用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/pnils08/GodWorld --skill letters-desk命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Close a GodWorld external-lane session (Grok) cleanly: inventory work, land authorized commits if needed, rewrite only NEXT[grok] in SESSION_CONTEXT.md, commit that handoff path-specifically, report git stack / push status. Use when the user says session end, close session, handoff, wrap up, done for now, or runs /session-end. Not the Claude Code session-end skill (no PIN bump, no ROLLOUT sweep, no sessionEndMechanical.js).
Deputy Mayor Brenda Okoro's office. Generates operational statements on West Oakland Stabilization Fund, Community Development, and Economic Development (Osei-portfolio coverage). Carries Mayor's-office operational reality — not political framing.
Oakland Police Chief Rafael Montez. Generates public safety statements, OARI implementation responses, and crime data communications. Professional, measured, data-driven.
正在显示 SKILL.md
基于 SOC 职业分类
| name | letters-desk |
| description | Write the letters to the editor section with citizen voices. |
| version | 1.0 |
| updated | "2026-04-17T00:00:00.000Z" |
| tags | ["media","active"] |
| effort | low |
| disable-model-invocation | true |
/letters-desk [cycle-number]
output/desk-packets/manifest.json to verify packets exist.output/desks/letters/current/briefing.md doesn't exist, run:
node scripts/buildDeskFolders.js {cycle}
model: "haiku" (routine desk — citizen voice letters, lower complexity):
Prompt: |
Write the letters section for Edition {XX}.
Your workspace: output/desks/letters/
Read previous_grades.md if it exists — learn from past performance.
READ your briefing.md and packet FIRST. Write FROM the data — citizen spotlights,
neighborhood dynamics, active storylines, and civic context all come from the
packet. The packet contains real simulation output for this cycle.
Available in your workspace (v3.9):
- briefing.md — story priorities, returning citizens, canon notes, errata
- Desk packet — citizen spotlight detail (named citizens with life events),
neighborhood dynamics, civic context, active arcs, cycle summary
- base_context.json — calendar date, weather, cycle number
- Past desk output — last 3 editions for continuity
- Interview transcripts (if available)
- Truesource reference data
Your job: write letters from Oakland citizens reacting to THIS cycle's events.
Use named citizens from the spotlight or interview pool — real POPIDs, real
neighborhoods, real occupations from the packet. Each letter should respond to
a different storyline or event. Do not invent citizens.
output/desk-output/letters_c{XX}.md