Content Decay Detector logo

Content Decay Detector

Organization
Affitor
content-decay-detector

Monitor existing content for ranking drops and trigger refresh workflows. Triggers on: "check for content decay", "which content needs updating", "content refresh", "ranking drops", "traffic decline", "stale content", "content audit", "what to refresh", "outdated content", "content performance check", "update old articles", "declining rankings", "content maintenance", "refresh priority list", "which articles are losing traffic", "SEO content audit".

Overview

PublisherAffitor
Repositoryaffiliate-skills
Skill namecontent-decay-detector
Stars
705
Forks
209
Bundled files
Instructions only
LicenseMIT
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 Affitor on GitHub. Read the source before you install it.

Installation

Install the Content Decay Detector 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/Affitor/affiliate-skills/tree/main/skills/blog/content-decay-detector
  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/Affitor/affiliate-skills.git /tmp/affiliate-skills
mkdir -p .claude/skills
cp -r /tmp/affiliate-skills/skills/blog/content-decay-detector .claude/skills/content-decay-detector
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Content Decay Detector 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 Content Decay Detector 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 Content Decay Detector 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.

Content Decay Detector

Monitor existing content for ranking drops and generate a prioritized refresh queue. Refreshing decaying content is the highest-ROI SEO activity — it's faster and cheaper than creating new content, and recovering a lost position is easier than earning a new one.

Stage

S3: Blog & SEO — Blog maintenance and optimization. This skill keeps your existing content competitive and prevents rankings from silently eroding.

When to Use

  • User has existing blog content and wants to check for decay
  • User notices traffic declining on specific pages
  • User asks "what content needs updating?"
  • User says "content decay", "ranking drops", "stale content", "refresh", "content audit"
  • Monthly maintenance check — should run every 30 days on active blogs
  • After seo-audit reveals declining pages

Input Schema

yaml
site_url: string              # REQUIRED — the site to audit
                              # e.g., "myblog.com", "example.com/blog"

content_list: object[]        # OPTIONAL — specific pages to check
  - url: string               # Page URL
    title: string             # Page title
    publish_date: string      # Original publish date
    last_updated: string      # Last update date
    target_keyword: string    # Primary keyword

check_competitors: boolean    # OPTIONAL — whether to check if competitors published fresher content
                              # Default: true

timeframe: string             # OPTIONAL — "30d" | "90d" | "6m" | "1y"
                              # Default: "90d"

Chaining from S6 seo-audit: Use declining_pages as the content_list.

Workflow

Step 1: Gather Content Data

If content_list not provided:

  1. web_search: site:[site_url] — discover indexed pages
  2. Identify the top 15-20 most important pages (by topic relevance)
  3. For each page, note: title, URL, apparent publish/update date

Step 2: Check for Decay Signals

Read shared/references/seo-strategy.md for decay signals and refresh methodology.

For each page:

  1. web_search for the page's target keyword — check current ranking position
  2. Look for decay signals:
    • Outdated information: Product features, pricing, dates mentioned
    • Competitor freshness: Newer, better content published by competitors
    • Missing elements: No images, no data, thin content compared to current SERP
    • Broken patterns: "2023" in a title when it's 2025+, discontinued products mentioned

Step 3: Score Decay Priority

For each decaying page, assign priority:

FactorScoreCriteria
Revenue impact1-5Contains affiliate links + had traffic = high revenue impact
Decay severity1-5Major outdated info = 5, minor = 1
Fix effort1-5 (inverted)Easy fix = 5, full rewrite = 1
Competitor threat1-5Competitor published better version = 5

Priority = Revenue × Decay × Fix_Ease × Competitor_Threat (normalized)

Step 4: Generate Refresh Instructions

For each page in priority order, specify:

  1. What's decayed — specific outdated elements
  2. What to update — concrete changes to make
  3. What to add — new sections, data, or elements competitors have
  4. Internal linking — new pages to link to/from since original publish
  5. Estimated effort — time to refresh

Step 5: Self-Validation

  • Decay signals are evidence-based (not guesses)
  • Priority ordering makes business sense (revenue-impacting first)
  • Refresh instructions are specific and actionable
  • Effort estimates are realistic
  • Not recommending refreshes for content that's performing fine

Output Schema

yaml
output_schema_version: "1.0.0"
content_decay:
  site: string
  pages_analyzed: number
  pages_decaying: number
  total_refresh_effort: string  # Estimated total hours

  decaying_pages:
    - url: string
      title: string
      priority: string          # "P0-critical" | "P1-high" | "P2-medium" | "P3-low"
      decay_signals: string[]
      refresh_actions: string[]
      estimated_effort: string
      revenue_impact: string    # "high" | "medium" | "low"

  healthy_pages: string[]       # Pages that don't need refresh

chain_metadata:
  skill_slug: "content-decay-detector"
  stage: "blog"
  timestamp: string
  suggested_next:
    - "affiliate-blog-builder"
    - "seo-audit"
    - "internal-linking-optimizer"
    - "keyword-cluster-architect"

Output Format

## Content Decay Report: [Site]

### Summary
- **Pages analyzed:** XX
- **Pages decaying:** XX
- **Total refresh effort:** XX hours
- **Estimated traffic recovery:** XX%

### Priority Refresh Queue

#### P0 — Critical (do this week)

**[Page Title]** — [URL]
- Decay: [what's wrong]
- Action: [what to do]
- Effort: [time estimate]
- Impact: [expected result]

#### P1 — High (do this month)
[same structure]

#### P2 — Medium (schedule)
[same structure]

### Healthy Pages (no action needed)
- [Page] — still ranking, content fresh
- [Page] — recently updated

### Monthly Maintenance Schedule
- Week 1: Refresh P0 pages
- Week 2: Refresh P1 pages
- Week 3: Create new content for gaps found
- Week 4: Internal linking review

Error Handling

  • No site URL: "I need your blog URL to check for content decay. What's the site?"
  • Site has no indexed pages: "I can't find indexed pages for this URL. Check that the site is public and indexed by search engines."
  • All content is fresh: "Great news — no significant decay detected. Run this check again in 30 days."
  • Can't determine ranking positions: Use available signals (content age, competitor freshness, outdated info) for prioritization.

Examples

Example 1: "Check my blog for content decay" → Discover indexed pages, check each for decay signals, generate prioritized refresh queue with specific actions per page.

Example 2: "Which of my articles need updating?" → Analyze content list, identify outdated pricing, stale comparisons, missing new products. Rank by revenue impact.

Example 3: "Content decay check" (after seo-audit) → Pick up declining pages from seo-audit output. Deep-dive each with competitor analysis and specific refresh instructions.

Flywheel Connections

Feeds Into

  • affiliate-blog-builder (S3) — refresh instructions for specific articles
  • internal-linking-optimizer (S6) — decaying pages may need better internal links
  • keyword-cluster-architect (S3) — content gaps revealed by decay analysis

Fed By

  • seo-audit (S6) — declining pages to investigate
  • internal-linking-optimizer (S6) — pages with weak link structure may be decaying
  • performance-report (S6) — traffic decline data

Feedback Loop

  • After refreshing, seo-audit (S6) tracks whether rankings recovered → measure refresh ROI, refine decay detection sensitivity

Quality Gate

Before delivering output, verify:

  1. Would I share this on MY personal social?
  2. Contains specific, surprising detail? (not generic)
  3. Respects reader's intelligence?
  4. Remarkable enough to share? (Purple Cow test)
  5. Irresistible offer framing? (refresh actions feel actionable)

Any NO → rewrite before delivering.

References

  • shared/references/seo-strategy.md — Decay signals, refresh methodology, priority matrix
  • shared/references/flywheel-connections.md — Master connection map

Frequently asked questions

What does the Content Decay Detector AI skill do?

Monitor existing content for ranking drops and trigger refresh workflows. Triggers on: "check for content decay", "which content needs updating", "content refresh", "ranking drops", "traffic decline", "stale content", "content audit", "what to refresh", "outdated content", "content performance check", "update old articles", "declining rankings", "content maintenance", "refresh priority list", "which articles are losing traffic", "SEO content audit".

Why use Content Decay Detector on TypingMind?

Because you install it once and use it with any model. Content Decay Detector 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 Content Decay Detector in TypingMind?

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

Which AI models can use Content Decay Detector?

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 Content Decay Detector?

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

Is the Content Decay Detector AI skill free?

Yes. It is published on GitHub by Affitor under the MIT license. 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 👇