Not in the top 1,000 by GitHub stars
likangkangkang/mcd-tarot
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
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 7286fc846c09
No earlier version was observed for comparison.
Heat
Insufficient historyNot enough history yet to measure heat. It appears after a few days of data.
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
How it works
mcd-tarot
When your agent uses it
用塔罗牌的仪式感做「一张图预测」:每次抽一张把汉堡画成塔罗圣像的牌面 + 一段暖心解读,默认优先套餐(并在套餐名下方写明每样餐品和数量)、叠加立减与满减券,结合口味习惯与点餐时段,确认后可直接下单(付款由用户本人完成)。支持「今日宜吃」与「按问题抽一张预测」两种单张场景,含正逆位、真实菜单价格与优惠。**首次被唤起时先自我介绍、说明能做什么,并询问是否开启今日运势(只需对方回答 是 / 否),得到肯定才抽牌**。仅做情绪陪伴与选餐建议;深度比价、凑单算最优券、代点外卖请用点餐/省钱类技能。
What it loads into context
Frontmatter
316 tokensAlways available to the agent
SKILL.md
3,636 tokensWhen the skill is activated
Reference documents
5,670 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 首次使用:先打招呼(每次会话开场必查)
- 两种玩法(每次都只抽一张、出一张图)
- 启用前提
- 快速路径(日常首选)
- 工作流(缓存缺失或要下单时走)
- 下单与支付(真实花钱,必须守规矩)
- 情绪价值与输出规范
- 与其它技能的边界
- 维护
- 模块参考
Scripts executed separately
scripts/cache.pyscripts/combo_detail.pyscripts/mcp_client.pyscripts/menu_from_connector.pyscripts/onboard.pyscripts/order.pyscripts/pack.pyscripts/profile.pyscripts/quick.pyscripts/selfcheck.pyscripts/tarot_art.pyscripts/tarot_card.pyscripts/tarot_deck.pyscripts/tarot_engine.pyscripts/tarot_sense.pytests/test_tarot_engine.py
Files
.gitignoreasset178 bytesREADME.mddoc12,528 bytesSKILL.mdcore12,211 bytesSKILL.mdcore12,211 bytesSKILL.mdcore12,211 bytesassets/.env.exampleasset201 bytesassets/mcp-config.example.jsonasset194 bytesassets/requirements.txtdoc192 bytesassets/sample-card.jpgasset65,923 bytesassets/sample-card.svgasset24,645 bytesreferences/INSTALL.mddoc3,075 bytesreferences/MCP_INTEGRATION.mddoc2,453 bytesreferences/README.mddoc379 bytesreferences/sample_reading.mddoc946 bytesscripts/cache.pyruns7,099 bytesscripts/combo_detail.pyruns17,761 bytesscripts/mcp_client.pyruns33,690 bytesscripts/menu_from_connector.pyruns6,505 bytesscripts/onboard.pyruns5,031 bytesscripts/order.pyruns8,253 bytesscripts/pack.pyruns2,986 bytesscripts/profile.pyruns21,279 bytesscripts/quick.pyruns7,204 bytesscripts/selfcheck.pyruns6,374 bytesscripts/tarot_art.pyruns37,000 bytesscripts/tarot_card.pyruns20,930 bytesscripts/tarot_deck.pyruns25,225 bytesscripts/tarot_engine.pyruns30,756 bytesscripts/tarot_sense.pyruns16,749 bytestests/test_tarot_engine.pyruns36,983 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- mcd-tarot
Repository facts
- License
- No license detected
- Created
- Oct 20, 2026
- Last pushed
- Oct 21, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 7 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedassets/sample-card.svg:51Analysis incomplete: physical or joined line exceeds character limitassets/sample-card.svg:49Analysis incomplete: physical or joined line exceeds character limitassets/sample-card.svg:50Analysis incomplete: physical or joined line exceeds character limitassets/sample-card.svg:53Analysis incomplete: physical or joined line exceeds character limitassets/sample-card.svg:52Analysis incomplete: physical or joined line exceeds character limit
- No broad tool permissions
- No dangerous shell commands
- 30 network referencesin 8 files: scripts/mcp_client.py:23 scripts/tarot_card.py:115 README.md:18 and 5 more
- No hidden or obfuscated text
- No instruction overrides
- 16 executable scriptsin 16 files: scripts/cache.py:1 scripts/combo_detail.py:1 scripts/mcp_client.py:1 and 13 more
- 26 references to secretsin 11 files: tests/test_tarot_engine.py:173 README.md:101 references/MCP_INTEGRATION.md:8 and 8 more
- No requests to vote in Hot
Show all 72 signals by file
README.md
- Network accessline 18
1. 下载技能包:[`mcd-tarot-skill.zip`](https://github.com/likangkangkang/mcd-tarot/releases/download/v1.0.0/mcd-tarot-skill.zip) - Network accessline 30
git clone https://github.com/likangkangkang/mcd-tarot.git ~/.workbuddy/skills/mcd-tarot - Network accessline 36
git clone https://github.com/likangkangkang/mcd-tarot.git "$HOME\.workbuddy\skills\mcd-tarot" - Network accessline 41
按开放平台规范把技能包 zip 提交审核即可(详见 [open.workbuddy.cn/docs/skill](https://open.workbuddy.cn/docs/skill)); - Access to secretsline 101
[Credential-related source omitted] - Access to secretsline 174
[Credential-related source omitted]
SKILL.md
- Access to secretsline 143
[Credential-related source omitted]
assets/mcp-config.example.json
assets/sample-card.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="750" height="1200" viewBox="0 0 750 1200">
references/INSTALL.md
- Network accessline 3
## 单一真源 - 唯一来源就是这个目录:`~/.workbuddy/skills/mcd-tarot/`(WorkBuddy 直接加载的「主 skill」)。 - 目录本身就是一个 git 仓库,`origin` = https://github.com/likangkangkang/mcd-tarot - Network accessline 4
- 唯一来源就是这个目录:`~/.workbuddy/skills/mcd-tarot/`(WorkBuddy 直接加载的「主 skill」)。 - 目录本身就是一个 git 仓库,`origin` = https://github.com/likangkangkang/mcd-tarot - **不再维护第二份副本**:改动直接在主 skill 里做,然后 `git commit && git push`;仓库与本地永远同一份代码。 - Network accessline 5
- 目录本身就是一个 git 仓库,`origin` = https://github.com/likangkangkang/mcd-tarot
references/MCP_INTEGRATION.md
- Network accessline 5
## 1. 连接的 MCP Server - **名称**:`mcd-mcp` - **端点**:`https://mcp.mcd.cn`(Streamable HTTP) - Network accessline 6
[Credential-related source omitted] - Network accessline 7
- **端点**:`https://mcp.mcd.cn`(Streamable HTTP) - Access to secretsline 8
[Credential-related source omitted] - Access to secretsline 44
[Credential-related source omitted]
scripts/cache.py
scripts/combo_detail.py
- Executable scriptline 1
Executable file
scripts/mcp_client.py
- Executable scriptline 1
Executable file - Network accessline 23
MCD_MCP_URL = "https://mcp.mcd.cn" - Network accessline 81
[Credential-related source omitted] - Network accessline 82
data = json.dumps(payload).encode("utf-8") req = urllib.request.Request(MCD_MCP_URL, data=data, method="POST") req.add_header("Authorization", f"Bearer {token}") - Network accessline 83
req = urllib.request.Request(MCD_MCP_URL, data=data, method="POST") - Network accessline 87
if session_id: req.add_header("Mcp-Session-Id", session_id) resp = urllib.request.urlopen(req, timeout=20) - Network accessline 88
req.add_header("Mcp-Session-Id", session_id) resp = urllib.request.urlopen(req, timeout=20) body = resp.read().decode("utf-8") - Network accessline 89
resp = urllib.request.urlopen(req, timeout=20) - Access to secretsline 159
[Credential-related source omitted] - Access to secretsline 811
[Credential-related source omitted]
scripts/menu_from_connector.py
- Executable scriptline 1
Executable file
scripts/onboard.py
scripts/order.py
- Executable scriptline 1
Executable file - Network accessline 16
# 2) 连接器 create-order 成功后登记(支付仍由用户完成) python3 scripts/order.py record --order-id 123456 --pay-url "https://..." --total 34.0 - Network accessline 17
python3 scripts/order.py record --order-id 123456 --pay-url "https://..." --total 34.0 - Access to secretsline 36
[Credential-related source omitted]
scripts/pack.py
- Executable scriptline 1
Executable file
scripts/profile.py
scripts/quick.py
- Executable scriptline 1
Executable file
scripts/selfcheck.py
- Executable scriptline 1
Executable file
scripts/tarot_art.py
- Executable scriptline 1
Executable file
scripts/tarot_card.py
- Executable scriptline 1
Executable file - Network accessline 115
if not path.exists(): try: req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0 (mcd-tarot)"}) - Network accessline 116
try: req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0 (mcd-tarot)"}) with urllib.request.urlopen(req, timeout=8) as resp: - Network accessline 117
req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0 (mcd-tarot)"}) - Network accessline 118
with urllib.request.urlopen(req, timeout=8) as resp: - Network accessline 287
title = _esc(meta.get("title") or CARD_TITLE) return f"""<svg xmlns="http://www.w3.org/2000/svg" width="{W}" height="{H}" viewBox="0 0 {W} {H}"> - Network accessline 288
return f"""<svg xmlns="http://www.w3.org/2000/svg" width="{W}" height="{H}" viewBox="0 0 {W} {H}"> - Network accessline 413
parts = [f'<svg xmlns="http://www.w3.org/2000/svg" width="{canvas_w:.0f}" '
scripts/tarot_deck.py
- Executable scriptline 1
Executable file
scripts/tarot_engine.py
scripts/tarot_sense.py
- Executable scriptline 1
Executable file
tests/test_tarot_engine.py
- Executable scriptline 1
Executable file - Access to secretsline 173
[Credential-related source omitted] - Access to secretsline 174
[Credential-related source omitted] - Access to secretsline 188
[Credential-related source omitted] - Access to secretsline 190
[Credential-related source omitted] - Access to secretsline 268
[Credential-related source omitted] - Access to secretsline 269
[Credential-related source omitted] - Access to secretsline 285
[Credential-related source omitted] - Access to secretsline 287
[Credential-related source omitted] - Access to secretsline 610
[Credential-related source omitted] - Access to secretsline 611
[Credential-related source omitted] - Access to secretsline 619
[Credential-related source omitted] - Access to secretsline 621
[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.
Some files could not be read; the facts below still hold.
Declared and executed: 2 facts
- Contacts mcp.mcd.cn, which SKILL.md, the README and the plugin manifest do not mentionscripts/mcp_client.py:23High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionscripts/tarot_card.py:288High confidence
Signal confidence: 67 facts
- Network access in prose of documentationREADME.md:18Low confidence
- Network access in code of documentationREADME.md:30Low confidence
- Network access in code of documentationREADME.md:36Low confidence
- Network access in prose of documentationREADME.md:41Low confidence
- Access to secrets in code of documentationREADME.md:101Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valueREADME.md:174Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueSKILL.md:143Low confidence
- Network access in prose of documentationreferences/INSTALL.md:3Low confidence
- Network access in prose of documentationreferences/INSTALL.md:4Low confidence
- Network access in prose of documentationreferences/INSTALL.md:5Low confidence
- Network access in prose of documentationreferences/MCP_INTEGRATION.md:5Low confidence
- Network access in prose of documentationreferences/MCP_INTEGRATION.md:6Low confidence
- Network access in prose of documentationreferences/MCP_INTEGRATION.md:7Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valuereferences/MCP_INTEGRATION.md:8Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valuereferences/MCP_INTEGRATION.md:44Low confidence
- Executable script in prose of a file that runsscripts/cache.py:1Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/cache.py:42Low confidence
- Executable script in prose of a file that runsscripts/combo_detail.py:1Low confidence
- Executable script in prose of a file that runsscripts/mcp_client.py:1Low confidence
- Network access in code of a file that runsscripts/mcp_client.py:23High confidence
- Network access in code of a file that runsscripts/mcp_client.py:81High confidence
- Network access in code of a file that runsscripts/mcp_client.py:82High confidence
- Network access in code of a file that runsscripts/mcp_client.py:83High confidence
- Network access in code of a file that runsscripts/mcp_client.py:87High confidence
- Network access in code of a file that runsscripts/mcp_client.py:88High confidence
- Network access in code of a file that runsscripts/mcp_client.py:89High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/mcp_client.py:159Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/mcp_client.py:811Low confidence
- Executable script in prose of a file that runsscripts/menu_from_connector.py:1Low confidence
- Executable script in prose of a file that runsscripts/onboard.py:1Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/onboard.py:33Low confidence
- Executable script in prose of a file that runsscripts/order.py:1Low confidence
- Network access in prose of a file that runsscripts/order.py:16Low confidence
- Network access in prose of a file that runsscripts/order.py:17Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/order.py:36Low confidence
- Executable script in prose of a file that runsscripts/pack.py:1Low confidence
- Executable script in prose of a file that runsscripts/profile.py:1Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/profile.py:43Low confidence
- Executable script in prose of a file that runsscripts/quick.py:1Low confidence
- Executable script in prose of a file that runsscripts/selfcheck.py:1Low confidence
- Executable script in prose of a file that runsscripts/tarot_art.py:1Low confidence
- Executable script in prose of a file that runsscripts/tarot_card.py:1Low confidence
- Network access in code of a file that runsscripts/tarot_card.py:115High confidence
- Network access in code of a file that runsscripts/tarot_card.py:116High confidence
- Network access in code of a file that runsscripts/tarot_card.py:117High confidence
- Network access in code of a file that runsscripts/tarot_card.py:118High confidence
- Network access in code of a file that runsscripts/tarot_card.py:287High confidence
- Network access in code of a file that runsscripts/tarot_card.py:288High confidence
- Network access in code of a file that runsscripts/tarot_card.py:413High confidence
- Executable script in prose of a file that runsscripts/tarot_deck.py:1Low confidence
and 17 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md 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.