<pectus.ai/>
./pectus.ai — builder framework · self-hosted · MIT

For end users

weekly-analysis

Weekly content plan with post suggestions ranked by projected traffic.

What it does

Pulls together brand, ICP, knowledge insights, the active app insights, your top keywords, your recent articles, and answer-the-public seeds. Returns a structured weekly plan: post suggestions, refreshed keyword clusters, signs of old posts rising, possible new categories, and a list of negatives to avoid.

If your workspace has connected apps (GA4, Search Console, Google Ads, etc.), weekly-analysis re-runs each app’s interpretation skill first so the insights it reads are current. You don’t run those interpretations manually.

Inputs

  • workspace_id
  • brand_profile
  • icp_profile
  • knowledge_insights
  • insights (active insights from connected apps)
  • top_keywords
  • recent_articles
  • answer_public_entries
  • last_run (the previous week’s output, for continuity)

Outputs

  • post_suggestions — ranked list with topic, intent, projected traffic, draft brief
  • keyword_clusters — refreshed cluster map
  • old_posts_rising — pages gaining traffic worth refreshing
  • new_category_suggestions — pillar topics worth adding
  • negatives — topics to actively avoid

When to run

Once a week. The dashboard surfaces a “Run weekly analysis” button on Mondays. The skill is the heaviest single call in Pectus, so the runner uses prompt caching on the stable layers (brand, ICP, knowledge) to keep cost down across reruns within the same window.

Where it lives

pectusai/skills/weekly-analysis/SKILL.md