Stock Report Generator
v1.0.0A股股票复盘报告自动生成工具。支持午间复盘和全天复盘，包含多维度评分体系、技术面深度分析、基本面跟踪、市场环境研判、操作策略等完整模块。
⭐ 3· 140·1 current·1 all-time
byMartin Yan@martinyan623
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (A股复盘报告生成器) match the included files: SKILL.md, scoring guide, README and a Python script that formats reports and computes scores. The code implements the scoring rules described in the docs. Minor metadata mismatch: registry metadata lists a different ownerId than _meta.json (registry owner id vs 'MartinYan623'), which is an inconsistency to check but does not change functionality.
Instruction Scope
SKILL.md and README describe generating midday/full-day reports and list external data sources (搜狐证券、东方财富、kimi_finance, 同花顺). The included script expects input data in a dict (no built-in network fetching). The docs note that real-time data requires integrating kimi_finance / other data sources; however the skill does not include code to fetch live data or request credentials. This is a scope/expectation note: the skill will produce reports only if the agent or user supplies market data or installs/links a data source.
Install Mechanism
No install spec; instruction-only + a local Python script. Nothing is downloaded or extracted. Dependencies are documented (matplotlib, kimi_finance, memory_search) but not automatically installed.
Credentials
The skill requires no environment variables, no credentials, and no config paths. The functionality (generating reports from provided data) does not justify requesting secrets. This is proportionate.
Persistence & Privilege
always:false and default agent invocation settings. The skill does not request permanent system presence or modify other skills. Autonomous invocation is allowed by platform default but there are no elevated privileges requested.
Assessment
This skill appears to do what it says: it formats and scores A‑share reports using supplied data and templates and includes a Python script to build the Markdown reports. Before installing or running: 1) note the metadata mismatch (registry owner id vs _meta.json owner) and confirm you trust the publisher; 2) the script does not fetch live market data — to generate real reports you must supply market data or integrate an external data provider (the README mentions kimi_finance, 东方财富, etc.); 3) install any Python deps (matplotlib, plus any data-source libraries you choose) and review the script locally before running; 4) no credentials are requested, so there is no obvious secret-exfiltration risk from this package. If you need automatic live data, expect to wire in a data provider (which may require API keys) — evaluate those provider integrations separately.Like a lobster shell, security has layers — review code before you run it.
latestvk97bz5rzxds9d5s6an5qvzx39d83d7ak
License
MIT-0
Free to use, modify, and redistribute. No attribution required.