Mcd Status Codes

麦门监控台 —— 主动运维型身体 SRE。把每一笔麦当劳订单判定为 HTTP 状态码（双方向语义宪法 v4.0：18 码 + 3 指标告警），Agent 依据代谢模型（体重/身高/年龄→BMR→TDEE→分餐预算）在咖啡窗与补给窗主动探活提醒：该喝没喝的咖啡判 599 超时、减脂缺口下发 103 下午茶建议、超预算 412 否决、异常订单自动生成 P1-P3 事故复盘。当用户想回顾麦当劳订单、查看热量/营养/健康合规、生成监控面板或状态码报告、听取主动补给提醒、复盘事故或查询自己的 SRE 职级，或询问 1024 程序员节限定玩法时使用。基于麦当劳中国官方 MCP 只读采集，全部数值确定性可复算。

7 starsSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add chaucerj/mcd-status-codes --skill mcd-status-codes

Manual install

git clone --depth 1 https://github.com/chaucerj/mcd-status-codes.git /tmp/mcd-status-codes
mkdir -p ~/.claude/skills
cp -r /tmp/mcd-status-codes/. ~/.claude/skills/mcd-status-codes

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 麦门监控台 · 身体服务运维 Skill（值班手册）

**语义宪法（最高优先级，任何输出都不得违反）—— v4.0 双方向声明制 + 语义分层**

> **你是主体，你的身体是服务端。**

- **ingest 摄入方向**（你发起）：每一笔订单 = 一次摄入请求，状态码 = 你的身体对这批摄入的生命周期响应（12 码）。营养负荷（热量/钠）是**指标告警**不是状态码（v4.0）：超配额记入 breaches 触发 P1/P2 事故复盘，不占码
- **probe 探活方向**（你的运维 Agent 发起）：Agent 依据代谢模型主动探活，状态码 = 这次探活的结果（6 码：103/204/412/425/599/522）

铁律：

1. ingest 类状态码定义句的主语只能是「你 / 你的身体 / 你的摄入行为」；probe 类主语只能是「你的运维 Agent」，被探对象仍然是你
2. 麦当劳官方数据、MCP 接口、营养表等平台侧事实**只能作为诊断证据**出现，绝不充当状态码定义
3. 一个状态码只有**一个含义、一个方向**，全项目逐字一致
4. **语义的唯一事实源是 `scripts/codes.py`**，完整 18 码定义表与指标告警见 [references/state-codes.md](references/state-codes.md)，冲突时以 codes.py 为准

## 前置条件

- MCP Token：open.mcd.cn/mcp 登录激活，环境变量 `MCD_MCP_TOKEN`
- Python 3.10+，纯标准库零第三方依赖
- 所有命令在**本仓库根目录**执行（本仓库即 Skill 目录）

## 值班流程（每次会话按此顺序执行）

### 第 0 步：交接班播报（主动提醒，先于回答用户问题）

读 `data/ops.json`（若存在）：

- `probesOpen` 队列非空 → **主动播报**每条待处理探活（播报模板见 [references/agent-playbook.md](references/agent-playbook.md)）
- `level` 与上次相比有晋升 → 先报喜
- `newIncidents` 非空 → 播报新事故
- 用户回复「采纳 / 忽略」→ 将对应 probe 的 `status` 改为 `adopted / ignored`（下次 evolve.py 自动判定超时为 timed_out）

### 第 1 步：采集数据（只读）

```bash
python3 scripts/collect.py
```

调用 order-list / query-order（商品图）/ list-nutrition-foods / query-my-account。**禁止调用任何领券、抽奖工具；下单走第 5 步守则。**

### 第 2 步：分类 + 自进化 + 面板

```bash
python3 scripts/classify.py    # ingest 判定（确定性规则，数值不进 LLM）
python3 scripts/evolve.py      # 交接班：事故复盘/口味画像/代谢探活/职级
python3 scripts/report.py      # 单文件 dashboard.html
```

Read the full skill on GitHub

Details

Skill name: mcd-status-codes
Repository: chaucerj/mcd-status-codes
License: MIT
Repo updated: 22 October 2026

FAQ

What does the Mcd Status Codes skill do?

How do I install the Mcd Status Codes skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add chaucerj/mcd-status-codes --skill mcd-status-codes. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Mcd Status Codes popular?

It lives in chaucerj/mcd-status-codes, which has 7 GitHub stars and 0 forks.

Related skills

Safe Encryption

grittygrease/safe-encryption-skill

Encrypt, decrypt, and manage keys with the SAFE CLI — a modern GPG alternative with post-quantum support.

Software DevelopmentIn 1 list

Codebase Map

rdilruba/codebase-map

Build a persistent, evidence-based map of a software repository inside docs/codebase-map/ - TL;DR, architecture and dependency diagrams in Mermaid, real data flows traced with an archetype-specific strategy, the most important files ("the spine"), a reading order, potentially AI-assisted code, key concepts, and open questions. Five modes - "codebase-map init" builds the full map, "codebase-map update" refreshes it after changes, "codebase-map explain [topic]" covers one feature or domain, "codebase-map trace [flow]" follows one request path, "codebase-map check" reports drift without writing.

Software Development

Steam Debug

kmturley/steam-debug

Inspect, debug, and inject custom code into a running Steam client — desktop (macOS, Linux, Windows) or Steam Deck over the network — through its Chromium Embedded Framework (CEF) Chrome DevTools Protocol endpoint. Use when developing Steam UI plugins, mods, themes, or integrations — injecting CSS/JS to try a change, locating webpack modules and obfuscated class names, reading React or SteamUIStore state, inspecting Big Picture / Quick Access Menu windows, screenshotting what actually rendered, streaming console logs, or diagnosing runtime errors in Steam's UI. The same commands run against ei

Software Development

Adobe Fonts Skill

alexh/adobe-fonts-skill

Search Adobe Fonts (Typekit) families, create and manage web kits/projects, and return ready-to-use embed snippets plus CSS font-family values. Use when the user asks to find Adobe fonts, compare font options, set up Typekit for a website, add fonts to kits, publish kits, or generate copy/paste font embed metadata for Codex, Claude Code, or OpenCode workflows.

Software Development

Ynm

RobLe3/ynm-skill

Evidence-backed project and repository review for implementation correctness, architecture, specification-versus-code conflicts, tests-versus-documentation, release or production readiness, adoption, maintenance, security claims, and conflicting project evidence. Enter through lightweight YNM-0 routing, preserve unresolved evidence as MAYBE, and escalate only when additional work can materially improve the disposition.

Software Development

Code Feeder

Ecrypted-Data/Code_Feeder_Skill

当用户需将代码提供给外部 AI（重构/分析/修复）时激活。自动收集代码、记录意图、生成上下文文档。支持增量合并。

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.