A股短线交易决策 A Share Short Term Decision
PassAudited by ClawScan on May 1, 2026.
Overview
This appears to be a market-analysis skill that fetches A-share data and writes local reports, with notable but purpose-aligned risks around unpinned dependencies, scheduled jobs, and config changes.
Before installing, use a virtual environment, pin or review the Python dependencies, decide whether you want the recurring scheduler jobs enabled, and treat the generated stock outputs as research rather than automatic trading instructions.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing unpinned packages can pull unexpected future versions or transitive dependencies.
The README provides a user-directed install command for runtime dependencies, but the packages are unpinned and the registry metadata has no install spec. These dependencies are directly related to the stated AkShare market-data purpose.
pip install akshare pandas
Install in an isolated environment, verify package provenance, and preferably pin known-good versions of akshare and pandas.
If the scheduler is active, the skill may run recurring analysis jobs and write report artifacts without a fresh manual command each time.
The skill defines recurring weekday jobs for market scans and daily reports. This is persistent/autonomous scheduling, but it matches the stated daily market-analysis workflow.
cron: "30 14 * * 1-5" ... task: short_term_signal_engine ... cron: "20 15 * * 1-5" ... task: generate_daily_report
Enable the schedule only if you want recurring market scans; otherwise remove or disable the scheduler entries.
Running the apply option can change how later stock recommendations are scored and filtered.
The optional optimization workflow can change the runtime configuration that affects future recommendations. The behavior is disclosed and aligned with strategy tuning.
Optional: apply optimized full config to runtime config. ... optimize_from_aggressive.py --apply-to-config
Review and back up config.json before using --apply-to-config, and compare generated config artifacts under data/ before applying them.