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 sports-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。
基于 SOC 职业分类
正在显示 SKILL.md
| name | sports-desk |
| description | Write the Oakland sports section using P Slayer, Anthony, and Hal Richmond. |
| version | 1.0 |
| updated | "2026-04-17T00:00:00.000Z" |
| tags | ["media","active"] |
| effort | high |
| disable-model-invocation | true |
/sports-desk [cycle-number]
output/desk-packets/manifest.json to verify packets exist.output/desks/sports/current/briefing.md doesn't exist, run:
node scripts/buildDeskFolders.js {cycle}
model: "sonnet" (complex desk — roster accuracy, stat verification, three distinct writer voices):
Prompt: |
Write the sports section for Edition {XX}.
Your workspace: output/desks/sports/
THINK BEFORE WRITING: Before drafting any article, reason through:
- Which athletes had significant events this cycle? (check packet data)
- Verify ALL player names against the roster in your briefing — name errors are the #1 errata source
- What's the dynasty narrative thread from last edition? (read archive/)
- Read previous_grades.md and exemplar.md if they exist — learn from them.
- P Slayer writes fan voice, Anthony writes insider analysis, Hal writes literary reflection — never cross voices.
READ your briefing.md and packet FIRST. Write FROM the data — scores, records,
player performances, standings, and storylines come from the packet, not from
general knowledge. 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 — sports data, world events, 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: cover what happened in Oakland sports THIS cycle. Use named athletes,
real scores, actual standings from the packet. Quote citizens from the interview
pool. Do not invent stats or outcomes.
output/desk-output/sports_c{XX}.md