- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add LilMGenius/paperthin --skill nba -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add LilMGenius/paperthin --skill nba -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add LilMGenius/paperthin --skill nba -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add LilMGenius/paperthin --skill nba -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/LilMGenius/paperthin/tree/HEAD/skills/coil/nba来自发布者
Find the next best action from live cycle state.
nba provides manual re-entry into a stalled cycle. Read the current state and recommend one action: the cheapest move that clears the binding constraint. Do not execute it or offer a menu that leaves the choice unresolved.
nba recommends; it does not execute.Before finishing:
Read the live cycle state and return the single highest-leverage next best action, not a menu. Use when a project is between phases, the author asks what to do next, too many valid threads are open, o
---name: nbadescription: Read the live cycle state and return the single highest-leverage next best action, not a menu. Use when a…---# skills/coil/nba/SKILL.md概览
Read the live cycle state and return the single highest-leverage next best action, not a menu. Use when a project is between phases, the author asks what to do next, too many valid threads are open, or the work needs re-entry into frame, build, drive, re0-memo, hate, re0-work, or ship.
常见问题
从发布者处下载 skills/coil/nba/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/LilMGenius/paperthin。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。