菜单
根据论文目录下的跟踪文档, 选取最容易实现的未实现任务, 进行科研论文编写工作
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。
基于 SOC 职业分类
| name | killo-golden |
| description | 根据论文目录下的跟踪文档, 选取最容易实现的未实现任务, 进行科研论文编写工作 |
| disable-model-invocation | true |
修改 theory/
请充分理解用户的输入内容, 学术化的进行重组思考
$ARGUMENTS
你 一定 理解用户的输入后, 再修改论文, 完美融入原文. 无需询问用户, 直接修改论文.
Publication Cycle — scans the main theory paper, identifies new paper extractions and existing paper gaps, then orchestrates the full review+fix pipeline. Workflow: Triage → Codex review+fix (2 rounds) → ChatGPT review → Codex fix → Claude review → Codex fix → ChatGPT journal-targeted acceptance gate. During wait times, runs backflow from ACCEPT papers into core theory. Trigger: /pub-cycle, "scan papers", "publication cycle", "review cycle"
Omega Reasoning Protocol — changes how the LLM thinks. Three principles: FORCING (what is structurally inevitable), MINIMIZE (remove assumptions until something breaks), AUDIT (every conclusion traceable to premises). Searches github.com/the-omega-institute/automath for structural correspondences. Use when: deep analysis, reasoning verification, first-principles thinking, or any task that benefits from distinguishing "forced" from "chosen". Trigger: /omega, "think deeply", "first principles", "why is this inevitable"
Write scientific manuscripts with proper structure (IMRAD), citations (APA/AMA/Vancouver), figures/tables, and reporting guidelines (CONSORT/STROBE/PRISMA). Use when drafting any manuscript section, improving writing clarity, or preparing for journal submission.