Agent skill · marketing growth · aradotso
threads-growth-skill
Systematically improve Threads content using real performance data and algorithm-aware drafting
Why this skill is useful
Adds automated scripts for scraping Threads Insights and drafting optimized posts based on performance data, which the AI cannot generate on its own.
What it needs
Requires cookie-editor, git installed locally. Requires threads account access. About 6k tokens when loaded. Last updated 2026-08-05. 8 stars on the source repository.
What this skill does
Threads Growth Skill Skill by ara.so — Marketing Skills collection. Data-driven Threads content optimization that learns from your actual post performance. Uses browser automation to scrape Insights, identifies winning patterns, and drafts algorithm-compliant posts with AI-tone detection. What this does Performance tracking: Scrapes your real Threads Insights (views, likes, replies, shares) Pattern detection: Identifies what works for YOUR account (not generic advice) Smart drafting: Creates posts using your patterns + algorithm red-line checks + AI-tone detection Automated updates: Bi-weekly cron keeps your performance database current Share optimization: Prioritizes DM forwardability (3-5x weight vs likes per Mosseri 2025) Installation First-time setup 1. Export Threads cookies Required for authentication (cookies last ~60 days): 2. Run setup script This will: Validate cookie format Test authentication Run first Insights scrape (~5 min) Create references/winning-formats.md Set up bi-weekly cron job 3. Configure environment Key files Core workflows Draft a new post Example pattern matching: Algorithm red-line check 12 hard suppression rules from Meta's 2025 guidelines: AI-tone detection Flags and fixes 15 common AI tells before posting: Score a draft Insights scraper Manual run What it collects Auto-update cron Hook framework Built-in post structures ranked by performance: Hook Type Use Case Avg. Multiplier ----------- ---------- ----------------- Anti-Demo You hit failure → found fix 1.5x Secret Knowledge Insider info + steps 1.4x Truth/Comparison A vs B, clear winner 1.2x Builder Journey Workflow switch + results 1.1x Link Drop Just a link 0.2x (avoid) Anti-Demo example structure Signal weighting Based on Mosseri 2025 algorithm updates: Optimization priority: 1. DM forwardability (utility, tools, templates) 2. Conversation depth (ask questions, provide incomplete info) 3. Save-worthiness (reference value) 4. Repost-ability (identity signal for sharer) 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/threads-growth-skill