Not in the top 1,000 by GitHub stars
Addition2000/mcd-diet-guard
帮有忌口的朋友在麦当劳安心点餐。 不吃猪肉、吃素、海鲜过敏、乳糖不耐、不吃辣、不吃酸黄瓜……说一句话，它就查遍整家门店的实时菜单，告诉你哪些放心点、哪些“去培根”就能吃、套餐里该换成什么，算好价再帮你下单。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/mcd-diet-guard/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 634d4b930ad9
No earlier version was observed for comparison.
120GitHub stars
8stars in 7 days
1skill in this repository
3commits in 30 days
Heat
4.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- mcd-diet-guard
skills/mcd-diet-guard
How it works
mcd-diet-guard
When your agent uses it
麦麦忌口管家。帮有忌口的人（不吃猪肉/清真需求、素食、纯素、海鲜/蛋/奶/麸质过敏、乳糖不耐、不吃辣、不吃葱蒜、不要咖啡因，或“不吃酸黄瓜”这类个人口味）在麦当劳安心点餐：用麦当劳 MCP 查门店实时菜单和每个餐品的特调配料，把餐品分成 放心点/特调后可点/需确认/不建议，套餐自动换成符合忌口的子项并“去培根”等，算价后经用户确认再下单。用户提到麦当劳/麦麦/麦乐送 + 忌口、过敏、吃素、清真、不吃某样东西、帮朋友点餐、多人拼单时使用。
What it loads into context
Frontmatter
208 tokensAlways available to the agent
SKILL.md
2,759 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 四档判定
- 工作流程
- 安全规则（必须遵守）
- 文件
Scripts executed separately
scripts/mcd_diet.py
Files
SKILL.mdcore8,958 bytesSKILL.mdcore8,958 bytesreferences/knowledge.jsonasset9,767 bytesscripts/mcd_diet.pyruns45,910 bytes
Read SKILL.md
# 麦麦忌口管家（mcd-diet-guard）
让有忌口的朋友点麦当劳时不用一个个问店员。核心思路：**麦当劳 MCP 的 `query-meal-detail` 会返回每个餐品可“特调”的配料（如培根、吉士、酸黄瓜、洋葱粒）和套餐每一轮的可选子项**，据此可以判断一个餐品能不能吃、要去掉什么、套餐里该换成什么。
[Credential-related source omitted]
## 四档判定
| 档位 | 含义 | 对用户怎么说 |
|---|---|---|
| ✅ 放心点 | 名称和可见配料里都没发现冲突 | “按菜单信息没发现冲突” —— 不要说“绝对安全” |
| 🔧 特调后可点 | 冲突配料在特调里可以去掉（如 培根蔬萃双层牛堡 去培根），或可替换（黑巧饮品 换燕麦奶） | 写清要去掉/替换什么、是否加价 |
| ⚠<U+FE0F> 需确认 | 可能含有、或识别不出主料（如“如意百宝袋”）、或名称含冲突词但只能去掉部分配料 | 建议到店/下单备注再确认 |
| ❌ 不建议 | 主料冲突且去不掉（猪柳、火腿扒、香肠、麦香鱼之于海鲜过敏），或套餐某一轮只有冲突选项 | 一句话说明原因 |Skills included
- mcd-diet-guard
Repository facts
- License
- MIT
- Created
- Oct 23, 2026
- Last pushed
- Oct 23, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
skills/mcd-diet-guard/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 11 network referencesin 2 files: mcd-diet-guard/scripts/mcd_diet.py:38 mcd-diet-guard/SKILL.md:10
- No hidden or obfuscated text
- No instruction overrides
- 1 executable scriptin 1 file: mcd-diet-guard/scripts/mcd_diet.py:1
- 1 reference to secretsin 1 file: mcd-diet-guard/scripts/mcd_diet.py:856
- No requests to vote in Hot
Show all 13 signals by file
skills/mcd-diet-guard/SKILL.md
- Network accessline 10
[Credential-related source omitted]
skills/mcd-diet-guard/scripts/mcd_diet.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 38
VERSION = "1.0.0" DEFAULT_URL = "https://mcp.mcd.cn" - Network accessline 39
DEFAULT_URL = "https://mcp.mcd.cn" - Network accessline 75
[Credential-related source omitted] - Network accessline 76
[Credential-related source omitted] - Network accessline 77
raise McpError("缺少 MCP Token：请先设置环境变量 MCD_MCP_TOKEN（在 https://open.mcd.cn/mcp 控制台申请）") - Network accessline 105
if self.session_id: headers["Mcp-Session-Id"] = self.session_id req = urllib.request.Request(self.url, data=json.dumps(body).encode("utf-8"), headers=headers, method="POST") - Network accessline 106
headers["Mcp-Session-Id"] = self.session_id req = urllib.request.Request(self.url, data=json.dumps(body).encode("utf-8"), headers=headers, method="POST") try: - Network accessline 107
req = urllib.request.Request(self.url, data=json.dumps(body).encode("utf-8"), headers=headers, method="POST") - Network accessline 108
try: with urllib.request.urlopen(req, timeout=self.timeout) as resp: sid = resp.headers.get("Mcp-Session-Id") - Network accessline 109
with urllib.request.urlopen(req, timeout=self.timeout) as resp: - Access to secretsline 856
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 13 facts
- Network access in prose of the SKILL.mdmcd-diet-guard/SKILL.md:10Low confidence
- Executable script in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:1High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:38High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:39High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:75High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:76High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:77High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:105High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:106High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:107High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:108High confidence
- Network access in code of a file that runsmcd-diet-guard/scripts/mcd_diet.py:109High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuemcd-diet-guard/scripts/mcd_diet.py:856Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/mcd-diet-guard/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/mcd-diet-guard/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/mcd-diet-guard/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/mcd-diet-guard/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/mcd-diet-guard/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/mcd-diet-guard/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
