seo-priority-score
Skill7 starsChanged 5 months agoMITView on GitHub
Rank SEO tasks by expected impact, confidence, effort, authority feasibility, and revenue proximity. Use when Codex needs to decide which of many identified issues to work on first.
In this repository22 other files it gives its agents.
- authority-mark-keyword-difficultySkill
- cannibalization-checkSkill
- client-report-writerSkill
- competitor-serp-monitorSkill
- content-decay-monitor-setupSkill
- 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-strategySkill
- technical-seo-triageSkill
- title-meta-rewriterSkill
- traffic-decay-detectorSkill
The file
Files
SEO Priority Score
Overview
Given a list of potential SEO tasks (from any Diagnose skill), score each one on a standardized framework and produce a ranked priority list.
Inputs
- List of SEO tasks or opportunities with supporting data
- Optional: business context (revenue per visitor, conversion rates, margins)
Workflow
- For each task, collect or estimate:
- Impact: traffic, conversion, or revenue potential (scale 1-10)
- Confidence: how reliable the signal is (scale 1-5)
- Effort: hours or cost to implement (scale 1-5, inverted)
- Authority feasibility: can the site realistically compete (scale 1-5)
- Revenue proximity: how directly this affects pipeline (scale 1-5)
- Calculate a composite priority score:
(Impact × Confidence) / (Effort × Authority gap)with revenue proximity as a multiplier. - Group tasks by effort band: quick wins (< 4 hours), medium projects (4-20 hours), strategic initiatives (20+ hours).
- Output a sorted priority list with the score breakdown.
Output
Ranked task list with priority score, breakdown, and effort band.
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.