← 返回 Skills 市场
Recipe Finder
作者
cp3d1455926-svg
· GitHub ↗
· v2.0.0
· MIT-0
135
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cp3d1455926-svg-recipe-finder
功能描述
推荐适合现有食材的菜谱,提供详细做法、烹饪技巧及营养信息,支持随机和个性化推荐。
使用说明 (SKILL.md)
🍳 Recipe Finder - 菜谱助手\r
\r
触发规则\r
\r 关键词:\r
- 菜谱、食谱、怎么做菜\r
- 今天吃什么、推荐菜\r
- 食材、烹饪方法\r \r 场景:\r
- 用户不知道吃什么\r
- 用户有食材不知道怎么做\r
- 用户想学新菜\r \r
功能描述\r
\r
核心功能\r
\r
- 食材推荐菜谱\r
- 输入现有食材\r
- 推荐可做的菜\r
- 显示难度和时间\r \r
- 随机推荐\r
- 今日推荐菜\r
- 根据口味推荐\r
- 根据季节推荐\r \r
- 菜谱详情\r
- 食材清单\r
- 详细步骤\r
- 烹饪技巧\r \r
- 营养分析\r
- 卡路里计算\r
- 营养成分\r
- 健康建议\r \r
权限需求\r
\r
- 文件读写(收藏菜谱)\r
- 网络访问(菜谱 API)\r \r
示例对话\r
\r
用户:今天吃什么\r
助手:🍳 今日推荐菜谱:\r
\r
1️⃣ 宫保鸡丁 ⭐⭐⭐\r
难度:中级 | 时间:20 分钟\r
食材:鸡胸肉、花生、干辣椒\r
口味:麻辣\r
\r
2️⃣ 番茄炒蛋 ⭐\r
难度:简单 | 时间:10 分钟\r
食材:番茄、鸡蛋\r
口味:酸甜\r
\r
3️⃣ 红烧肉 ⭐⭐⭐⭐\r
难度:高级 | 时间:60 分钟\r
食材:五花肉、冰糖、料酒\r
口味:甜咸\r
\r
想吃哪个?我告诉你详细做法!\r
\r
用户:我有土豆和牛肉\r
助手:🥔 用土豆和牛肉可以做:\r
\r
1️⃣ 土豆烧牛肉\r
难度:中级 | 时间:40 分钟\r
\r
2️⃣ 土豆牛肉汤\r
难度:简单 | 时间:30 分钟\r
\r
3️⃣ 咖喱土豆牛肉\r
难度:中级 | 时间:35 分钟\r
\r
想学哪个?\r
\r
用户:怎么做番茄炒蛋\r
助手:🍅 **番茄炒蛋**\r
\r
📝 食材:\r
- 番茄 2 个\r
- 鸡蛋 3 个\r
- 葱花 适量\r
- 盐、糖 少许\r
\r
👨🍳 步骤:\r
1. 番茄切块,鸡蛋打散\r
2. 热锅凉油,炒鸡蛋盛出\r
3. 炒番茄出汁\r
4. 加入鸡蛋翻炒\r
5. 加盐、糖调味\r
6. 撒葱花出锅\r
\r
💡 技巧:\r
- 鸡蛋加少许水更嫩\r
- 番茄去皮口感更好\r
```\r
\r
## 数据存储\r
\r
```json\r
// ~/.openclaw/workspace/recipe-finder/favorites.json\r
{\r
"favorites": [\r
{\r
"name": "番茄炒蛋",\r
"added_date": "2026-03-16",\r
"cook_count": 5\r
}\r
]\r
}\r
```\r
\r
## 待办事项\r
\r
- [ ] 菜谱数据库\r
- [ ] 食材匹配算法\r
- [ ] 详细步骤\r
- [ ] 收藏功能\r
- [ ] 营养计算\r
\r
---\r
\r
**版本:** 1.0.0\r
**创建日期:** 2026-03-16\r
**作者:** 小鬼 👻\r
安全使用建议
This skill is internally consistent with its stated purpose: it recommends recipes and stores favorites/shopping lists locally and does not request credentials or network access. Before installing: 1) Inspect SKILL.md and recipe_finder.py for any unexpected hidden characters or strings (the static scan flagged unicode-control-chars). Those are often benign but can be used to manipulate prompt parsing; remove or correct them if present. 2) Confirm where data will be stored — SKILL.md references ~/.openclaw/workspace/recipe-finder/, while the code writes files next to the script; decide which location you prefer and verify the paths after installation. 3) Run the skill in a sandbox or with limited permissions if you are cautious; check the created favorites.json and shopping_list.json contents. 4) If you expect remote recipe fetching later, require explicit network permission and review any added network code at that time. If you are comfortable after these checks, the skill's footprint appears reasonable.
功能分析
Type: OpenClaw Skill
Name: cp3d1455926-svg-recipe-finder
Version: 2.0.0
The skill bundle is a standard recipe recommendation tool that operates entirely locally. The Python implementation (recipe_finder.py) manages recipes, favorites, and shopping lists using local JSON files and hardcoded data, without any network requests, shell command execution, or access to sensitive system information. The instructions in SKILL.md and documentation in README.md are consistent with the code's functionality and contain no evidence of prompt injection or malicious intent.
能力评估
Purpose & Capability
Name/description (recipe recommendations, nutrition, favorites) matches the code and instructions. The code implements local recipe DB, ingredient matching, favorites and shopping-list JSON files and nutrition summaries — all reasonable for this purpose. Minor inconsistency: SKILL.md shows a storage path under ~/.openclaw/workspace/recipe-finder/, while recipe_finder.py writes favorites/shopping_list.json next to the code (DATA_DIR = Path(__file__).parent). This is a functional mismatch but not a permissions/credential issue.
Instruction Scope
SKILL.md confines operations to recommending recipes and storing favorites/shopping lists. It declares file read/write for favorites and does not enable network access. The instructions reference a specific user workspace path (~/.openclaw/workspace/recipe-finder/...), but the bundled Python uses its own directory for data files — review/confirm which path will be used at runtime. No instructions ask the agent to read unrelated system files or exfiltrate data.
Install Mechanism
No install spec; this is instruction+code only. There are no external downloads, package installs, or unknown URLs. Risk from install mechanism is low.
Credentials
The skill requests no environment variables or external credentials. The only access is local file read/write for favorites and shopping_list, which is proportionate to the stated features.
Persistence & Privilege
always is false and the skill does not declare any elevated or system-wide persistence. It appears to only create/read JSON files in its data directory (or the workspace path referenced in SKILL.md). It does not modify other skills or global agent settings.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install cp3d1455926-svg-recipe-finder - 安装完成后,直接呼叫该 Skill 的名称或使用
/cp3d1455926-svg-recipe-finder触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.0.0
v2.0 - 12 道菜谱 + 营养分析
元数据
常见问题
Recipe Finder 是什么?
推荐适合现有食材的菜谱,提供详细做法、烹饪技巧及营养信息,支持随机和个性化推荐。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 135 次。
如何安装 Recipe Finder?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cp3d1455926-svg-recipe-finder」即可一键安装,无需额外配置。
Recipe Finder 是免费的吗?
是的,Recipe Finder 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Recipe Finder 支持哪些平台?
Recipe Finder 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Recipe Finder?
由 cp3d1455926-svg(@cp3d1455926-svg)开发并维护,当前版本 v2.0.0。
推荐 Skills