Every morning, I run /morning — a custom Claude Code slash command that consolidates crucial information about my game, BattleTabs, into one structured summary. Rather than losing the first hour scrolling Discord, checking dashboards, and reviewing notifications, this command delivers a complete picture in minutes.
The command operates through six phases:
- Review priorities from
.claude/priorities.md - Check GitHub for open issues, pull requests, and recent merges
- Review git state including active worktrees and branches
- Monitor relevant Discord channels
- Pull recent app store reviews
- Synthesize everything into a structured summary
The priorities file is crucial — it prevents signal from drowning in noise by helping Claude distinguish between critical issues and minor problems. Discord integration provides the most value, pulling the last 15–20 messages from bug-support, mod channels, trusted-community spaces, and suggestion forums to surface bugs, complaints, and feature requests.
The technical backbone relies on MCP (Model Context Protocol) servers — lightweight integrations giving Claude access to external services like Discord, App Store Connect, Google Play, and GA4. These are configured in .mcp.json and allow Claude to read not just code, but player behaviour and business metrics.
The briefing concludes with 2–3 prioritised focus areas for the day, and “if something on it looks worth tackling, I can spawn a fresh agent on it right there in the same session. The context is already loaded; the new agent inherits it.”
Briefing on Business Intelligence
As the daily briefing became routine, I recognised gaps in understanding deeper trends — weekly retention patterns, cohort quality, and revenue stability. This led to three companion commands: /business-daily, /business-weekly, and /business-monthly.
Daily Command: Mirrors /morning for business metrics — yesterday’s revenue, paying-user counts, refund spikes, and ratings changes — compared against rolling seven-day baselines to filter noise.
Weekly Command: Runs Mondays and measures revenue, engagement, retention, and acquisition against a four-week rolling average rather than week-to-week comparisons, which are skewed by weekends and paydays. The headline metric is ARPDAU (average revenue per daily active user) rather than DAU, since “as a solo studio with no marketing budget, I can’t really move DAU much in a week.”
Monthly Command: Deeper analysis including retention heatmaps across twelve weeks, LTV by cohort age, whale concentration metrics, and crucially, “departed whales” — top 1% players who’ve churned — often providing more useful signals than new whale acquisition.
Each command sits at a different temporal scale: daily asks “is anything on fire?”; weekly evaluates trend direction; monthly assesses fundamental health. This layered approach prevents the daily briefing from becoming unwieldy while ensuring nothing important falls through the cracks.