PJ选股智能评分12维模型
v1.0.012维股票智能分析评分模型。基于行业、头部玩家、市场环境、管理团队、市值规模、主营业务、收入、利润、分红、回购、机构持股、大股东增减持12个维度对股票进行综合评分。触发词：股票分析、选股评分、股票评分、智能选股。
⭐ 0· 67·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name, description, SKILL.md and the included Python script all describe and implement a local 12-dimension stock scoring model (interactive input, JSON input, markdown/JSON output). No unrelated credentials, binaries, or cloud services are requested, which is coherent with the stated purpose.
Instruction Scope
SKILL.md instructs running the included Python script with flags (--stock, --interactive, --file, --output). The instructions do not direct the agent to read unrelated system files, secret env vars, or to transmit data to external endpoints. All described operations are limited to local input/output and analyst judgment.
Install Mechanism
There is no install spec; this is essentially an instruction-only skill with an included Python script. That minimizes installation risk because nothing is downloaded or written automatically to the system during install.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The code shown performs scoring and interactive prompts and references public data sources only in documentation; there is no apparent need for secrets or external tokens.
Persistence & Privilege
The skill does not request always:true and will not be force-enabled; it has no install-time persistence mechanism declared. It does not attempt to modify other skills or system configuration in the visible content.
Assessment
This skill appears internally consistent with its stated purpose: it runs a local Python scoring script and uses interactive or JSON input to produce reports. Before installing or running: (1) open and review the remainder of scripts/stock_analyse.py (the provided content was truncated) to confirm there are no unexpected network calls, telemetry, or subprocess execution; (2) run the script in an isolated environment (e.g., a sandbox or VM) the first time; (3) do not feed sensitive credentials or private files to the tool (it doesn't need them); (4) treat outputs as informational only and not as financial advice; and (5) if you want automated upstream data fetching, require explicit review and justification because the skill currently documents data sources but does not declare network behavior or credentials.Like a lobster shell, security has layers — review code before you run it.
latestvk97d14sm4getka978bj02jn0fx83yp43
License
MIT-0
Free to use, modify, and redistribute. No attribution required.