refresh workflow comprehensively.

5 / 5

Completeness

Explicitly answers both "what" (identify/update outdated content, analyze freshness, update stats, optimize SEO/GEO) and "when" with a concrete "Use when the user asks to…" trigger clause enumerating specific phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural phrases users would actually say, e.g. "update old content", "refresh content", "content is outdated", "improve declining rankings", "revive old blog posts", "traffic is declining on this page", "rankings dropped for this article".

5 / 5

Distinctiveness Conflict Risk

Clear SEO/GEO content-refresh niche with distinct triggers, plus explicit disambiguation ("For writing new content from scratch, see seo-content-writer. For auditing without rewriting, see on-page-seo-auditor") minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (748 lines); consider splitting into references/ and linking

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 27 suspicious

Warning

Total

13

/

16

Passed

Repository
teeclaw/phorm-nft
Reviewed

Table of Contents

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.