Intel Sweep Setup

intel-sweep-setup

A Claude Code skill that sets up autonomous monitoring for deployed apps — signals, intel-digest endpoint, admin dashboard, and automated pipeline. Works on any stack and host.

What it does

Gives you a continuous feed of crashes, user frustration, feature requests, and churn signals — without relying on users to report anything.

**End state:** A queryable `/api/intel-digest` endpoint that aggregates all intel from your app, an admin page to view it on demand, and an automated process that checks it regularly and surfaces findings wherever you work.

Two modes

Audit mode — `/intel-sweep-setup`

Scans what a project currently captures across three signal tiers, reports gaps, and offers to fix them.

Wire mode — `/intel-sweep-setup wire [project-name]`

Full setup: signals → endpoint → admin page → automation.

Signal tiers

Tier 1: Eyes Open (every app, day 1)

• User counts (total, new today, DAU/WAU)
• Client errors (crashes you'll never hear about otherwise)
• Churn signals (paying users silent 3+ days)

Tier 2: Understanding Users (feature-dependent)

• Onboarding funnel drop-off
• Feature usage distribution
• Chat topics, complaints, and feature wishes
• Payment failures and cancellations
• Trial-to-paid conversion
• User feedback / PMF signals

Tier 3: Deep Ops (at scale)

• Behavioral patterns (rage quit, burst-then-silence)
• AI quality signals (regenerations, short responses)
• Push notification health
• Search dead ends
• Rate limit hits
• Cron / content freshness
• Anti-abuse / bot detection

Farcaster add-on

Frame → app conversion, cast-to-engagement, social-graph churn.

Stack support

Detects your stack automatically:

Layer	Supported
DB	Prisma, Turso/libsql, Supabase, Drizzle, Mongoose
Platform	Vercel, Cloudflare Workers, Fly.io, Railway, VPS
Billing	Stripe, Lemon Squeezy
Observability	Sentry, PostHog, Umami, Vercel Analytics

Output

Always en