← 返回 Skills 市场

A股短线交易决策 A Share Short Term Decision

Name: A股短线交易决策 A Share Short Term Decision
Author: kenera

作者 kenera · GitHub ↗ · v1.2.0

cross-platform ✓ 安全检测通过

1380

总下载

当前安装

版本数

在 OpenClaw 中安装

/install a-share-short-decision

功能描述

A-share short-term trading decision skill for 1-5 day horizon. Use when you need market sentiment, sector rotation, strong stock scanning, capital flow confi...

使用说明 (SKILL.md)

A-Share Short-Term Decision Skill

Implement in sequence:

Run short_term_signal_engine(analysis_date) for target date.
If needed, persist prediction with run_prediction_for_date(analysis_date).
Compare prediction vs actual market with compare_prediction_with_market(prediction_date, actual_date).
Output report with generate_daily_report(analysis_date).

Tool Contracts

`short_term_signal_engine(analysis_date=None)`

analysis_date: YYYY-MM-DD or YYYYMMDD
Returns weighted short-term score and recommendation status.
Always returns friendly no_recommendation_message when no tradable candidate exists.

`run_prediction_for_date(analysis_date)`

Runs signal engine for the specified date.
Appends decision snapshot into data/decision_log.jsonl.

`compare_prediction_with_market(prediction_date, actual_date=None)`

Loads prediction from log (or auto-generates if missing).
Compares predicted candidates against real market closes on actual_date.
Returns per-stock return and summary statistics.

No-Recommendation Behavior

Required behavior:

Never return empty output.
If candidates is empty or signal is NO_TRADE, explicitly say: 当前暂无可执行短线买入标的.
Include reason and next action.

Runtime

python3 main.py short_term_signal_engine --date 2026-02-12
python3 main.py run_prediction_for_date --date 2026-02-12
python3 main.py compare_prediction_with_market --prediction-date 2026-02-12 --actual-date 2026-02-13
python3 main.py generate_daily_report --date 2026-02-12

Subskills Workflow

For recurring optimize-then-recommend flow, run:

python3 subskills/config-optimization/optimize_from_aggressive.py --analysis-period "2026-02-01 to 2026-02-12"
python3 subskills/daily-recommendation/generate_daily_recommendation.py --date 2026-02-14

All generated artifacts are stored under data/.

安全使用建议

This skill appears to be what it claims: a short‑term A‑share decision tool that fetches market data (via akshare), scores candidates, writes logs and JSON artifacts into a local data/ folder, and can optionally update config.json via the optimization subskill. Before installing or running: 1) Be prepared to install akshare and pandas (not declared in registry metadata—install manually or review dependency policy). 2) Inspect config.json and data/ to ensure you are comfortable with files being written/overwritten (the optimizer can overwrite config.json when run with --apply-to-config). 3) Expect the skill to make outbound HTTP requests through the akshare library to fetch market data (normal for this purpose). 4) Run it in a sandbox or non‑privileged environment if you want to limit effects on your filesystem. 5) If you want stricter control, avoid running the optimizer's --apply-to-config flag and review produced artifacts before applying them.

功能分析

Type: OpenClaw Skill Name: a-share-short-decision Version: 1.2.0 The skill is designed for A-share short-term trading decisions, leveraging `akshare` and `pandas` to fetch and process financial market data. All code and documentation (including AI agent prompts) are aligned with the stated purpose, focusing on market sentiment, sector rotation, stock scanning, and capital flow analysis. File operations are confined to local configuration files (`config.json`) and a dedicated `data/` directory for logs and generated reports. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts against the agent, or obfuscation. The `requirements.md` and `scheduler.yaml` files specify legitimate dependencies and scheduling for the OpenClaw platform, respectively. The skill appears to be a well-defined and legitimate financial analysis tool.

能力评估

✓ Purpose & Capability

Name/description (short‑term A‑share decisioning) matches what the code does: market sentiment, sector rotation, stock scanning, capital‑flow analysis, scoring, logging and report generation. The use of akshare/pandas is expected for this purpose.

✓ Instruction Scope

SKILL.md instructs running the included Python CLI (main.py) and subskill scripts; those commands map directly to functions in the code. The skill reads/writes local files under data/, reads config.json, and contacts market data via akshare — all within the stated scope. It enforces a required no‑recommendation message when no candidates exist.

ℹ Install Mechanism

No install spec is declared in the registry; the README suggests 'pip install akshare pandas'. That mismatch (no declared dependencies in metadata) is a usability/packaging omission but not malicious. There are no downloads from arbitrary URLs or extract/install steps in the skill bundle itself.

✓ Credentials

The skill does not declare or require any sensitive environment variables or credentials. It optionally reads SHORT_DECISION_DEBUG and SHORT_DECISION_FALLBACK_ENABLED for debug/fallback behavior — reasonable for development/runtime toggles and documented in code. No secret exfiltration patterns observed.

ℹ Persistence & Privilege

always:false (no forced persistent inclusion). The skill writes logs and artifacts under data/ (decision_log.jsonl, today_recommendation_*.json, config optimization outputs). The config-optimization subskill has an explicit --apply-to-config option that can overwrite the repository's config.json; this is a legitimate feature but worth noting because it mutates config files if invoked.

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-share-short-decision
安装完成后，直接呼叫该 Skill 的名称或使用 /a-share-short-decision 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

v1.2.0

Version 1.2.0 - Introduced subskills for configuration optimization and daily recommendation workflows, with dedicated SKILL.md documentation and Python scripts. - Added support for recurring optimize–then–recommend flows, with instructions and commands included in SKILL.md. - Updated SKILL.md: clarified runtime commands (using python3), and documented integration of new subskills and data storage structure.

v1.1.1

Version 1.1.1 - Added real-data support, prediction logging, and next-day market comparison tools. - Main workflow now uses date-based `short_term_signal_engine` and logs decisions. - Introduced commands for prediction, logging, and comparing predictions vs actuals. - Improved no-recommendation handling with clear messaging and next steps. - Expanded reporting and evaluation capabilities for daily market review.

v1.1.0

- Updated runtime instructions in SKILL.md for tool usage. - Changed from "Always use the directory containing this SKILL.md as the skill root" to "Run tools via" with direct example commands.

v1.0.0

- Initial release of the A-share short-term trading decision skill for 1–5 day strategies. - Automates a structured decision workflow: sentiment analysis, sector rotation, strong stock scanning, capital flow study, signal scoring, risk control, and daily reporting. - Integrates strict risk management with position sizing and hard stops, and blocks new entries in poor sentiment markets. - Delivers actionable daily summaries for momentum traders in CN A-shares.

元数据

Slug a-share-short-decision

版本 1.2.0

许可证 —

累计安装 15

当前安装数 13

历史版本数 4

常见问题