social-media-agentlisted

Project context and working guide for Vishal's AI social media manager — a local Python agent in Desktop/claude/socialagent that monitors YouTube, Facebook and Instagram, diagnoses why performance dropped, designs replacement thumbnails, rewrites titles, learns from what he approves, and publishes a password-gated dashboard to socialagent-dashboard.vercel.app. Load this whenever the user mentions the social agent, "my channel", "the YouTube agent", thumbnails or CTR dropping, Facebook/Instagram engagement or reach, the channels/monitoring list, the micro-agents (design, copy, analyst, meta, strategy, critic), the manager, playbook.md or learned.md, "Fix it now"/"Don't need it", autopilot, the Telegram /fix and /skip commands, run_daily/run_sync/run_weekly, the Vercel dashboard or its password, or anything inside the socialagent folder. Use it even for vague asks like "check my channel", "why are my views down", "the agent isn't running", "add a channel to monitor", "redeploy the dashboard", or "keep building
hellokianben-collab/vishal-agarwal-context · ★ 0 · DevOps & Infrastructure · score 60

Install: claude install-skill hellokianben-collab/vishal-agarwal-context

# Social Media Agent An AI social media manager that runs on Vishal's own laptop for **$0/month**. It watches YouTube, Facebook and Instagram, tells him what is going wrong and *why*, prepares the fix, and gets better at his specific channels over time. **Location:** `C:\Users\Susanta Podder\Desktop\claude\socialagent` **Live dashboard:** https://socialagent-dashboard.vercel.app (password-gated) **In-repo docs:** `README.md` (overview), `SETUP.md` (click-by-click setup), `LEARN.md` (why it is built this way — written for a non-coder learning agents) ## Who you are working with Vishal has **no coding background and does not want to write code**. He clicks through consent screens and pastes secrets; everything else is yours. When you give him steps, write them click-by-click, with the exact command in a fenced `bash` block. Never hand him a code snippet to "just add". He also wanted to *learn* as this got built — that is what `LEARN.md` is for. When you do something architecturally interesting, explain the why briefly. ## Current state | Piece | State | |---|---| | YouTube collectors, rules, agents | built, verified on synthetic data | | Facebook + Instagram | built, verified on synthetic data — **never yet run against a real Meta token** | | Manager + 6 micro-agents | built, working | | Fix it now / Don't need it, preference learning, autopilot | built, working | | Unified dashboard + channels list | built, working | | Vercel published dashboard + command queue | deploy