P

股票筛选排序

Professionalv1.0.0
By user_8a5e88f1Updated 2026-10-01proactive-opportunity-pursuit@user_8a5e88f1/proactive-opportunity-pursuit
Finance

According to AlphaMoat, as of 2026-09, 股票筛选排序 has 1,926 downloads and 3 stars — ranked #4,475 of 5,078 AI skills overall, and #393 of 465 in Professional.

Installs
107
Downloads
1.9K
Stars
3
Overall Rank
#4,475
Top 89% overall · Top 85% in Professional
PlatformInstallsDownloadsStarsComments
SkillHub ↗1071.9K3—

Platforms count differently and update at different times.

What this skill does

The primary says to read or generate a candidate pool, screen and reorder candidates, explain higher-priority choices and strategy types, identify candidates not to prioritize, and suggest a further refinement. If data retrieval fails and the result is based only on existing data, state that limitation. Verify input dates and sources; do not present a screening result as a live market conclusion or guarantee.

Profile published 2026-10-29

What you can do with it

  • Sort a supplied candidate pool using the stated framework
  • Compare selection reasons and strategy tendencies
  • Identify lower-priority candidates and data limitations

When to use it

  • When the user asks to rank or narrow a supplied stock candidate pool
  • When the candidate data’s source and freshness can be checked
  • When selection reasons and a next refinement step should be explained

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Rank these candidates using the supplied data and explain each reason without inventing market data
Identify candidates that should not be prioritized and explain why
State the data date and source before presenting the limited screening result

Monthly Trend

Downloads1.9K
01.0K2.1K2026-03 · Downloads 832026-05 · Downloads 3652026-06 · Downloads 5342026-07 · Downloads 8322026-08 · Downloads 1.1K2026-09 · Downloads 1.9K26-0326-09
Stars3
0232026-03 · Stars -2026-05 · Stars -2026-06 · Stars 12026-07 · Stars 12026-08 · Stars 32026-09 · Stars 326-0326-09

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-091.9K—3
2026-081.1K+36.9%3
2026-07832+55.8%1
2026-06534+46.3%1
2026-05365—-
2026-0383—-

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

2.2 KB · SkillHub v1.0.0
---
name: proactive-opportunity-pursuit
description: 面向 OpenClaw 的主动机会推进 skill,用于把“想找机会”转成可执行候选股、优先级排序和缩圈建议。
---

# 主动机会推进

当用户表达以下需求时,使用这个 skill:

- “帮我找今天能交易的机会”
Show all (78 lines)
- “给我更主动一点,不要只列股票”
- “从候选里直接帮我缩圈”
- “我时间有限,先看哪几只”

## 设计目标

普通问答只会给出一个列表,这个 skill 要完成的是“从列表到决策推进”:

1. 先筛出候选股
2. 按优先级重新排序
3. 主动缩圈到 2 到 3 只
4. 提供每只股票对应的执行理由

## 默认工作流程

### 1. 先生成或读取候选池

Windows:

```powershell
d:/pythonfile/uderestimate/.venv/Scripts/python.exe d:/pythonfile/uderestimate/trade_candidate_pipeline.py
```

Linux:

```bash
./.venv/bin/python ./trade_candidate_pipeline.py
```

### 2. 主动做二次筛选

不要把 `a_share_agent_top5.csv` 原样抛给用户,而是主动回答:

- 哪 2 只的交易优先级最高
- 哪 1 只更偏突破型
- 哪 1 只更偏回踩低吸型
- 哪些股票虽然入围,但今天不应优先执行

### 3. 缺少用户偏好时,主动使用默认交易框架

如果用户没有提供持仓周期、风险偏好、资金量,也不要卡住。先按工作区默认短线框架给出初版,再提示:

- 如需更激进,可提高突破权重
- 如需更保守,可优先低估分与置信度更高的标的

### 4. 主动给出下一轮收敛建议

完成后应继续推进,而不是停在第一次结果:

- “是否要我把这 2 只进一步拆成盘中触发条件”
- “是否要我只保留适合尾盘买、次日卖的版本”
- “是否要我排除某些行业后再重跑”

## 输出要求

输出时至少包含:

- Top 2 或 Top 3 主盯标的
- 每只的核心入选理由
- 不建议优先执行的候选股及原因
- 建议的下一步收敛动作

## 约束

1. 不要把所有候选股都说成“都可以”。
2. 没有额外偏好时,也要给出一个可执行默认排序。
3. 如果数据失败,只能基于已有结果缩圈时,要明确说明。

Popular in Professional

Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.