A Stock Leader Identification 1.0.0 — 技能工具
v1.0.0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。
0· 2·1 当前·1 累计
by 安全扫描
OpenClaw
可疑
high confidenceThe skill is an instruction-only trading heuristic that generally matches its description and requests no credentials or installs, but there are packaging inconsistencies (meta ownerId mismatch) and the runtime instructions are high-level and vague about data sources — this combination warrants caution.
评估建议
This skill is essentially a short, human-readable checklist of heuristics for spotting sector leaders and does not request credentials or install code — that's good. However: (1) the package metadata appears inconsistent (ownerId/slug mismatch in _meta.json), which is a publishing red flag you may want to verify with the source; (2) the instructions are high-level and do not specify trusted data sources or APIs, so if you let your agent run this skill and it has network access it may call arbitr...详细分析 ▾
ℹ 用途与能力
The name/description and the SKILL.md align: both describe heuristics for identifying leading A-share (A股) short-term stocks. The skill requests no binaries, env vars, or installs, which is proportionate for an instruction-only heuristic. However, _meta.json contains a different ownerId/slug than the registry metadata provided, an unexplained packaging inconsistency that could indicate sloppy publishing or a copy-paste error.
ℹ 指令范围
The SKILL.md contains only high-level rules and a simple workflow (find first limit-up in a sector, check order size, turnover, themes). It does not instruct reading local files, environment variables, or external endpoints explicitly. That said, it is vague on how to obtain market data (which APIs/feeds to use) and therefore grants the agent broad discretion at runtime to query external services or fetch data — a potential operational risk if the agent is allowed network access or to use third-party API keys.
✓ 安装机制
No install spec and no code files — instruction-only. There is nothing written to disk by the skill itself and no third-party packages are pulled in by an installer.
✓ 凭证需求
The skill declares no required environment variables, no credentials, and no config paths. There is no apparent need for secrets or cloud credentials to perform what the instructions describe.
✓ 持久化与权限
always:false and user-invocable:true. The skill does not request permanent presence or elevated privileges. Autonomous model invocation is allowed by platform default but is not combined here with other high-risk factors.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/4/16
Initial release of leader-stock-identification skill for A股短线交易选股. - Enables rapid identification of true sector leaders ("真龙") instead of follower stocks. - Uses specific signals: first涨停 in the sector and substantial封单量. - Validates strength with连板, healthy换手率, and multi-theme or industry leadership. - Provides a practical workflow to find, assess, and act on sector leaders. - Offers clear criteria to filter out non-leader, "杂毛" stocks.
● 无害
安装命令 点击复制
官方npx clawhub@latest install a-stock-leader-identification-1-0-0
镜像加速npx clawhub@latest install a-stock-leader-identification-1-0-0 --registry https://cn.clawhub-mirror.com
技能文档
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%
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"
数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制
免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制