← 返回 Skills 市场

Calorie Visualizer

Name: Calorie Visualizer
Author: vintlin

作者 Vint · GitHub ↗ · v1.0.0

darwinlinux ✓ 安全检测通过

717

总下载

当前安装

版本数

在 OpenClaw 中安装

/install calorie-visualizer

功能描述

Local calorie logging and visual reporting (auto-refreshes and returns report image after each log)

使用说明 (SKILL.md)

Calorie Visualizer

A local skill for meal logging and visual nutrition analysis.

Core Flow

User sends meal text/photo (upstream extracts calorie/protein values or calls food-db lookup).
add (or add-food) writes to calorie_data.db.
After write, visual_renderer.py generates a fresh report image.
CLI prints REPORT_IMAGE:\x3Cpath> so the chat layer can send the image.

Daily Goal Priority

config.daily_goal (manual override)
TDEE derived from USER.md
If user explicitly refuses profile data: logging only, no repeated prompting
Fallback default in renderer: 2000 kcal

CLI Commands

# Add a meal with explicit nutrition values
python3 scripts/calorie_visualizer.py add "food name" 500 25 [--photo /path/to/image.jpg]

# Add from local food database (local-first, online fallback optional)
python3 scripts/calorie_visualizer.py add-food "Subway chicken sandwich" --multiplier 1.0
python3 scripts/calorie_visualizer.py add-food "rice" --offline

# Daily summary
python3 scripts/calorie_visualizer.py summary

# Regenerate report image
python3 scripts/calorie_visualizer.py report

# Config
python3 scripts/calorie_visualizer.py config daily_goal 2000
python3 scripts/calorie_visualizer.py config user_refused_profile True

Dependencies

cd skills/calorie-visualizer
python3 -m pip install -r requirements.txt

Python libs: html2image, Pillow
Online fallback: optional USDA API (USDA_API_KEY)
Database: SQLite (built into Python)
Rendering: requires system Chromium/Chrome (called by html2image)

Storage

calorie_data.db (local SQLite)
No automatic external sync

安全使用建议

This appears to be a local-only calorie logging/reporting skill that stores data in calorie_data.db and writes daily_report.png inside the skill folder. Before installing: 1) Review whether you’re comfortable the tool will read USER.md in your repository (or any path you set via CALORIE_VIS_USER_MD) to compute TDEE, 2) only set USDA_API_KEY if you want online lookup (it is optional), 3) ensure you have a system Chromium/Chrome runtime for html2image and install the Python deps via requirements.txt, and 4) if you have privacy concerns, inspect the scripts (they are included) — there are no hidden network endpoints or obfuscated code. If you want extra assurance, run the scripts in an isolated environment (container or VM) first.

功能分析

Type: OpenClaw Skill Name: calorie-visualizer Version: 1.0.0 The OpenClaw skill 'calorie-visualizer' is classified as benign. All observed behaviors, including local SQLite database operations, reading user profile data from `USER.md` for TDEE calculation, optional external API calls to USDA for food data lookup (requiring `USDA_API_KEY`), and subprocess execution to generate visual reports using `html2image` (which requires a system browser), are clearly aligned with the skill's stated purpose. The `SKILL.md` and `README.md` are transparent about these functionalities and explicitly state 'No automatic external sync', indicating no intent for data exfiltration. There is no evidence of prompt injection, malicious execution, persistence mechanisms, or obfuscation.

能力评估

✓ Purpose & Capability

Name/description (local calorie logging + visual reports) match the code and files: CLI for adding entries, local SQLite DB, local food DB, renderer that produces a PNG. Declared runtime (python3, html2image + Pillow, local Chromium) is proportional to the reported functionality.

ℹ Instruction Scope

SKILL.md and the CLI instruct only local operations (write to calorie_data.db, regenerate local report, output REPORT_IMAGE:<path>). The code also reads USER.md (two directories up by default) to compute TDEE — this is documented in the README/SKILL.md, but it means the skill will attempt to read a workspace-level USER.md for profile data. That behavior is consistent with the feature but is a privacy-sensitive read that users should be aware of. The only external network call is an optional USDA API lookup when USDA_API_KEY is set.

✓ Install Mechanism

There is no opaque download/install script. The repo contains Python scripts and a requirements.txt; the install instructions are to pip install the listed dependencies (html2image, Pillow). This is a low-risk, standard install path. html2image uses a system Chromium runtime (documented).

ℹ Credentials

No required environment variables are declared. The code optionally reads USDA_API_KEY (for online food lookup) and CALORIE_VIS_USER_MD (an override path for the USER.md file). Both are reasonable for their purposes, but CALORIE_VIS_USER_MD lets a user-supplied path be read — only set it if you trust the skill. No unrelated secrets or credentials are requested.

✓ Persistence & Privilege

The skill does not request always:true and will not auto-enable itself. It writes local files inside the skill directory (calorie_data.db, daily_report.png, and updates data/food_database.json) which is expected for local persistence. 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 calorie-visualizer
安装完成后，直接呼叫该 Skill 的名称或使用 /calorie-visualizer 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

v1.0.0

Initial public release: local-first food DB, USDA online fallback, visual report auto-refresh.

元数据

Slug calorie-visualizer

版本 1.0.0

许可证 —

累计安装 2

当前安装数 2

历史版本数 1

常见问题