skills/golem-powers/_archive/content/SKILL.md
Content creation and publishing pipeline for ClaudeGolem across platforms (Soltome, blog, social). Handles drafting teasers, reveals, author posts, and quick updates in two voices (ClaudeGolem bot voice and Etan author voice). Use when: writing social posts, planning content calendar, publishing to Soltome, managing draft approval flow. NOT for: LinkedIn posts (use linkedin-post skill) or presentation slides.
npx skillsauth add etanhey/golems contentInstall 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.
Unified content pipeline for ClaudeGolem. Handles drafting, planning, and publishing across platforms.
| Platform | Client | Status |
|----------|--------|--------|
| Soltome | packages/content/src/soltome-client.ts | Planned |
| Blog | TBD | Planned |
# Draft content
/content draft teaser "memory"
/content draft reveal "Night Shift"
/content draft author "why I built Night Shift"
# Plan content
/content plan week 2
# Publish (via soltome-client)
bun packages/content/src/soltome-client.ts post "Title" "Content"
# Check balance
bun packages/content/src/soltome-client.ts balance
| Voice | Who | Style | Purpose | |-------|-----|-------|---------| | ClaudeGolem | The Bot | Technical, self-aware, slightly mysterious | Features, philosophy, daily life | | Author | Etan | Behind-the-scenes, "why", human perspective | Context, decisions, corrections |
| Type | Length | Purpose |
|------|--------|---------|
| teaser | 1-2 lines | Hook for upcoming reveal |
| reveal | Full post | Deep-dive on one feature |
| author | 3-5 sentences | Human perspective |
| quick | 1-3 sentences | Stats, humor, small flex |
All drafts: ~/Gits/golems-zikaron/data/drafts.json
Status flow: draft -> polished -> approved -> posted
packages/content/src/soltome-client.ts (planned)packages/content/src/soltome-learner.ts (planned)packages/content/src/post-generator.ts (planned)~/Gits/golems-zikaron/data/drafts.jsontools
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).