etanhey/email-golem
skills/golem-powers/_archive/email-golem/SKILL.md
Email triage system using Gmail + MLX local inference for scoring and prioritization. Use when: checking emails, running email triage, viewing urgency scores, checking if email scheduler is running, debugging missing email notifications, or managing the launchd email-golem daemon. Scores emails 1-10 and sends Telegram alerts for urgent ones. NOT for: general Gmail search without triage context.
$ install --global
skillsauthnpx skillsauth add etanhey/golems email-golemInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 9:03 PM1.8s1 file scanned
SKILL.md
- name:
- email-golem
- description:
- Email triage system using Gmail + MLX local inference for scoring and prioritization. Use when: checking emails, running email triage, viewing urgency scores, checking if email scheduler is running, debugging missing email notifications, or managing the launchd email-golem daemon. Scores emails 1-10 and sends Telegram alerts for urgent ones. NOT for: general Gmail search without triage context.
EmailGolem - Email Triage Control
Check status, run manual triage, view recent scores, and manage the email system.
Commands
Check Status
# View scheduler status
launchctl list | grep email-golem
# View recent logs
tail -20 /tmp/golems-email-golem.log
# View offline queue
cat ~/.local/share/brainlayer/offline-queue.json 2>/dev/null || echo "Queue empty"
Manual Run
# Dry run (safe - no DB writes, no notifications)
cd ~/Gits/golems && bun run packages/shared/src/email/index.ts --dry-run
# Full run (will score, save, and notify if urgent)
cd ~/Gits/golems && bun run packages/shared/src/email/index.ts
# Check specific number of emails
cd ~/Gits/golems && bun run packages/shared/src/email/index.ts --dry-run --max=5
Scheduler Control
# Enable (runs every 10 minutes)
launchctl load ~/Library/LaunchAgents/com.golems.email-golem.plist
# Disable
launchctl unload ~/Library/LaunchAgents/com.golems.email-golem.plist
# Reload (after changes)
launchctl unload ~/Library/LaunchAgents/com.golems.email-golem.plist
launchctl load ~/Library/LaunchAgents/com.golems.email-golem.plist
When To Use
- "Check my emails" → Run dry-run to see what would be scored
- "Any urgent emails?" → Run dry-run and check for score 10
- "Is email checker running?" → Check launchctl status
- "Why no email notifications?" → Check logs for errors
Scoring Reference
| Score | Category | Action | |-------|----------|--------| | 10 | interview, urgent | Telegram alert NOW | | 7-9 | job | Morning briefing | | 5-6 | subscription | Monthly tracking | | 1-4 | newsletter, promo | Ignore |
Troubleshooting
No emails scoring
- Check Gmail credentials in
.env - Check MLX backend is available:
which mlx_lm.generate - Check logs:
tail -50 /tmp/golems-email-golem.log
Notifications not working
- Check telegram-bot is running:
pgrep -fl telegram-bot - Check port 3847:
curl http://localhost:3847/health
Items stuck in queue
# View queue
cat ~/.local/share/brainlayer/offline-queue.json
# Clear queue (if corrupt)
rm ~/.local/share/brainlayer/offline-queue.json
Related Files
~/Gits/golems/packages/shared/src/email/- Source code~/Gits/golems/packages/shared/src/email/index.ts- Entry point~/.local/share/brainlayer/state.json- State (lastEmailCheck, processedIds)
Requirements
- Telegram bot running on port 3847 (for notifications)
- MLX backend for local inference
- Gmail OAuth configured
- Supabase tables created
Related Skills
etanhey/phoenix-human-view
tools
VerifiedTrustedCommunity
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).
3SKILL.mdUpdated Jun 7, 2026
etanhey/mac-systems
tools
VerifiedTrustedCommunity
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+.
3SKILL.mdUpdated Jun 7, 2026
etanhey/judge-fleet
development
VerifiedTrustedCommunity
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.
3SKILL.mdUpdated Jun 7, 2026
etanhey/fleet-wrap
development
VerifiedTrustedCommunity
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).
3SKILL.mdUpdated Jun 7, 2026