← Back to Skills Marketplace
aaron-he-zhu

Content Refresher

by Aaron Zhu · GitHub ↗ · v9.9.5 · MIT-0
cross-platform ✓ Security Clean
1919
Downloads
1
Stars
2
Active Installs
23
Versions
Install in OpenClaw
/install content-refresher
Description
Use when updating outdated content, fixing traffic/ranking decay, refreshing stats, adding new sections, or improving freshness signals. 内容更新/排名恢复
README (SKILL.md)

Content Refresher

Identifies outdated content, scores decay/freshness, prioritizes refresh work, and produces update plans with GEO and republishing guidance.

Quick Start

Find content on [domain] that needs refreshing
Which of my blog posts have lost the most traffic?
Refresh this article for [current year]: [URL/content]
Update this content to outrank [competitor URL]: [your URL]
Create a content refresh strategy for [domain/topic]

Skill Contract

Expected output: a scored diagnosis, prioritized repair plan, and a short handoff summary ready for memory/audits/.

  • Reads: the current page or site state, symptoms, prior audits, and current priorities from CLAUDE.md and the shared State Model when available.
  • Writes: a user-facing audit or optimization plan plus a reusable summary that can be stored under memory/audits/.
  • Promotes: blocking defects, repeated weaknesses, and fix priorities to memory/open-loops.md and memory/decisions.md.
  • Next handoff: use the Next Best Skill below when the repair path is clear.

Handoff Summary

Emit the standard shape from skill-contract.md §Handoff Summary Format.

Data Sources

Use ~~analytics, ~~search console, and ~~SEO tool when connected; otherwise ask for traffic data, ranking history, publish dates, candidate URLs, and competitor examples. See CONNECTORS.md.

Instructions

When a user requests content refresh help:

  1. CORE-EEAT Quick Score -- Estimate all 8 dimensions, prioritize red/yellow areas, and hand off to content-quality-auditor for full scoring when needed.
  2. Identify Refresh Candidates -- Use age, dated claims, declining traffic, lost rankings, broken links, SERP shifts, and missing topics.
  3. Analyze Page-Level Decay -- Compare 6-month-old vs current performance, keyword deltas, SERP intent, competitor updates, and the why-refresh rationale.
  4. Define Updates Needed -- Capture outdated elements, competitor/PAA gaps, SEO updates, GEO updates, links, images, sources, and dates.
  5. Create Refresh Plan -- Specify title, structure, new sections, refreshed statistics, internal/external links, images, and validation requirements.
  6. Write Refresh Content -- Draft updated intro, replacement sections, refreshed facts, FAQ answers, and Changes Made notes.
  7. Optimize for GEO -- Add 40-60 word definitions, quotable statements, Q&A, dated citations, and standalone factual statements.
  8. Set Republishing Strategy -- Use published-date update for 50%+ new content, last-updated date for 20-50%, original date for \x3C20%; update schema, sitemap lastmod, cache, Search Console, and 4-6 week monitoring.
  9. Create Refresh Report -- Summarize completed changes, expected outcomes, owners, next review date, and open loops.

Reference: references/refresh-templates.md has compact templates for steps 2-9.

Example

User: "Refresh my blog post about 'best cloud hosting providers'"

Output: CORE-EEAT quick score flags weak Referenceability, Experience, and Trust; recommends pricing refresh, broken-link fixes, author credential additions, affiliate disclosure, and a Changes Made block ready for republish.

Reference: See references/refresh-example.md for the full worked example and checklist.

Tips for Success

Prioritize by ROI/search demand, make substantive improvements instead of date-only edits, add stronger evidence than competitors, track post-publish rankings/traffic, and treat every refresh as a GEO citation opportunity.

Reference data: references/content-decay-signals.md covers decay signals, lifecycle stages, refresh-vs-rewrite decisions, and content-type strategy.

Save Results

Ask to save results; if yes, write a dated summary to memory/audits/content-refresher/YYYY-MM-DD-\x3Ctopic>.md. Append veto-level issues to memory/hot-cache.md automatically.

Gate check recommended: Run content-quality-auditor on refreshed content before republishing.

Reference Materials

Next Best Skill

Primary: content-quality-auditor -- re-score refreshed content before shipping.

Usage Guidance
This skill is an instruction-only SEO/content refresher and appears coherent: it will analyze pages, ask for or use analytics/GSC data if available, and produce refresh plans. Before using it, be prepared to (a) provide analytics/ranking data or configure official connectors rather than pasting long credentials, (b) confirm you are comfortable the agent can write audit summaries into its memory storage, and (c) avoid sharing sensitive account secrets in chat. If you want extra caution, run an initial test with a non-sensitive URL and provide anonymized metrics rather than full account access. If the agent ever asks to connect to an external service, verify the connector endpoint is official and that you control the credentials it will use.
Capability Analysis
Type: OpenClaw Skill Name: content-refresher Version: 9.9.5 The 'content-refresher' skill bundle is a legitimate SEO tool designed to help AI agents identify and update outdated web content. The code and instructions in SKILL.md and the reference files (content-decay-signals.md, refresh-templates.md) focus entirely on content auditing, traffic analysis, and SEO optimization strategies. It uses standard local file-based state management (writing to a 'memory/' directory) and lacks any indicators of data exfiltration, malicious execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The name/description match the instructions: diagnosing content decay, prioritizing refreshes, drafting updates, and giving republishing guidance. No unexpected binaries, installs, or credentials are required for the stated SEO/content tasks.
Instruction Scope
SKILL.md instructs the agent to read page/site state, analytics/Search Console when available, and to write handoff summaries into memory/audits/ and memory/open-loops.md. This behavior is appropriate for an audit/refresh skill, but the instructions are somewhat broad — the agent may ask the user for analytics or ranking data (or for connectors to be configured). Users should expect the skill to fetch target URLs and competitor pages as part of analysis.
Install Mechanism
No install spec and no code files: lowest-risk, instruction-only skill. Nothing is downloaded or written to disk by an installer.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. It references external analytics/Search Console connectors but does not embed or demand secrets in the manifest; any credentials would need to be supplied at runtime by the user or platform connectors.
Persistence & Privilege
always:false and no special privileges. The skill writes expected outputs into agent memory paths (memory/audits/, memory/open-loops.md) per its contract — this is proportional to its function. It does not request to modify other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install content-refresher
  3. After installation, invoke the skill by name or use /content-refresher
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v9.9.5
Published from v9.9.5 @ 7ecc77b
v9.9.0
Published from main @ 7861a09
v9.5.0
Published from main @ 9967b3d
v9.1.0
Published from main @ d9bf8c7
v9.0.1
Published from main @ 3642433
v9.0.0
Published from main @ 032eb65
v8.0.2
Published from main @ 728f02d
v8.0.1
Published from main @ e644cbe
v8.0.0
v8.0.0: Unified version release — consolidates Wiki Knowledge Layer, Auditor Runbook inline strategy, Critical Fail Cap, Guardrail Negatives, and 2 new commands
v7.2.0
v7.2.0: conversion-focused first paragraphs, cross-promotion tables, deduplicated Chinese keywords, semantic density paragraphs for on-page/technical SEO auditors
v7.1.0
Improve ClawHub search discoverability: optimized display name, tags, and description for vector search
v7.0.0
v7.0.0: Wiki Knowledge Layer + infrastructure upgrades
v6.2.0
v6.2.0: when_to_use + argument-hint frontmatter, hook hardening, memory system upgrades
v6.0.0
v6.0.0: GStack pattern adoption — Completion Status Protocol, Escalation Protocol, Anti-Slop Output Voice, 8 named workflow phases, Decision Gates, AUTO-FIX vs ASK, 750+ multilingual triggers, all descriptions ≤180 UTF-8 bytes for full ClawHub display
v5.1.0
v5.1.0: multilingual trigger optimization — 5 languages, 750+ triggers, 8-agent reviewed
v5.0.0
v5.0.0: Unified operating model — hook automation, temperature memory, protocol gates, state write-through, trigger widening
v4.1.0
v4.1.0: publish GitHub absolute links for published docs and sync version metadata
v4.0.0
v4.0.0: ClawHub-first marketplace optimization — security fixes, vector search descriptions, multi-ecosystem install docs
v3.0.0
**Content Refresher 3.0.0 Changelog** - Added integration compatibility notes for marketplace and skills ecosystems. - Expanded tags to improve discoverability (e.g., "content-update", "evergreen-content"). - Added new reference files: refresh examples and templates. - Updated documentation for clarity and structure. - No breaking changes to functionality or workflow.
v2.0.0
**Major update with improved usability, triggers, and documentation.** - Added explicit natural language triggers and use case keywords to improve discoverability when users request content refresh or updates. - Expanded and clarified the skill description and metadata to specify when to use this skill versus others. - Included a full skills library directory with navigation and cross-links to related SEO and GEO skills. - Updated author and licensing metadata for clarity and attribution. - No changes to underlying refresh methodology or process instructions.
Metadata
Slug content-refresher
Version 9.9.5
License MIT-0
All-time Installs 2
Active Installs 2
Total Versions 23
Frequently Asked Questions

What is Content Refresher?

Use when updating outdated content, fixing traffic/ranking decay, refreshing stats, adding new sections, or improving freshness signals. 内容更新/排名恢复. It is an AI Agent Skill for Claude Code / OpenClaw, with 1919 downloads so far.

How do I install Content Refresher?

Run "/install content-refresher" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Content Refresher free?

Yes, Content Refresher is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Content Refresher support?

Content Refresher is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Content Refresher?

It is built and maintained by Aaron Zhu (@aaron-he-zhu); the current version is v9.9.5.

💬 Comments