← 返回 Skills 市场
bytesagain-lab

Macd

作者 bytesagain-lab · GitHub ↗ · v2.0.4 · MIT-0
cross-platform ⚠ suspicious
184
总下载
0
收藏
1
当前安装
5
版本数
在 OpenClaw 中安装
/install macd
功能描述
Calculate MACD from price data. Use when computing MACD/signal/histogram from a price series, spotting crossovers, reading momentum, or planning MACD-based e...
使用说明 (SKILL.md)

MACD — Moving Average Convergence Divergence

Calculate MACD from price data. Compute EMA, MACD line, signal line, and histogram from a CSV or inline price series.

Requirements

  • bash 4+
  • python3 (standard library only)

Commands

calculate

Calculate MACD from a comma-separated price series.

bash scripts/script.sh calculate "170.5,171.2,172.8,171.0,173.5,174.2,175.0,174.8,176.1,175.5,177.2,178.0,176.5,177.8,179.0,178.5,180.2,179.8,181.0,180.5,182.3,181.8,183.0,182.5,184.0,183.5"

calculate-file

Calculate MACD from a CSV file (one price per line or column).

bash scripts/script.sh calculate-file prices.csv

interpret

Interpret MACD, signal, and histogram values with trading signals.

bash scripts/script.sh interpret 1.25 0.80

crossover

Explain crossover patterns and trading rules.

bash scripts/script.sh crossover

histogram

MACD histogram analysis and momentum reading guide.

bash scripts/script.sh histogram

strategies

MACD trading strategies with entry/exit rules.

bash scripts/script.sh strategies

help

Show all commands.

bash scripts/script.sh help

Output

  • Computed MACD line, signal line, and histogram from real price data
  • EMA values at each step
  • Crossover and divergence signals
  • Trading strategy frameworks

Feedback

https://bytesagain.com/feedback/ Powered by BytesAgain | bytesagain.com

安全使用建议
This skill appears to do only local MACD calculations using your provided price series or a CSV file. Before running: ensure you have python3 and bash available; only pass files you intend the tool to read (it will open any path you give it); if you plan to run untrusted skills, consider running them in a sandbox. Also validate numeric results (indexing/alignment logic in the script is a bit intricate) before using outputs for live trading decisions — this review addresses coherence, not financial correctness.
功能分析
Type: OpenClaw Skill Name: macd Version: 2.0.4 The skill contains a command injection vulnerability in `scripts/script.sh` within the `cmd_calculate_file` function. The script interpolates the `$file` variable directly into an unquoted Python heredoc (`python3 << PYEOF`), which allows for arbitrary Python code execution if a maliciously crafted filename is provided. While the overall functionality appears to be a legitimate MACD calculator for trading, this lack of input sanitization in a shell script is a high-risk vulnerability.
能力评估
Purpose & Capability
Name/description match the included code and instructions. The skill only requires bash and python3 and exposes commands to calculate MACD from an inline series or a CSV file, interpret values, and display trading guidance — all consistent with a MACD calculator.
Instruction Scope
SKILL.md instructs the agent to run the provided scripts/script.sh commands. The script only reads user-supplied input (inline price list or a file path), computes values locally, and prints results. It does not reach out to external endpoints or read environment variables beyond those it sets to pass data to Python. Note: calculate-file reads whatever file path the user supplies (expected for this feature).
Install Mechanism
No install spec is provided and the skill is instruction/script-only. Nothing is downloaded or written to disk by an installer — the lowest-risk model for install behavior.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The script uses temporary environment variables to pass parameters to the embedded Python invocations only, which is proportional to its function.
Persistence & Privilege
always is false and the skill does not request persistent or elevated agent/system privileges. It does not modify other skills or alter system configuration.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install macd
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /macd 触发
  4. 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
v2.0.4
Real MACD calculation from price series, declared python3 requirement
v2.0.3
Clean build
v2.0.2
v2.0.2 clean .claude-plugin, trigger re-review
v2.0.1
v2.0.0 full rewrite: name+description+script
v1.0.0
publish v1.0.0
元数据
Slug macd
版本 2.0.4
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 5
常见问题

Macd 是什么?

Calculate MACD from price data. Use when computing MACD/signal/histogram from a price series, spotting crossovers, reading momentum, or planning MACD-based e... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 184 次。

如何安装 Macd?

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

Macd 是免费的吗?

是的,Macd 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Macd 支持哪些平台?

Macd 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 Macd?

由 bytesagain-lab(@bytesagain-lab)开发并维护,当前版本 v2.0.4。

💬 留言讨论