功能描述

Track baby sleep, feeding, diapers, and growth via the Huckleberry CLI. Use when the user asks about logging baby activities, starting/stopping sleep, bottle feeding, diaper changes, or growth measurements.

使用说明 (SKILL.md)

Huckleberry CLI

Name: Huckleberry
Author: jayhickey

Command-line interface for Huckleberry, a baby tracking app. Authenticate once and log sleep, feeds, diapers, and growth from your terminal.

Note: This is an unofficial tool and is not affiliated with Huckleberry.

Install

pip install huckleberry-cli

Quick start

huckleberry login
huckleberry children
huckleberry sleep start

Commands

Sleep

huckleberry sleep start      # Start sleep timer
huckleberry sleep stop       # Complete sleep (saves duration)
huckleberry sleep pause      # Pause sleep timer
huckleberry sleep resume     # Resume paused sleep
huckleberry sleep cancel     # Cancel without saving

Feeding

Breastfeeding:

huckleberry feed start --side=left    # Start nursing (left side)
huckleberry feed start --side=right   # Start nursing (right side)
huckleberry feed switch               # Switch sides mid-feed
huckleberry feed stop                 # Complete feeding

Bottle:

huckleberry feed bottle \x3Camount> [--type=TYPE] [--units=UNITS]

# Examples:
huckleberry feed bottle 120                           # 120ml formula (default)
huckleberry feed bottle 4 --units=oz                  # 4oz formula
huckleberry feed bottle 100 --type="Breast Milk"      # 100ml pumped milk

Types: Formula, Breast Milk, Mixed Units: ml (default), oz

Diapers

huckleberry diaper pee                              # Wet only
huckleberry diaper poo                              # Dirty only
huckleberry diaper both                             # Wet + dirty
huckleberry diaper dry                              # Dry check

# With details:
huckleberry diaper poo --color=yellow               # With color
huckleberry diaper poo --consistency=soft           # With consistency
huckleberry diaper both --color=brown --consistency=runny

Colors: yellow, green, brown, black, red Consistency: runny, soft, solid, hard

Growth

huckleberry growth --weight=7.5                     # Weight in kg
huckleberry growth --height=65                      # Height in cm
huckleberry growth --head=42                        # Head circumference in cm
huckleberry growth --weight=7.5 --height=65 --head=42  # All at once

# Imperial units:
huckleberry growth --weight=16.5 --units=imperial   # Weight in lbs

Info

huckleberry children           # List children
huckleberry --json children    # JSON output (--json before subcommand)
huckleberry status             # Current status

Multiple Children

huckleberry --child="Baby" sleep start   # Specify child by name
huckleberry -c "Baby" diaper pee

Authentication

Config stored at ~/.config/huckleberry/config.json.

huckleberry login                        # Interactive setup

Or use environment variables:

export HUCKLEBERRY_EMAIL="[email protected]"
export HUCKLEBERRY_PASSWORD="your-password"
export HUCKLEBERRY_TIMEZONE="America/Los_Angeles"

Requirements

Python 3.11+
huckleberry-api

Unit Conversions

1 oz ≈ 30 ml
1 lb ≈ 0.45 kg
1 inch ≈ 2.54 cm

安全使用建议

This skill appears to be a straightforward wrapper for an unofficial Huckleberry CLI, but exercise caution before installing or using it: - The SKILL.md shows the CLI stores credentials at ~/.config/huckleberry/config.json and accepts HUCKLEBERRY_EMAIL/HUCKLEBERRY_PASSWORD — treat these as sensitive. The manifest did NOT declare these env vars/config paths, which is an inconsistency. - The install step recommends pip install huckleberry-cli (and depends on py-huckleberry-api). Installing unvetted PyPI packages can execute arbitrary code. Before installing, review the package on PyPI and its source repository (check authorship, recent commits, and issues). - Prefer creating a disposable/test account rather than using your primary Huckleberry account credentials if you want to try it. Consider running the CLI in an isolated environment (container or VM). - Inspect ~/.config/huckleberry/config.json after login to see what is stored (avoid storing plaintext passwords if possible). If the package supports token-based auth or OAuth, prefer that. - If you need the skill for sensitive or production use, ask the author for a provenance link (official repo, PyPI package URL, or signed release) and validate the code before granting access. Given the mismatched metadata and the need for credentials plus the unvetted pip install, treat this skill as suspicious until you verify the package/source.

功能分析

Type: OpenClaw Skill Name: huckleberry Version: 1.0.1 The skill bundle is benign. It provides instructions for installing and using the `huckleberry-cli` to track baby activities. All commands and authentication methods described (CLI login, environment variables) are standard practices for interacting with a command-line tool and are directly aligned with the stated purpose. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts against the agent, or obfuscation.

能力评估

✓ Purpose & Capability

Name/description (baby tracking via a Huckleberry CLI) align with the SKILL.md: commands, feeds, diapers, growth, and multi-child support are all described and relevant. Declared requirements in the registry are minimal and consistent with a lightweight CLI integration.

ℹ Instruction Scope

SKILL.md instructs use of a CLI (huckleberry) and shows commands, an on-disk config path (~/.config/huckleberry/config.json), and environment variables (HUCKLEBERRY_EMAIL, HUCKLEBERRY_PASSWORD, HUCKLEBERRY_TIMEZONE). These are appropriate for a CLI that authenticates, but they mean the agent will be expected to read/write a local config file and potentially handle credentials — sensitive operations that are outside purely read-only info-gathering.

ℹ Install Mechanism

The skill is instruction-only (no install spec), which reduces direct platform risk. However SKILL.md recommends pip install huckleberry-cli and depends on py-huckleberry-api (GitHub link). Installing an unreviewed PyPI package runs arbitrary code; the manifest does not pin a trusted release or provide a vetted install source.

⚠ Credentials

Registry metadata declares no required env vars/config paths, but the instructions explicitly reference environment variables for email/password and a specific config file path. This mismatch (manifest says none, instructions require credentials/config) is an incoherence and increases risk because the skill expects secrets that the manifest did not advertise.

✓ Persistence & Privilege

always is false and there is no install script, no code files, and no request to change other skills or system-wide settings. Autonomous invocation is permitted (default) but not coupled with elevated privileges or persistent installation in the manifest.

版本历史

v1.0.1

Fix: --json placement, remove non-existent feed commands, update Python to 3.11+

v1.0.0

Initial release - CLI for Huckleberry baby tracking

元数据

Slug huckleberry

版本 1.0.1

许可证 —

累计安装 0

当前安装数 0

历史版本数 2

常见问题

Huckleberry 是什么？

Track baby sleep, feeding, diapers, and growth via the Huckleberry CLI. Use when the user asks about logging baby activities, starting/stopping sleep, bottle feeding, diaper changes, or growth measurements. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2002 次。

如何安装 Huckleberry？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install huckleberry」即可一键安装，无需额外配置。

Huckleberry 是免费的吗？

是的，Huckleberry 完全免费（开源免费），可自由下载、安装和使用。

Huckleberry 支持哪些平台？

Huckleberry 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 Huckleberry？

由 jayhickey（@jayhickey）开发并维护，当前版本 v1.0.1。

Huckleberry