About this skill

Problem

When checking or reviewing today's stock market data, the task often goes beyond pulling a few quotes. The goal is to turn the day's market summary into a reusable, date-bound report. Manual data stitching, screenshots, and ad hoc field notes easily introduce missing dates, inconsistent paths, or incomplete output fields.

How It Works

The skill delegates the work to a local Python pipeline instead of assembling the report entirely in the model. Key steps include:

Prerequisite: OpenClaw must have a Python 3 environment configured; run scripts/check_dependencies.py on first use to verify readiness.
Execution entrypoint: call scripts/main.py to generate the daily review data.
Output artifact: after the script finishes, an image report is written to /stock/reports/[YYYYMMDD(current date)]/, using the filename pattern 每日复盘_{current date}.png.
Result delivery: the skill sends the generated image to the user; if the user later requests fields step by step, the content is written into JSON incrementally.
Error boundary: when an error is reported, only the error message is returned and no other operations are performed.

Boundary And Notes

This skill is suited to daily stock review workflows and image-based report generation. It is not a substitute for real-time trading signals, in-depth equity research, or complex quantitative strategy work. If Python dependencies are missing, the target directory is not writable, date fields are not parsed correctly, or the requested fields go beyond the script's output contract, the environment and output assumptions should be checked first.

Screenshots

Use Cases

A research assistant reviewing today's market data calls the local script to generate and return the daily PNG report.
An editorial owner producing daily stock reviews relies on a fixed date-named image output in the reports directory.
A data engineer debugging the OpenClaw pipeline runs the dependency check and main script to isolate errors.
A quant assistant delivering review fields first retrieves the image, then writes requested fields to JSON step by step.

Best For

A research assistant following daily stock reviews who needs the daily PNG quickly and then stepwise fields.
An operations owner maintaining a stock daily-report workflow who needs date-bound output and a stable reports path.
An engineer debugging local Python skill pipelines who needs dependency checks, script execution, and error passthrough.
An editorial publisher preparing market content who needs the review image as a daily asset and later field additions.