skills/golem-powers/railway/SKILL.md
Deploy and manage the golems cloud-worker on Railway. Use when deploying backend changes, checking logs, managing env vars, or restarting services. Wraps `railway` CLI. Covers railway, deploy, cloud-worker, redeploy, logs, variables. NOT for: Vercel deployments, frontend, Supabase.
npx skillsauth add etanhey/golems railwayInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Manages the golems cloud-worker service on Railway. The cloud-worker runs email poller, job scraper, briefing, and soltome learner.
Railway CLI commands can be run directly — no cd required. The railway CLI uses the linked project config, not the working directory.
If you do get a "Could not find root directory" error, it means railway link has not been run yet for this project.
| Key | Value |
|-----|-------|
| Project | helpful-empathy |
| Service | golems |
| Environment | production |
| Entry point | bun run src/cloud-worker.ts |
| Health check | /health |
| What you want to do | Workflow | |---------------------|----------| | Deploy latest code | workflows/deploy.md | | Check logs | workflows/logs.md | | Manage env vars | workflows/variables.md | | Restart without rebuilding | workflows/restart.md | | Check status | workflows/status.md |
Deploy to Railway after merging PRs that change:
packages/services/src/cloud-worker.ts (schedules, worker config)packages/shared/src/email/ (email processing)packages/jobs/src/ (job scraping)packages/shared/src/lib/cloud-llm.ts (Haiku backend)railway.jsonDo NOT forget to deploy after backend PRs merge. Use the CLI — no "manual redeploy" needed.
tools
The human-eval UX contract for Phoenix views: turn-by-turn scrollable replay (not a scorecard), hide-but-copyable IDs, collapsed thinking, identity chips, tool filters, tiny frozen starter datasets, mark-wrong-in-thread, mobile-first. Use when: building or reviewing ANY Phoenix/eval view, annotation UI, session replay, or human-grading surface. Triggers: phoenix view, eval UI, annotation view, session replay, human eval UX, grading interface. NOT for: Phoenix data pipelines/ingest (capture scripts have their own specs).
tools
macOS systems specialist — AppKit NSPanel architecture, launchd services, socket activation, MCP bridge resilience, syspolicyd, and high-frequency SwiftUI dashboards. Use when building menu-bar apps, LaunchAgents, debugging syspolicyd/Gatekeeper/TCC, resilient UDS/MCP bridges, or SwiftUI dashboards at 10Hz+.
development
Bulk LLM-judging protocol for fleet-dispatched verdict runs (KG cluster, eval harness). Use when: dispatching or running judge workers (J1/J2/RT), planning bulk-apply from verdict JSONL, or triaging evidence_degraded outputs. Triggers: judge fleet, bulk judge, R3 verdicts, kg-judge, RT gate, evidence_degraded. NOT for: single-item code review, Phoenix view UX (use phoenix-human-view), or non-judge eval pipelines.
development
Quiet-down protocol for sprint close: when the fleet wraps, delete ALL polling crons and monitors, send ONE final dashboard + ONE message, then go SILENT. Use when: fleet wraps, all workers done, overnight queue exhausted, sprint close, Etan asleep/away with nothing approved left. Triggers: fleet wrap, wrap the fleet, stand down, going quiet, sprint close. NOT for: mid-sprint monitoring (keep your loops), spawning a successor (use /session-handoff first).