Blog Refresher logo

Blog Refresher

Community
Illyism
blog-refresher

Refresh and improve existing blog posts to outrank competitors using a 6-phase content audit and SERP gap analysis. Use when the user wants to update, refresh, or improve an existing blog post, recover lost rankings, or asks why a post fell behind competitors.

Overview

PublisherIllyism
Repositoryseo-skills
Skill nameblog-refresher
Stars
584
Forks
60
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Illyism on GitHub. Read the source before you install it.

Installation

Install the Blog Refresher AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Illyism/seo-skills/tree/main/seo/blog-refresher
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Illyism/seo-skills.git /tmp/seo-skills
mkdir -p .claude/skills
cp -r /tmp/seo-skills/seo/blog-refresher .claude/skills/blog-refresher
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Blog Refresher in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Blog Refresher on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Blog Refresher is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Blog Refresher

You update existing blog posts so they outrank the pages above them. Analyze the post, compare it with the top-ranking competitors, find the gaps, and write an improved version that keeps the original voice.

Use real research tools: web search or a SERP API for rankings, and a page fetcher for competitor content. Do not rely on memory for what ranks or what competitors say. Use today's date for anything time-sensitive.

Keep messages short and actionable until the final refreshed content.

The 6-phase framework

  1. Current state analysis: assess the existing post
  2. Competitor research: analyze the top 5–10 SERP results
  3. Gap identification: what competitors have that the post lacks
  4. Improvement plan: a structured upgrade strategy
  5. Approval checkpoint: present findings and wait for approval
  6. Content recreation: write the refreshed version

Phase 1: Current state analysis

Content audit checklist

BASIC METRICS
□ Word count
□ Last updated
□ Current ranking for the main keyword (if Search Console or rank data exists)
□ Page traffic per month (if analytics exists)

STRUCTURE
□ Number of H2s and H3s
□ Lists, tables, images, media
□ Internal and external links

QUALITY
□ Readability (grade level)
□ Content depth: shallow / medium / deep
□ Unique insights
□ CTAs present

Initial assessment

EXISTING POST ANALYSIS
Title:
URL:
Primary keyword:

STRENGTHS: what works, unique angles, strong sections to keep
WEAKNESSES: outdated information, missing topics, weak sections, poor flow
QUICK WINS: easy updates, stats to refresh, broken links to fix

Phase 2: Competitor research

Step 1: Read the SERP

Extract the top 10 titles, the featured snippet, People Also Ask questions, related searches, and the dominant content format.

Step 2: Pick 5 competitors

Prioritize direct competitors, pages ranking #1–3, recently updated content, and pages with visible engagement.

Step 3: Audit each competitor page

URL / Ranking position
Word count
H2 sections and H3 breakdown
Unique elements: features, data, examples, visuals, interactive tools
Last modified date

Phase 3: Gap analysis

Build a table that compares the post with each competitor:

ElementYour postComp 1Comp 2Comp 3Comp 4Comp 5Priority
Word count
Featured snippet format
[Topic 1]
[Topic 2]
Statistics / data
Examples / cases
Visuals
FAQ section
Schema markup

Then list missing topics by priority:

  • High: covered by 4+ competitors
  • Medium: covered by 2–3 competitors
  • Low: covered by 1 competitor
  • Emerging: angles nobody covers yet

Finish with each competitor's unique angle and the post's opportunity to differentiate.

Phase 4: Refresh strategy

IMMEDIATE
□ Update outdated statistics to the latest available data
□ Fix broken links
□ Add missing high-priority topics
□ Format the answer for the featured snippet
□ Refresh examples and screenshots

STRUCTURE
□ Reorder H2s for better flow
□ Add an FAQ from People Also Ask
□ Add comparison tables
□ Improve the intro hook

OPTIMIZATION
□ Target word count
□ Internal links to add
□ Authoritative external sources to cite
□ Image alt text
□ Schema markup

Proposed outline

  • 3 new title options (current year or new angle, snippet-focused, differentiated)
  • The new H2 structure, each marked Keep / Modified / New with what changes
  • Target word count and new elements (table, FAQ, diagram)

Phase 5: Approval

Present the plan before writing:

markdown
## Content refresh plan: [Post title]

### Summary
The post ranks #[X] and has fallen behind on [areas]. This refresh adds [N] sections and updates [N] outdated elements.

### Key findings
1. Content depth: competitors average [X] words vs [Y]
2. Missing topics: [top 3 gaps]
3. Outdated elements: [main issues]
4. Opportunity: [unique angle]

### Gap table
### New outline

Shall I write the refreshed version? Any sections to prioritize?

Do not promise specific ranking or traffic gains.

Phase 6: Writing the refresh

Keep what works

  • Sections that already rank well
  • The original voice and tone
  • The URL (or plan a 301 redirect)
  • Existing anchors that other pages link to

Improve

  • Add a visible "Last updated: [date]"
  • Cite the year next to every statistic
  • Go deeper than competitors on the topics that matter
  • Add original data, examples, or diagrams competitors lack

Make it scannable

  • Paragraphs of 2–3 sentences
  • More H3s
  • Lists and tables where they help
  • Jump links for long posts

SEO checklist

□ Title tag 50–60 characters
□ Meta description 150–160 characters
□ Primary keyword in the first 100 words
□ Related terms used naturally
□ Snippet-ready answer near the top
□ FAQ answers People Also Ask
□ Internal links to and from related posts

Output format

markdown
# [New title]

_Last updated: [date]_

[New intro]

[Jump links]

[Refreshed sections]

## Frequently asked questions

## Conclusion

---

### Refresh summary for the publisher
- Meta description: [new]
- Schema: [types to add]
- Internal links: [pages to link]
- Images needed: [list]
- URL: [keep / redirect plan]
- Word count: [old] → [new]
- Sections added: [list]

Quality check

  • Every gap from Phase 3 is addressed or consciously skipped
  • All data and examples are current and sourced
  • The original voice is intact
  • No keyword stuffing
  • The post gives more practical value than each competitor analyzed

Frequently asked questions

What does the Blog Refresher AI skill do?

Refresh and improve existing blog posts to outrank competitors using a 6-phase content audit and SERP gap analysis. Use when the user wants to update, refresh, or improve an existing blog post, recover lost rankings, or asks why a post fell behind competitors.

Why use Blog Refresher on TypingMind?

Because you install it once and use it with any model. Blog Refresher is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Blog Refresher in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Illyism/seo-skills/tree/main/seo/blog-refresher. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Blog Refresher?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Blog Refresher?

As many as you like. As long as a model supports skills, you can use Blog Refresher with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Blog Refresher AI skill free?

It is published on GitHub by Illyism. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇