← 返回 Skills 市场

A股龙头股识别

Name: A股龙头股识别
Author: haohanyang92

作者 haohanyang92 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

737

总下载

当前安装

版本数

在 OpenClaw 中安装

/install a-stock-leader-identification

功能描述

快速找到板块内的"真龙"，识别龙头股。用于A股短线交易选股。

使用说明 (SKILL.md)

龙头股识别 Skill

核心能力

快速找到板块内的"真龙"，而不是跟风杂毛。

龙头股识别规则

启动信号

板块内第一个涨停
封单量占流通盘比例 > 1%

强度验证

连续2日涨停
换手率保持在 10%-20%
- 过高易出货
- 过低易炸板

辨识度

叠加多重题材（如"人工智能+算力"）
或为行业龙头公司

实战流程

板块爆发时，先找第一个涨停的标的
看封单强度和题材正宗度
锁定龙头后直接跟进
避免在跟风股上浪费时间

排除杂毛的特征

跟风涨停，非板块引领者
封单量小，易被砸
题材不正宗，纯炒概念
换手率异常（过高或过低）

触发场景

"谁是AI板块龙头"
"这个板块谁是真龙"
"能追吗还是买跟风股"

安全使用建议

This skill is a short, coherent set of trading heuristics (how to spot a sector leader) and contains no code or installers. Before relying on it: (1) ensure the agent or your environment provides accurate real-time market data (order-book/封单量, circulating shares, turnover rate) — the skill does not specify data sources or API keys; (2) do NOT grant any brokerage/trading credentials to an autonomous agent without careful controls — the skill implies 'follow' but does not implement safe execution; (3) remember these are simple heuristics and carry financial risk — test on historical data or in paper trading first; (4) if you plan to make the agent act on signals, require explicit user confirmation and limit any automated trading permissions.

功能分析

Type: OpenClaw Skill Name: a-stock-leader-identification Version: 1.0.0 The skill bundle contains purely instructional content for identifying leading stocks in the A-share market. It lacks any executable code, network requests, or malicious instructions, focusing entirely on trading strategies and criteria within SKILL.md.

能力评估

ℹ Purpose & Capability

The skill's name, description, and SKILL.md are aligned: it provides heuristics for identifying A-share sector leaders (涨停, 封单比, 换手率, 题材叠加). However, the rules implicitly require real-time market data (price, limit-up status, order book/封单量, circulating shares, turnover rate) which the skill does not declare how to obtain (no APIs, env vars, or data-source instructions). That omission is notable but not necessarily malicious.

ℹ Instruction Scope

SKILL.md contains only decision rules and a simple workflow (identify first limit-up, check 封单 and 题材, then follow). It does not instruct the agent to read local files, use credentials, or call external endpoints. It does, however, assume access to real-time market data and implicitly recommends trading actions ('直接跟进'), so users should be aware it is advisory and lacks concrete data-feed or execution safeguards.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files. No software is written to disk and no external packages are pulled in — low install risk.

ℹ Credentials

The skill requests no environment variables or credentials. In practice, implementing these heuristics requires market-data APIs and possibly brokerage/execution credentials; the absence of declared data-source requirements is a gap that a deploying agent or user must fill explicitly.

✓ Persistence & Privilege

No special persistence requested (always:false). The skill does not request elevated agent privileges or modify other skills' configurations.

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 a-stock-leader-identification
安装完成后，直接呼叫该 Skill 的名称或使用 /a-stock-leader-identification 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 release of leader-stock-identification skill. - Enables rapid identification of true leader stocks ("真龙") within a sector for A-share short-term trading. - Provides clear rules for leader stock signals, strength validation, and recognizability. - Includes a practical workflow for quickly locking onto sector leaders and avoiding follower stocks. - Lists exclusion criteria to help filter out non-leader stocks. - Supports scenarios like identifying sector leaders and deciding between chasing leaders or following others.

元数据

Slug a-stock-leader-identification

版本 1.0.0

许可证 MIT-0

累计安装 2

当前安装数 2

历史版本数 1

常见问题