What makes technical-indicator-signal-engine notable?

2.2K downloads. Trust evidence available

How should technical-indicator-signal-engine be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

agentCLAWHUBUnverified

technical-indicator-signal-engine

三维技术面信号引擎，融合趋势类 EMA(13/55)+ADX(14)、均值回归类布林带(20,±2)、量价类 OBV+量比，通过三维投票生成买入/卖出/观望信号。触发口令「分析 XXXX」（个股名称或代码）。纯 pandas 实现，适用于任意 OHLCV 行情。 Skill: technical-indicator-signal-engine Owner: night-king-lt Summary: 三维技术面信号引擎，融合趋势类 EMA(13/55)+ADX(14)、均值回归类布林带(20,±2)、量价类 OBV+量比，通过三维投票生成买入/卖出/观望信号。触发口令「分析 XXXX」（个股名称或代码）。纯 pandas 实现，适用于任意 OHLCV 行情。 Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-09T07:59:04.155Z | auto Initial release of the 三维技术面信号引擎 (technical-indicator-signal-engine): - Combines trend (EMA13/55 + ADX14), mean reversion (Bollinger Bands 2

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.2k

Updated

Oct 9, 2026

Version

0.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.2K downloadsadoption · observed Oct 9, 2026
Latest release: 0.1.0release · observed Aug 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17ed772bfys3mgf76g5qb3px98c55hd:technical-indicator-signal-engine

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-night-king-lt-technical-indicator-signal-engine/snapshot"

Documentation

CLAWHUB

9,304 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: technical-indicator-signal-engine
description: 三维技术面信号引擎，融合趋势类 EMA(13/55)+ADX(14)、均值回归类布林带(20,±2)、量价类 OBV+量比，通过三维投票生成买入/卖出/观望信号。触发口令「分析 XXXX」（个股名称或代码）。纯 pandas 实现，适用于任意 OHLCV 行情。
license: MIT
agent_created: true
version: 1.0.0
author: yanming
category: strategy
---

# 基础技术指标信号引擎（三维技术面分析）

## Overview

本技能提供一套纯 pandas 实现的三维技术面信号引擎，将三类经典西方技术分析指标合并为综合交易信号。适用于对个股、ETF、加密货币等任意 OHLCV 行情做量化择时判断。

触发口令：在对话中输入 **「分析 XXXX」**（XXXX 为个股名称或代码），即按本技能口径执行三维分析并输出买入 / 卖出 / 观望结论。

## When to Use

- 用户要求对某只标的做技术面买入 / 卖出信号判断时。
- 用户给出「分析 600519」「分析 贵州茅台」等带「分析」前缀的指令时。
- 需要在趋势、均值回归、量价三个维度交叉验证，而非依赖单一指标下结论时。

## 三维信号框架

| 维度 | 指标 | 作用 |
|------|------|------|
| 趋势 | EMA(13/55) + ADX(14) | 判定方向及趋势强度（ADX 阈值 25） |
| 均值回归 | 布林带(20, ±2) | 识别超买 / 超卖 |
| 量价 | OBV + 量比 | 确认量能配合 |

### 投票逻辑

- **买入（做多，信号 = 1）**：趋势看多（EMA 快线在慢线上方且 ADX 大于 25）或价格跌破布林下轨（超卖），且 OBV 上行，且未突破布林上轨。
- **卖出（做空，信号 = -1）**：趋势看空（EMA 快线在慢线下方且 ADX 大于 25）或价格突破布林上轨（超买），且 OBV 下行，且未跌破布林下轨。
- **观望（信号 = 0）**：三维度信号分裂、无法形成合力。

信号约定：`1` = 做多，`-1` = 做空，`0` = 观望。

## 引擎用法

核心实现见 `scripts/signal_engine.py`，提供 `SignalEngine` 类：

```python
import pandas as pd
from scripts.signal_engine import SignalEngine

# df 需含 open/high/low/close/volume 列，index 为 datetime
engine = SignalEngine()  # 默认参数：ema_fast=13, ema_slow=55, adx_period=14, adx_threshold=25, bb_window=20, bb_std=2
signal = engine.generate({"SH600519": df})["SH600519"]
```

指标计算口径（含布林带总体标准差 ddof=0、ADX Wilder 平滑链路的完整实现）见 `references/indicator_spec.md`。

## Dependencies

```bash
pip install pandas numpy requests
```

## 数据接入建议

- A 股 / 港股 / 美股行情：优先使用 `westock-data` 取结构化 K 线与财报（如 `westock-data kline <code> --period day --limit 250`）。
- 加密货币：引擎内置 OKX 示例（`SignalEngine` 演示用 `_fetch_okx`）。
- 关键陷阱：K 线列序需确认「收盘价为哪一列」，勿把最低价误当收盘价，否则信号建立在错误价格上。

README.md

# 基础技术指标信号引擎（三维技术面分析）

> 市场展示名：**基础技术指标信号引擎**
> 包名 / 技能 ID：`technical-indicator-signal-engine`
> 版本：1.0.0 ｜ 分类：策略 / 量化 / 技术分析 ｜ 许可证：MIT

## 一句话简介

融合趋势（EMA + ADX）、均值回归（布林带）、量价（OBV + 量比）三个维度的纯 pandas 信号引擎，通过三维投票输出买入 / 卖出 / 观望结论。

## 触发口令

```
分析 XXXX        （XXXX = 个股名称或代码，如：分析 贵州茅台 / 分析 600519）
```

## 三维框架

| 维度 | 指标 | 信号作用 |
|------|------|----------|
| 趋势 | EMA(13/55) + ADX(14，阈值 25) | 方向 + 趋势强度 |
| 均值回归 | 布林带(20, ±2) | 超买 / 超卖 |
| 量价 | OBV + 量比 | 量能配合确认 |

- 买入：趋势看多（或价格跌破布林下轨超卖）且 OBV 上行且未破上轨。
- 卖出：趋势看空（或价格突破布林上轨超买）且 OBV 下行且未破下轨。
- 观望：三维度信号分裂。

## 目录结构（上架包）

```
technical-indicator-signal-engine/
├── SKILL.md                    # 技能定义 + 触发口径
├── scripts/
│   └── signal_engine.py        # SignalEngine 三维信号引擎（纯 pandas）
├── references/
│   └── indicator_spec.md       # 指标计算口径详解（BOLL ddof=0 / ADX Wilder 链）
├── assets/
│   └── icon.svg                # 市场上架图标
├── README.md                   # 本文件（上架展示信息）
└── LICENSE.txt                 # MIT 许可证
```

## 安装方式

- **市场一键安装**：在 WorkBuddy 推荐市场搜索「基础技术指标信号引擎」→ 安装。
- **手动安装**：将本目录整体放到 `~/.workbuddy/skills/基础技术指标信号引擎/` 下（覆盖同名文件夹）。
- **手机学员**：使用随附的「基础技术指标信号引擎_手机安装版.md」便携包，在 WorkBuddy 中粘贴全文并发送「请按本文件安装技能」。

## 运行依赖

```
pandas numpy requests
```

## 风险提示

本技能仅为技术面量化分析工具，所有信号基于历史行情统计，不代表未来表现，不构成任何投资建议。市场有风险，投资需谨慎。任何投资决策应结合个人风险承受能力独立判断，必要时咨询持牌专业机构。

_meta.json

{
  "ownerId": "kn7dk418mcbh6gcmebgm420fv18c5d73",
  "slug": "technical-indicator-signal-engine",
  "version": "0.1.0",
  "publishedAt": 1786262344155
}

references/indicator_spec.md

# 指标计算口径详解

本文件供引擎实现与复核参考，确保信号口径与主流行情软件（通达信）一致。

## 布林带（对齐通达信公式）

通达信源码编译逻辑：

```
N := 20;
MID := MA(C, N);
VART1 := POW((C - MID), 2);
VART2 := MA(VART1, N);
VART3 := SQRT(VART2);
UPPER := MID + 2 * VART3;
LOWER := MID - 2 * VART3;
```

要点：

- 中轨 `MID = MA(C, N)`（简单移动平均）。
- 标准差 `VART3` 采用 `N` 日窗口内的**总体标准差**，即偏差平方和的简单移动平均再开方（`ddof=0`），与源码 `MA((C-MID)^2, N)` 一致；**不要**使用 pandas 默认的 `rolling().std()`（样本标准差，`ddof=1`），否则带宽会被系统性低估。
- 源码另以 `BOLL/UB/LB := REF(MID/UPPER/LOWER, 1)` 仅用于画线显示，信号判定使用当根 K 线的带宽（标准均值回归口径），故信号计算不套用 REF 移位。

## ADX（Wilder EWM 全链路）

链路：`+DM / -DM → TR → Wilder 平滑 → +DI / -DI → DX → ADX`。

- `+DM = max(high - prev_high, 0)` 当 `up_move > down_move`，否则 0；`-DM` 同理。
- `TR = max(high-low, |high-prev_close|, |low-prev_close|)`。
- 平滑采用 Wilder EWM：`ewm(alpha = 1/period, min_periods = period)`（**不是**普通滚动均值）。
- `+DI = 100 * smoothed_+DM / smoothed_TR`；`-DI` 同理。
- `DX = 100 * |+DI - -DI| / (+DI + -DI)`；`ADX = DX.ewm(alpha = 1/period)` 平滑。
- 趋势强度阈值默认 `25`：ADX 大于 25 视为有效趋势，小于则视为震荡。

## OBV（能量潮）

```
sign = sign(close.diff())
OBV = (volume * sign).cumsum()
```

量价维度以 `OBV` 与其 `N` 日移动平均比较：OBV 在均线上方视为量能配合看多，下方视为看空。

## 量比

量比由行情数据直接提供（如 westock-data 的 `quote` 字段），用于确认当日成交相对近 5 日均量的放大 / 萎缩程度，与 OBV 共同构成量价维度。

## 参数表

| 参数 | 默认 | 说明 |
|------|------|------|
| ema_fast | 13 | 快线 EMA 周期 |
| ema_slow | 55 | 慢线 EMA 周期 |
| adx_period | 14 | ADX 计算周期 |
| adx_threshold | 25.0 | ADX 趋势强度阈值 |
| bb_window | 20 | 布林带窗口 |
| bb_std | 2.0 | 布林带标准差倍数 |
| vol_ma_period | 20 | 成交量均线周期 |
| obv_ma_period | 20 | OBV 均线周期 |

skill-card.md

## Description:

三维技术面信号引擎，融合趋势类 EMA(13/55)+ADX(14)、均值回归类布林带(20,±2)、量价类 OBV+量比，通过三维投票生成买入/卖出/观望信号。

This skill is ready for commercial/non-commercial use.

## Publisher:

[night-king-lt](https://clawhub.ai/user/night-king-lt)

### License/Terms of Use:

MIT

## Use Case:

External users and developers use this skill to analyze OHLCV market data for equities, ETFs, and crypto assets, producing buy, sell, or hold technical-analysis signals. It is an analytical aid and should not be treated as investment advice.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Trading signals can be mistaken for investment advice or used directly for real trades.

Mitigation: Treat outputs as informational technical analysis and require independent review before any trading decision.

Risk: Dependency installation can affect the agent environment.

Mitigation: Install pandas, numpy, and requests in an isolated virtual environment.

Risk: Running scripts/signal_engine.py directly contacts OKX for BTC, ETH, and SOL candle data.

Mitigation: Run the demo only where outbound market-data requests are expected and acceptable.

## Reference(s):

- [Indicator Calculation Specification](references/indicator_spec.md)
- [Server-resolved GitHub provenance](https://github.com/night-king-lt/technical-indicator-signal-engine)
- [ClawHub skill page](https://clawhub.ai/night-king-lt/skills/technical-indicator-signal-engine)
- [Publisher profile](https://clawhub.ai/user/night-king-lt)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with Python code examples and numeric signal values]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Signals use 1 for buy, -1 for sell, and 0 for hold.]

## Skill Version(s):

0.1.0 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/night-king-lt/skills/technical-indicator-signal-engine",
      "sourceUrl": "https://clawhub.ai/night-king-lt/skills/technical-indicator-signal-engine",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:21:31.969Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-night-king-lt-technical-indicator-signal-engine/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-night-king-lt-technical-indicator-signal-engine/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:21:31.969Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "2.2K downloads",
      "href": "https://clawhub.ai/night-king-lt/technical-indicator-signal-engine",
      "sourceUrl": "https://clawhub.ai/night-king-lt/technical-indicator-signal-engine",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:21:31.969Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "0.1.0",
      "href": "https://clawhub.ai/night-king-lt/technical-indicator-signal-engine",
      "sourceUrl": "https://clawhub.ai/night-king-lt/technical-indicator-signal-engine",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-09T07:59:04.155Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-night-king-lt-technical-indicator-signal-engine/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-night-king-lt-technical-indicator-signal-engine/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 0.1.0",
      "description": "Initial release of the 三维技术面信号引擎 (technical-indicator-signal-engine): - Combines trend (EMA13/55 + ADX14), mean reversion (Bollinger Bands 20,±2), and volume-price (OBV + volume ratio) indicators for comprehensive buy/sell/hold signals. - Uses a three-factor voting system to avoid reliance on a single indicator. - Provides a simple trigger phrase: “分析 XXXX” for signal analysis on any OHLCV data. - Fully implemented with pandas, compatible with any equity, ETF, or crypto asset. - Outputs clear signals: 1 (buy), -1 (sell), or 0 (hold), based on confluence across three dimensions.",
      "href": "https://clawhub.ai/night-king-lt/technical-indicator-signal-engine",
      "sourceUrl": "https://clawhub.ai/night-king-lt/technical-indicator-signal-engine",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-09T07:59:04.155Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

README.md

_meta.json

references/indicator_spec.md

skill-card.md

Related agents

activepieces

cherry-studio

AionUi

CopilotKit

Machine-readable data