content-decay-refresh

Refreshes decaying blog content using Google Search Console signals and opens review PRs.

20.2k|3.4k|Updated Oct 5, 2024
One-click install
npx skills add https://github.com/kortix-ai/suna --skill content-decay-refresh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: content-decay-refresh
Source: https://github.com/kortix-ai/suna/tree/main/packages/starter/templates/marketplace/runtime/skills/content-decay-refresh
Command: npx skills add https://github.com/kortix-ai/suna --skill content-decay-refresh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Marketing and blog content silently loses search traffic over time, and teams rarely notice until rankings collapse. This Skill runs a weekly loop that finds pages losing impressions and clicks in Google Search Console, refreshes stale copy, outdated stats, and broken internal links, and opens a pull request for human review.

Core Features & Use Cases

  • Decay Detection: Pulls impressions and clicks per URL from Google Search Console, comparing the trailing 28 days against the prior 28 days to rank pages by decay severity weighted by traffic.
  • Fair Rotation Ledger: Maintains a durable log at .kortix/memory/content-refresh-log.md so the same high-traffic pages are not refreshed every week while the long tail is ignored.
  • PR-Only Workflow: Refreshes 3-5 pages per run on an isolated branch and opens one labeled pull request, never publishing or merging on its own.
  • Use Case: A content team notices organic traffic declining but cannot audit hundreds of posts manually. The weekly cron runs this Skill, which identifies the five fastest-decaying pages, updates aged statistics and renamed internal links, and opens a PR an editor reviews Monday morning.

Quick Start

Ask the agent to run a content refresh pass on your repository using Search Console decay data and open a pull request with the updated pages.

Frequently Asked Questions about content-decay-refresh

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find blog posts losing search traffic automatically?

Connect Google Search Console and compare impressions and clicks per URL over the trailing 28 days against the prior 28 days. Rank pages by decay severity weighted by absolute traffic to surface the highest-impact declines first.

How to automate content refresh with GitHub pull requests?

Run the refresh on an isolated branch, commit only changes under the content path, and open one labeled PR per run with the gh CLI. The agent never merges or publishes, so a human reviews every change before it ships.

Does this skill publish or merge content changes directly?

No. The agent only opens a pull request against an isolated branch and stops. It never pushes to the live content branch and never merges its own work; a human decides what ships.

Can the agent modify files outside the content directory?

No. Only files under the configured content path are editable. Application code, configuration, and everything outside that path are read-only to this agent, and the Search Console connector is read-only as well.

Why do the same pages keep getting refreshed in content audits?

Naive ranking always surfaces the highest-traffic decliners. This Skill uses a durable ledger recording last-refreshed dates, so recently refreshed pages drop in priority and never-touched pages move up in rotation.