Home / weaxs / stock-analysis-plugin · skills/stock-screener/SKILL.md · GitHub

stock-screener skillA

stock-screener is agent-read markdown (skill) from weaxs/stock-analysis-plugin: 全市场股票筛选:按市场、估值、成长、趋势或自定义条件生成候选列表并排序。已知个股的深度分析用 stock-analysis。.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# 全市场股票筛选

## 执行流程

### 第一步:确定筛选条件

优先从用户请求提取:
- **市场**:A股 / 港股 / 美股(默认A股)
- **筛选偏好**:价值型、成长型、趋势型、还是自定义条件
- **返回数量**:默认 Top 20

未指定的项直接使用默认值并在结果中说明;只有自定义条件彼此冲突时才请用户补充。

### 第二步:运行筛选

运行数据采集脚本进行 L1 量化筛选:

```bash
python3 tools/screener.py screen --market A --top 20
```

可选参数:`--market`(A/HK/US)、`--top`(返回数量)、`--config`(自定义 YAML 配置路径)、`--l2`(L2 量化增强开关,默认关闭)。

**何时开启 `--l2`**:需要对候选股做量化因子精排时开启。开启后逐股补算质量/成长/真实动量/波动率/资金流五类因子,结果更精细,但逐股抓取数据较慢,日常快速筛选保持关闭即可。开启 `--l2` 后候选按 `scores.final` 重新排序,config 里的 `sort_by`/`sort_order` 不生效;且 l2 模式下 `scores.momentum` 仍是 L1 参考值,不参与 final 综合分(final 用的是真实动量组)。

**`market_sentiment` 输出字段**:无论是否开 `--l2`,输出始终带 `market_sentiment`(市场情绪温度 0-100、level、multiplier 0.8-1.2 的 regime 调节器)。`multiplier < 1` 表示市场情绪偏弱,排序和推荐应更保守(收紧入选数量、降低激进度);`multiplier > 1` 表示情绪偏暖,可适度放宽。

### 第三步:L2 智能排序

对 L1 筛选出的候选股,基于返回的各项数据进行 LLM 智能排序。

注意区分两层"增强":`--l2` 是工具内的量化因子增强(在 L1 结果上补算因子,发生在排序之前);本步的 LLM 排序是 skill 流程的最后一环,在量化结果之上综合形态/量价/安全边际做最终排序。两者可叠加使用:先 `--l2` 拿精细因子,再做 LLM 排序。

排序考虑因素:
1. **技术形态质量**:趋势明确 > 震荡 > 趋势不明
2. **量价配合度**:放量上涨 > 缩量上涨 > 放量下跌
3. **指标共振**:多个指标同时看多/看空 > 指标分歧
4. **安全边际**:接近支撑 > 中间位置 > 接近压力

### 第四步:输出推荐列表

```
## 选股结果 — [市场] Top [N]

### 筛选条件
- 市场:...
- 过滤条件:...
…

Read the whole file at its exact version.

How to install

Latest version
mdr add weaxs/stock-analysis-plugin/stock-screener@git:20260922.a679af1
Exact content
mdr add weaxs/stock-analysis-plugin/stock-screener@sha256:f821085b66f28966

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6p57cjvfl7ml2gzo.svg)](https://markdownregistry.com/a/art_6p57cjvfl7ml2gzo)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260922.a679af1 latest2026-09-22 a679af1 3,496 BA view · diff
git:20260916.70e82282026-09-16 70e8228 3,489 BA view · diff
git:20260916.a1ca9262026-09-16 a1ca926 3,471 BA view · diff
git:20260904.421b62c2026-09-04 421b62c 3,312 BA view · diff
git:20260521.076544a2026-05-21 076544a 2,102 BA view · diff
git:20260514.9bdbe4d2026-05-14 9bdbe4d 2,059 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3496 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

weaxs/stock-analysis-plugin · 24 stars · license none · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6p57cjvfl7ml2gzo
GET https://markdownregistry.com/api/v1/resolve?ref=weaxs/stock-analysis-plugin/stock-screener
GET https://markdownregistry.com/api/v1/blob/f821085b66f289664a9e91d93c6f216c3d804709bb175eed0f2a3f138b14906a

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from weaxs/stock-analysis-plugin

AGENTS.md agents
weaxs/stock-analysis-plugin · AGENTS.md
git:20260922.a679af1 · audit A · 24 stars
CLAUDE.md claude
weaxs/stock-analysis-plugin · CLAUDE.md
git:20260807.a302e05 · audit B · 24 stars
bottom-volume skill
weaxs/stock-analysis-plugin · skills/bottom-volume/SKILL.md · 底部放量分析:判断长期下跌后的异常放量是否构成反转信号。用于低位放量;普通阻力突破用 volume-breakout。
git:20260916.70e8228 · audit A · 24 stars
box-oscillation skill
weaxs/stock-analysis-plugin · skills/box-oscillation/SKILL.md · 箱体震荡分析:识别横盘区间、支撑压力和突破失效条件。用于区间波段或高抛低吸问题。
git:20260916.70e8228 · audit A · 24 stars
bull-trend skill
weaxs/stock-analysis-plugin · skills/bull-trend/SKILL.md · 趋势追踪分析:识别中长期趋势、所处阶段和离场条件。用于多头排列、上升通道或持有趋势股。
git:20260916.70e8228 · audit A · 24 stars
chan-theory skill
weaxs/stock-analysis-plugin · skills/chan-theory/SKILL.md · 缠论分析:按笔、段、中枢和背驰识别缠论买卖点。仅在用户明确要求缠论口径时使用。
git:20260916.70e8228 · audit A · 24 stars
dragon-head skill
weaxs/stock-analysis-plugin · skills/dragon-head/SKILL.md · 龙头股分析:在已知板块中比较启动顺序、涨幅、回调和持续性。题材热度与参与节奏用 hot-theme。
git:20260919.9a70e54 · audit A · 24 stars
emotion-cycle skill
weaxs/stock-analysis-plugin · skills/emotion-cycle/SKILL.md · 市场情绪周期:用市场宽度、涨跌停、成交额和热度判断冰点、回暖、高潮或退潮。完整大盘复盘用 market-review。
git:20260919.9a70e54 · audit A · 24 stars
event-driven skill
weaxs/stock-analysis-plugin · skills/event-driven/SKILL.md · 事件驱动分析:评估公告、业绩、政策、订单或资本运作对个股的影响路径、定价程度和失效条件。
git:20260916.70e8228 · audit A · 24 stars
expectation-repricing skill
weaxs/stock-analysis-plugin · skills/expectation-repricing/SKILL.md · 预期重估分析:比较市场预期与可验证事实,判断正负预期差、定价程度和重估失效条件。
git:20260916.70e8228 · audit A · 24 stars
growth-quality skill
weaxs/stock-analysis-plugin · skills/growth-quality/SKILL.md · 成长质量分析:用多期收入、利润、现金流和盈利能力评估增长的真实性与可持续性。泛风险排查用 stock-analysis。
git:20260916.70e8228 · audit A · 24 stars
hot-theme skill
weaxs/stock-analysis-plugin · skills/hot-theme/SKILL.md · 热点题材分析:评估板块强度、扩散度、个股关联度和参与节奏。已知板块内的龙头比较用 dragon-head。
git:20260922.a679af1 · audit A · 24 stars

Every file in weaxs/stock-analysis-plugin

Other files named stock-screener

stock-screener skill
nicepkg/ai-workflow · workflows/stock-trader-workflow/.claude/skills/stock-screener/SKILL.md · Filter and screen stocks by financial metrics like P/E ratio, market cap, dividend yield, and growth rates. Analyze and…
git:20260118.be84779 · audit A · 283 stars

Browse by kind, by grade A, or by owner.