恢恢量化 A股数据助手
v1.1.0A 股量化数据助手 — 日报快照、A股日历、融资融券、实时快讯，零配置无需安装任何依赖。
⭐ 3· 458·4 current·4 all-time
by@niceck
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description promise zero‑config A股 data and the scripts only fetch JSON from https://hhxg.top/static/data and format it; required files and code (fetch_snapshot.py, calendar.py, margin.py, news.py, _common.py) align with that purpose.
Instruction Scope
SKILL.md tells the agent to run the included Python scripts via Bash and provides a find-based snippet to locate the skill directory under ~/.claude/skills or ~/.openclaw/skills. The find invocation enumerates those local skill directories (to locate _common.py) but does not transmit their contents; this is expected for locating files but worth noting.
Install Mechanism
There is no automatic install spec (instruction-only skill). README shows optional git clone instructions from a GitHub repo and the code itself uses only the Python standard library; no downloads from obscure URLs or archive extraction are performed by the skill.
Credentials
The skill requires no environment variables or credentials. It uses a local cache directory (~/.cache/hhxg-market) to store fetched JSON, which is proportional to its functionality.
Persistence & Privilege
always:false and no modifications of other skills or agent-wide configs. The only persistent footprint is a cache under ~/.cache/hhxg-market and the skill files placed in the user's skills directory when installed via git (as documented).
Assessment
This skill fetches public JSON data from https://hhxg.top and runs only the included Python scripts (no external installers or secrets required). Things to consider before installing: 1) verify you trust hhxg.top (network requests go there and data is displayed to the agent); 2) the skill will create/read a cache under ~/.cache/hhxg-market — inspect cached files if you want to confirm the data; 3) the SKILL.md uses a local find command to locate its directory under ~/.claude/skills or ~/.openclaw/skills (it only reads filesystem paths, not transmitting them); 4) if you prefer, review the included scripts in this package (they are plain Python and only use urllib.request) before enabling the skill. Overall the package is internally consistent with its stated purpose.Like a lobster shell, security has layers — review code before you run it.
a-sharevk97bzskkhyfqxyrsm4mx5cbp4h82260kchina-stockvk97bzskkhyfqxyrsm4mx5cbp4h82260kfinancevk97bzskkhyfqxyrsm4mx5cbp4h82260klatestvk97bzskkhyfqxyrsm4mx5cbp4h82260kmarket-datavk97bzskkhyfqxyrsm4mx5cbp4h82260k
License
MIT-0
Free to use, modify, and redistribute. No attribution required.