seo-content-pruning
Skill0 starsChanged 3 months agoNo licenceView on GitHub
Content pruning d'un site client, GSC UNIQUEMENT : recos automatiques page par page (garder / optimiser / actualiser / réécrire / fusionner / couper) selon l'arbre de décision consensuel des sources de référence (Ahrefs, Semrush, Search Engine Land, Conductor, Clearscope). La coupe et la fusion sont TOUJOURS des propositions pour un humain. Livrable = liste d'action actionnable dans la semaine. Architecture hybride : socle script (arbre mécanisable) + jugement agent (socle des offres, cas ambigus, livrable). Use when auditing existing content, deciding what to keep/merge/kill/rewrite, or producing the week-1 action list. Triggers : "content pruning <client>", "audit du contenu existant", "quoi garder / quoi couper", "/seo pruning <client>".
In this repository17 other files it gives its agents.
- seo-osSkill
- article-createSkill
- content-brief-creatorSkill
- content-quality-evaluatorSkill
- content-refreshSkill
- seo-audit-backlinksSkill
- seo-audit-eeatSkill
- seo-audit-geoSkill
- seo-audit-manualSkill
- seo-audit-technicalSkill
- seo-collectSkill
- seo-funnel-orchestratorSkill
- seo-monitoringSkill
- seo-publishSkill
- seo-reportSkill
- seo-strategySkill
- seo-weekly-recapSkill
The file
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.

