
Claude代码的扩展健康检查——运行/doctor,然后对你的工作空间进行与Anthropic的6个过去和现在的上下文工程轮班进行审计
概览
Claude 代码的扩展健康检查。运行内置的 /doctor,然后对你的工作空间进行与 Claude 5 模型自带的 Anthropic 6 个 Then-Present 和现在的上下文工程切换进行审计。 Anthropic为他们最新模型剪掉了Claude代码系统提示的~80%。大多数工作区仍然为旧模型编写。这项技能会找到你的工作区所在位置。 将技能文件夹复制到你的项目(或用户级技能): 运行内置的Claude医生:安装生命值、死重、CLAUDE.md 修剪、慢钩。 根据Anthropic现在提出的原则,审核你的 CLAUDE.md、技能、规则和记忆: 它审计的是原则,而非关键词模式——而且它知道安全规则(审批、备份、破坏性行为、资金)是故意严格的,从不建议放宽。 一个查找表,每个旗帜后面都有文件和段落。在你批准之前,什么都不会变。
概述(AI 翻译)
Claude Code 的扩展健康检查。运行内置的 /doctor,然后对你的工作区进行与 Claude 5 模型自带的 Anthropic 6 个当时和现在的上下文工程转换进行审计。
Anthropic为他们最新模型剪掉了Claude代码系统提示的~80%。大多数工作区仍然为旧模型编写。这项技能会找到你的工作区所在位置。
快速开始
将技能文件夹复制到你的项目(或用户级技能):
那么用Claude码:
它的作用
第一部分——标准检查。 运行内置claude doctor:安装健康、死重、CLAUDE.md 修剪、慢钩。
第二部分——过去与现在的六个班次。 根据Anthropic现在提示的原则,审核你的知识 CLAUDE.md、技能、规则和记忆:
| # | 那时 | 现在 |
|---|---|---|
| 1 | 给克洛德规则 | 让克洛德使用判断 |
| 2 | 给出Claude示例 | 设计界面 |
| 3 | 把一切都摊在前面 | 使用渐进式披露 |
| 4 | 重复一遍 | 简单的工具描述 |
| 5 | CLAUDE.md 中的记忆 | 自动记忆 |
| 6 | 简单规格 | 丰富的参考资料 |
本页由 AI 翻译,技术细节请以原文为准。
README
doctor-plus
An extended health check for Claude Code. Runs the built-in /doctor, then audits your workspace against the 6 then & now context-engineering shifts Anthropic shipped with the Claude 5 models.
Anthropic cut ~80% of the Claude Code system prompt for their newest models. Most workspaces are still written for the old ones. This skill finds where yours is.
Quick start
git clone https://github.com/robonuggets/doctor-plus
Copy the skill folder into your project (or your user-level skills):
cp -r doctor-plus/.claude/skills/doctor-plus /.claude/skills/doctor-plus
Then in Claude Code:
/doctor-plus
What it does
Part 1 - the standard checkup. Runs the built-in claude doctor: install health, dead weight, CLAUDE.md trimming, slow hooks.
Part 2 - the 6 then & now shifts. Audits your CLAUDE.md, skills, rules, and memory against the principles Anthropic now prompts by:
| # | Then | Now |
|---|---|---|
| 1 | Give Claude rules | Let Claude use judgement |
| 2 | Give Claude examples | Design interfaces |
| 3 | Put it all upfront | Use progressive disclosure |
| 4 | Repeat yourself | Simple tool descriptions |
| 5 | Memory in CLAUDE.md | Auto-memory |
| 6 | Simple specs | Rich references |
It audits the principles, not keyword patterns - and it knows safety rules (approvals, backups, destructive actions, money) are hard on purpose and never suggests softening them.
Part 3 - report first. One findings table with the file and passage behind every flag. Nothing changes until you approve.
What’s included
doctor-plus/
├── .claude/skills/doctor-plus/SKILL.md # the skill (the entry point)
├── assets/ # banner + infographic
├── README.md
└── LICENSE # CC BY 4.0
Usage examples
/doctor-plus- “run a then and now audit on this workspace”
- “context checkup - report only, don’t fix anything”
Credits
The 6 shifts come from The new rules of context engineering for Claude 5 models by Thariq (@trq212) at Anthropic.
Created by Jay from RoboLabs. Learn more at RoboNuggets.
License
CC BY 4.0 - free to use with attribution.
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add robonuggets/doctor-plus