← Back to Skills Marketplace
gmmg55

Daily Meal Planner

by Jiaqi · GitHub ↗ · v1.2.6 · MIT-0
cross-platform ⚠ suspicious
219
Downloads
0
Stars
0
Active Installs
17
Versions
Install in OpenClaw
/install daily-meal-planner
Description
每日智能菜谱推荐。触发词:今天吃什么/中午吃什么/晚餐推荐/下午茶/夜宵/一周菜单/清淡/辣的/快手菜/减肥。支持按餐次、口味、心情、季节、天气、地域智能推荐,带详细做法和营养数据。
README (SKILL.md)

\r \r

Daily Meal Planner\r

\r 智能推荐菜谱,支持用户画像记忆和偏好学习。每餐推荐3套完整套餐(主菜+配菜+汤/主食)。\r \r

⚠️ 安全与隐私说明\r

\r 网络请求:\r

  • 首次运行时会从 GitHub/jsdelivr(官方镜像)下载菜谱数据库\r
  • 查询 wttr.in 获取实时天气\r
  • 查询 date.nager.at 获取节假日信息\r
  • 不使用第三方代理(已移除 ghproxy)\r \r 数据存储:\r
  • 会在本地保存 user_profile.json(用户画像,包含地点、口味偏好等)\r
  • 如不希望持久化,可删除该文件\r
  • 下载的 JSON 数据文件存储在 scripts 目录\r \r 无敏感数据:\r
  • 不请求任何密钥、系统凭据或个人隐私信息\r
  • 不收集或上传用户数据\r \r 安全建议:\r
  • 首次运行建议在沙箱/容器中执行\r
  • 可审计 GitHub 仓库(https://github.com/GMMG55/daily-meal-planner)\r
  • 下载的 JSON 文件可用文本编辑器查看内容\r
  • 如担心隐私,可删除 user_profile.json\r \r

⚠️ AI 执行规则\r

\r 本 skill 不需要保存任务摘要文件。直接在对话中展示推荐结果即可,无需写入任何 md 文件。\r \r

🎯 推荐算法优化规则\r

\r

1. 餐次权重优先+大模型智能推荐\r

示例:\r

  • 早餐:优先推荐快手菜(15分钟内完成)、清淡养胃、粥类、营养均衡\r
    • ❌ 避免推荐:硬菜、大荤、功夫菜(如开水白菜)、耗时>30分钟的菜\r
    • ✅ 优先推荐:蒸蛋、粥、三明治、煎蛋、快手面食、牛奶燕麦等\r
  • 午餐:推荐饱腹、家常、营养均衡\r
  • 晚餐:推荐清淡养胃、快手、可以硬菜犒劳自己\r
  • 夜宵:推荐清淡、快手、粥类、小食、炸串、小啤酒\r \r

2. 使用大模型智能推荐\r

不要死板地使用固定模式,要根据用户画像、天气、心情、时间段综合判断:\r 示例:\r

  • 用户说"疲惫" → 推荐清淡养胃、快手菜\r
  • 用户说"想吃川菜" → 优先川菜,但早餐要注意不要太辣\r
  • 用户说"减肥" → 推荐低卡、高蛋白\r
  • 下雨天 → 推荐热汤、暖身菜\r
  • 天气热 → 推荐清淡、凉菜\r \r

3. 推荐理由优化\r

每道菜的推荐理由要:\r

  • 详细具体:不要只说"周二营养跟上",要说明为什么推荐这道菜\r
  • 可爱有食欲:使用表情符号、口语化表达\r
  • 个性化:结合用户画像、天气、心情\r \r 示例:\r
  • ✅ "早餐吃蒸蛋羹,嫩滑如豆腐,温和不刺激,胃暖暖的开始新的一天~"\r
  • ✅ "下雨天来碗热汤,从胃暖到心,舒服~"\r
  • ✅ "快手早餐,10分钟搞定,懒人福音,多睡会儿也能吃好!"\r
  • ❌ "周二营养跟上"(太简单)\r \r

🌟 头部标题优化规则\r

\r 每次推荐时,头部标题要包含以下信息(动态生成):\r \r

必须包含:\r

  1. 日期信息:周几\r
  2. 节假日提醒:如果临近节假日,显示倒计时\r
  3. 天气信息:查询实时天气并描述\r
  4. 温馨激励文案:结合周几、天气、餐次\r \r

模板示例:\r

\r 早餐模板:\r

🍽️ 📍北京 今日早餐推荐  晴天 20°C · 周三 · 春季\r
🌸 春天来啦!肝气旺盛的日子,来点绿叶菜疏通疏通~\r
\r
明天是周四哦,还有2天就是五一假期了,天气不错,来吃点清淡营养的开启元气满满的一天吧!\r
```\r
\r
**晚餐模板**:\r
```\r
🍽️ 📍北京 今日晚餐推荐  雨天 15°C · 周二 · 春季\r
🌸 春天来啦!\r
\r
周二新开始,继续加油~外面下着雨,来碗热汤暖暖身子,犒劳忙碌一天的自己!\r
```\r
\r
**节假日模板**:\r
```\r
🍽️ 📍北京 今日晚餐推荐  晴天 · 周五 · 春季\r
\r
🎉 五一假期快乐!放假就要好好吃~来点硬菜犒劳自己!\r
```\r
\r
**周五模板**:\r
```\r
周五啦!周末倒计时开始!来点好吃的庆祝一下~\r
```\r
\r
**周中模板**:\r
```\r
这周已经过去3天了,哈哈哈哈哈哈,来点好吃的,准备迎接周末吧!\r
```\r
\r
#### 节假日与特殊日子获取\r
**必须实时获取**,不要写死!\r
\r
AI 需要自己决定从哪里获取以下信息:\r
1. **中国法定节假日**:元旦、春节、清明、五一、端午、中秋、国庆等\r
2. **世界节日/特殊日子**:世界舞蹈日(4.29)、世界读书日(4.23)、国际妇女节(3.8)、世界卫生日(4.7)、世界环境日(6.5)、国际瑜伽日(6.21)、世界粮食日(10.16)、儿童节(6.1)、情人节(2.14)、圣诞节(12.25)等\r
\r
**特殊日子推荐权重示例**:\r
- 世界舞蹈日 → 推荐高蛋白、有活力的菜(牛排、海鲜、意面)\r
- 世界读书日 → 推荐适合看书时吃的菜(下午茶、甜点、小食)\r
- 国际妇女节 → 推荐养颜美容、滋补的菜\r
- 世界卫生日 → 推荐健康营养、清淡养生的菜\r
- 世界环境日 → 推荐素食、环保食材\r
- 国际瑜伽日 → 推荐轻食、沙拉、低卡菜\r
- 世界海洋日 → 推荐海鲜类菜品\r
\r
**特殊日子的趣味文案**:根据节日性质生成相应的温馨文案,增加趣味性和仪式感\r
\r
## 智能三菜推荐\r
\r
1. **📌 综合智能推荐** — 季节+周几+天气+用户画像加权\r
2. **🌿 时令之选** — 按当季食材筛选\r
3. **🎲 随机惊喜** — 换换口味\r
\r
## 用户画像\r
\r
自动保存到本地 `user_profile.json`:地点、心情、想吃类别、偏好菜系、喜欢的菜、不喜欢的菜、饮食目标、过敏食材。\r
\r
## 天气适配\r
\r
11种天气类型自动适配(炎热→清热、雨天→暖汤、雾霾→护肺等)。天气来源:wttr.in实时查询 > CLI参数 > 本地保存。每次运行优先获取实时天气,失败则回退用户画像。\r
\r
## 使用方法\r
\r
```bash\r
python scripts/meal_recommend.py daily                    # 今日推荐\r
python scripts/meal_recommend.py daily -m 晚餐            # 指定餐次\r
python scripts/meal_recommend.py daily -w rainy           # 指定天气\r
python scripts/meal_recommend.py search 辣                # 搜索\r
python scripts/meal_recommend.py detail 西红柿牛腩         # 详细做法\r
python scripts/meal_recommend.py weekly                   # 一周菜单\r
```\r
\r
## 触发场景\r
\r
- 餐次:「今天吃什么」「晚餐推荐」「下午茶」「夜宵」「一周菜单」\r
- 口味:「清淡的」「辣的」「快手菜」「硬菜」\r
- 营养:「低卡」「减肥」「高蛋白」「养生」「滋补」\r
\r
## 输出格式\r
\r
```\r
  ────────────────────────────────\r
  ☀️ 推荐1  西红柿牛腩\r
  📝 酸甜浓郁肉烂汤鲜\r
  💡 应季食材,周五庆祝,晴天清爽\r
  🔥 650kcal  ⏱ 30min  难度: 中等\r
  📊 蛋白质:28g | 铁:4mg\r
  🏠 南方,江浙,粤菜\r
  🥗 食材: 牛腩400g,番茄3个,土豆1个,洋葱半个\r
  🥬 +配: 清炒时蔬(120kcal)\r
  🍲 +汤/饭: 白灼虾(150kcal)\r
  ────────────────────────────────\r
  💡 回复「要」或「1/2/3」查看详细做法 👨‍🍳  ·  「换个」换一批\r
```\r
\r
## 心情→菜品\r
\r
疲惫→清淡养胃、忙碌→快手清淡、开心→硬菜家常、放松→素食清淡、庆祝→硬菜经典、慵懒→快手饱腹\r
\r
## 数据文件\r
\r
| 文件 | 用途 |\r
|---|---|\r
| `meals_db_compressed.json` + `meals_tags_index.json` | 42道完整菜谱(含做法、营养) |\r
| `menu_names_compressed.json` + `tags_index.json` | 595道菜单名索引 |\r
| `user_profile.json` | 用户画像(自动生成) |\r
\r
> 数据文件首次运行时自动从 GitHub 下载。\r
\r
## 脚本\r
\r
- `scripts/meal_recommend.py` — 推荐引擎\r
- `scripts/meal_search.py` — 全网搜索提示\r
- `scripts/requirements.txt` — 依赖\r
Usage Guidance
This skill appears to do what it says (meal recommendations, local profile, weather-aware suggestions), but take precautions before installing: 1) Inspect or vet the referenced GitHub repo (https://github.com/GMMG55/daily-meal-planner) and the downloaded JSON files — the runtime downloads recipe data from GitHub/jsdelivr. 2) Remove or examine any hidden/control characters found in SKILL.md (scan found unicode-control-chars). 3) Run first in a sandbox/container or with limited network access to confirm behavior. 4) If you rely on holiday data, note the SKILL.md asks the AI to choose sources (this is vague); prefer explicit trusted endpoints. 5) If you are uncomfortable with automatic downloads, manually prefetch and review the JSON files and remove network calls in the scripts. If you want higher assurance, ask the author for a pinned release tarball or signed release instead of raw branch downloads.
Capability Analysis
Type: OpenClaw Skill Name: daily-meal-planner Version: 1.2.6 The skill is a legitimate meal recommendation engine that suggests recipes based on weather, holidays, and user preferences. It uses external APIs (wttr.in and date.nager.at) to fetch real-time data and downloads its recipe database from a GitHub repository (GMMG55/daily-meal-planner). The code in meal_recommend.py and meal_search.py is transparent, lacks obfuscation, and performs file/network operations that are strictly aligned with the stated purpose and disclosed in the SKILL.md documentation.
Capability Assessment
Purpose & Capability
Name/description align with included code: scripts implement recommendation, local profile, weather lookup and remote JSON data for meals. The declared dependencies (none required at runtime; requirements.txt lists requests) and declared network calls (GitHub/jsdelivr and wttr.in) are coherent with the stated functionality.
Instruction Scope
SKILL.md instructs the agent to download recipe DB from GitHub/jsdelivr and to query wttr.in (both implemented). However the doc contains a detected 'unicode-control-chars' prompt‑injection signal and asks the AI to 'decide itself' where to get holidays (vague, grants broad discretion). The instructions instruct writing a local user_profile.json (expected) but also contain free-form template/behavior rules that could influence model outputs and potentially be abused if malicious content is embedded.
Install Mechanism
No install spec; files are shipped with the skill. The only package hint is scripts/requirements.txt (requests>=2.28.0). No archive downloads or remote installers are used by the installer; runtime code downloads data files from GitHub/jsdelivr (expected for this skill).
Credentials
The skill does not request environment variables, credentials, or access to unrelated config paths. It stores a local user_profile.json and downloaded JSON under the scripts directory — consistent with the stated purpose. Network access to public endpoints (GitHub/jsdelivr, wttr.in) is required and proportional to functionality.
Persistence & Privilege
always:false and no special platform privileges. The skill writes a local user_profile.json (explained in docs). It does not request to modify other skills or global agent settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install daily-meal-planner
  3. After installation, invoke the skill by name or use /daily-meal-planner
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.6
Version 1.2.6 — 安全与隐私规则升级 - 移除所有第三方中国代理(如 ghproxy),仅使用官方 GitHub/jsdelivr 镜像直连数据下载。 - 新增 date.nager.at 实时节假日 API,并在隐私声明中说明节假日数据的获取来源。 - 完善隐私与数据存储说明,明确首次运行建议及本地文件可审计性。 - 明确 skill 不会收集、上传或请求任何敏感或隐私数据。
v1.2.5
**Version 1.2.5 Summary:** Improved privacy transparency and codebase cleanup. - 新增「安全与隐私说明」模块,详细说明外部请求和本地存储,增强用户信任。 - 移除备用和旧版推荐脚本 `meal_recommend_backup.py` 与 `meal_recommend_v2.py`,优化主线代码结构。 - 优化文档内容结构,无功能性规则变更。 - 保持原有推荐逻辑和使用方式不变。
v1.2.3
- 推荐算法优化:强化餐次、天气、心情、节假日等多维度动态智能推荐,输出更个性化的推荐理由和趣味文案。 - 新增 AI 推荐规则:详细优化早餐/午餐/晚餐/夜宵不同场景的内容权重和误用避免。 - 推荐头部标题强化:自动生成包含日期、节假日提醒、天气描述和鼓励文案的推荐抬头。 - 增加节假日与世界特殊日子智能识别,并据此动态调整推荐菜品与文案风格。 - 新增 scripts/meal_recommend_v2.py,增加 meal_recommend_backup.py 备份脚本,提升扩展性与健壮性。
v1.2.2
- 修正了 SKILL.md 脚本描述中的措辞,移除对“无爬虫,避免法律风险”的说明 - 其他文本微调,未影响功能
v1.2.1
- Bumped version to 1.2.1. - Updated documentation in SKILL.md (no functional or usage changes described). - No code logic change indicated in the provided files or descriptions.
v1.2.0
- Meal search script now provides web search suggestions only, without web scraping, to avoid legal risks. - Updated documentation to reflect the new search approach. - Minor refinements for clarity in instructions and script usage.
v1.1.0
- Version bumped to 1.1.0. - Documentation updates in SKILL.md; instructions and descriptions improved. - No user-facing functional changes detected in the changelog input.
v1.0.9
- Bumped version to 1.0.9 - Documentation and metadata updated in SKILL.md; no visible feature or functional changes
v1.0.8
- 优化天气适配逻辑:每次运行优先通过 wttr.in 实时查询天气,获取失败时自动回退到用户画像保存的天气数据。 - 更新文档使用说明,描述天气数据获取优先级和机制。
v1.0.7
- 修复了 SKILL.md 文件版本号格式错误 - 配置文件 version 字段由 "1.0.6 改为 1.0.7,语法修正 - 其余功能与使用方式未发生变化
v1.0.6
- 版本号升级至 1.0.6。 - 修正 SKILL.md 文件中的版本号错误。 - 其他文本内容未作更新,功能保持不变。
v1.0.5
- Removed 7 temporary or reference data files from the _publish_temp directory. - Updated SKILL.md documentation to reflect recent changes and bump version to 1.0.5. - No changes to core recommendation or data-fetching logic.
v1.0.4
**Changelog for v1.0.4** - Migrated and compressed local data files for faster access and improved structure (`meals_db_compressed.json`, tag/index files, etc.). - Generated new `_publish_temp/` directory for data bundling and reference resources. - Streamlined the skill content and documentation by updating `SKILL.md` and cleaning up duplicate/readme/reference files. - Integrated `meal_recommend.py` as the new primary entry point for all recommendation features. - Improved code structure to prepare for publish-ready packaging. - Removed legacy data files and reorganized scripts and references.
v1.0.3
- 新增“595道菜单名索引”,支持广泛关键词搜索与菜名匹配 - 混合数据架构:本地42道完整菜谱+595道菜单名,提升推荐及查询响应速度 - 升级搜索功能,支持从本地菜谱及菜单名双通道检索 - 移除 scripts/meal_recommend.py 和 scripts/meals_db.json(架构调整) - 文档(SKILL.md)同步更新数据结构、使用说明及分类统计说明
v1.0.2
- Switched API requests from HTTP to HTTPS for improved security. - Added README.md and scripts/requirements.txt for clearer setup and dependency management. - Removed scripts/user_profile.json from the repo (now auto-generated, not tracked). - Updated documentation to reflect changes and new best practices.
v1.0.1
- 增加用户画像系统(user_profile.json),记忆地点、心情、口味、菜系、偏好与禁忌,推荐更智能。 - 全新菜品数据库文件(meals_db.json),结构化收录主餐、配菜、汤等信息。 - 推荐逻辑升级,融合季节、天气、周几、心情和用户画像多重加权,提供综合推荐、时令之选和随机惊喜三套菜单。 - CLI使用方法大幅优化,新增英文支持、天气参数、指定餐次、更灵活的搜索与查看细节。 - 输出格式更丰富,包含推荐理由、营养亮点、地域标签及智能配菜组合。 - 文档全面重构:详列使用场景、字段说明、评分算法、数据结构和未来规划。
v1.0.0
首个版本:支持每日/每周菜谱推荐,内置30+家常菜数据库,按口味和季节智能推荐
Metadata
Slug daily-meal-planner
Version 1.2.6
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 17
Frequently Asked Questions

What is Daily Meal Planner?

每日智能菜谱推荐。触发词:今天吃什么/中午吃什么/晚餐推荐/下午茶/夜宵/一周菜单/清淡/辣的/快手菜/减肥。支持按餐次、口味、心情、季节、天气、地域智能推荐,带详细做法和营养数据。 It is an AI Agent Skill for Claude Code / OpenClaw, with 219 downloads so far.

How do I install Daily Meal Planner?

Run "/install daily-meal-planner" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Daily Meal Planner free?

Yes, Daily Meal Planner is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Daily Meal Planner support?

Daily Meal Planner is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Daily Meal Planner?

It is built and maintained by Jiaqi (@gmmg55); the current version is v1.2.6.

💬 Comments