content-decay-monitor-setup
Skill7 starsChanged 5 months agoMITView on GitHub
Save monitored pages and topics to schedule recurring decay scans in local agents. Use when Codex needs to set up ongoing content performance monitoring for a set of pages or topics.
In this repository22 other files it gives its agents.
- authority-mark-keyword-difficultySkill
- cannibalization-checkSkill
- client-report-writerSkill
- competitor-serp-monitorSkill
- content-moat-plannerSkill
- content-refresh-briefSkill
- exceed-quality-thresholdSkill
- internal-link-builderSkill
- keyword-opportunity-finderSkill
- keyword-plannerSkill
- live-search-console-dataSkill
- proposal-builderSkill
- refresh-vs-new-contentSkill
- schema-fix-writerSkill
- seo-content-briefSkill
- seo-growth-loopSkill
- seo-offer-architectSkill
- seo-priority-scoreSkill
- seo-strategySkill
- technical-seo-triageSkill
- title-meta-rewriterSkill
- traffic-decay-detectorSkill
The file
Files
Content Decay Monitor Setup
Overview
Configure a recurring monitor that checks a list of pages or topics for organic performance changes. The monitor runs on a schedule (weekly/monthly) and alerts when performance drops below a threshold.
Inputs
- List of URLs or topics to monitor
- Monitoring frequency (weekly, biweekly, monthly)
- Alert threshold (e.g., 15% click decline, 20% impression drop)
- Optional: GSC property or GA4 property
Workflow
- Define the monitor scope: pages, topics, or both.
- Set baseline performance from current GSC/GA4 data.
- Configure the check frequency and alert threshold.
- Store the monitor configuration in a local file or agent config.
- On each check cycle: fetch current data, compare to baseline, flag pages below threshold.
- Route alerts to the user (with traffic-decay-detector for deeper analysis).
Output
Monitor configuration file and recurring check instructions for the agent runtime.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

