← 返回 Skills 市场
lkmsteven

CANSLIM-Top100-US

作者 lkmsteven · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
251
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install canslim-top100-us
功能描述
Analyze the top 100 S&P 500 companies by market capitalization using CANSLIM-style signals and return a ranked shortlist in Markdown.
使用说明 (SKILL.md)

\r \r

CANSLIM S&P 500 Analyzer\r

\r Analyze the top 100 S&P 500 stocks by market capitalization using the local analyzer.py script, then summarize the strongest candidates for the user.\r \r

When to use\r

Use this skill when the user asks to:\r

  • Run a CANSLIM analysis on large-cap U.S. stocks.\r
  • Screen S&P 500 leaders by growth, momentum, and institutional-quality signals.\r
  • Generate a ranked shortlist of CANSLIM-style candidates.\r \r

Inputs\r

Expected local files:\r

  • Scripts/analyzer.py\r
  • Scripts/requirements.txt (if dependencies are not already installed)\r \r Expected script output:\r
  • canslim_results.json (in root directory)\r
  • Optional: canslim_results.csv\r \r

Execution rules\r

Follow this checklist exactly:\r

  1. Confirm that Scripts/analyzer.py exists.\r
  2. If dependencies are missing, install them from Scripts/requirements.txt.\r
  3. Change to the Scripts directory or run python Scripts/analyzer.py from root.\r
  4. Wait for the script to finish successfully.\r
  5. Read canslim_results.json.\r
  6. Rank stocks by CANSLIM score from highest to lowest.\r
  7. Present the best candidates in a Markdown table.\r
  8. Explain which CANSLIM letters each top stock passed or failed.\r
  9. If no stock is a strong match, show the top 3 closest candidates instead.\r \r

Analysis guidance\r

Interpret the script output using these principles:\r

  • C: strong recent quarterly earnings growth.\r
  • A: strong annual growth trend.\r
  • N: price near new highs or supported by a fresh catalyst.\r
  • S: favorable supply-demand signal such as strong volume.\r
  • L: market leadership versus weaker peers.\r
  • I: meaningful institutional sponsorship.\r
  • M: favorable trend or market direction signal.\r \r Do not invent missing metrics. If any field is unavailable, say that the data is unavailable and continue with the remaining signals.\r \r

Output format\r

Return:\r

  • A 1-2 sentence overall assessment.\r
  • A Markdown table with the top candidates.\r
  • A short bullet list explaining why the top names ranked highly.\r
  • A note listing any missing data, weak signals, or caveats.\r \r Use this table format:\r \r | Rank | Ticker | Company | Score | Passed | Failed | Notes |\r |---|---|---|---:|---|---|---|\r \r

Constraints\r

  • Use only the files generated by this skill run.\r
  • Do not claim the results are investment advice.\r
  • Do not fabricate company names, prices, or scores.\r
  • If the script fails, clearly report the failure and suggest checking dependencies or network access for market data.\r \r

Failure handling\r

If execution fails:\r

  • State which step failed.\r
  • Include the error message if available.\r
  • Recommend the smallest next action, such as installing dependencies or rerunning the script.\r
安全使用建议
This skill is internally consistent, but before installing or running it: (1) be aware it fetches data from the web (Wikipedia and Yahoo Finance via yfinance) so network access is required; (2) installing dependencies will pull packages from PyPI (inspect requirements.txt); (3) it writes canslim_results.json to the repository root/parent directory — run in a sandbox if you want to avoid clutter; (4) the results are not investment advice (SKILL.md already states this); (5) if you don't want the agent to run the script autonomously, disable model invocation for the skill or invoke it manually. If you want higher assurance, review the analyzer.py code locally and run it in an isolated environment before granting the agent permission to execute it.
功能分析
Type: OpenClaw Skill Name: canslim-top100-us Version: 1.0.0 The skill bundle is a legitimate financial analysis tool that performs CANSLIM-style screening on S&P 500 stocks. The Python script (analyzer.py) fetches public data from Wikipedia and Yahoo Finance (via yfinance), processes it locally, and outputs results to a JSON file as described in SKILL.md. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
Name/description (CANSLIM analysis of top S&P 500 names) matches the included script and SKILL.md. The script fetches tickers from Wikipedia, uses yfinance to obtain market data, computes CANSLIM signals, and outputs canslim_results.json — all expected for this purpose.
Instruction Scope
SKILL.md limits runtime actions to checking for Scripts/analyzer.py, installing requirements.txt if needed, running the script, reading canslim_results.json, and producing a Markdown summary. The instructions do not ask the agent to read unrelated files, environment variables, or exfiltrate data to unknown endpoints.
Install Mechanism
There is no automated install spec in registry metadata (instruction-only). A Scripts/requirements.txt lists standard Python packages (yfinance, pandas, lxml, tqdm, requests); SKILL.md instructs installing them if missing. This is reasonable, but installation is manual (or agent-run) and will pull packages from PyPI if performed.
Credentials
The skill requests no environment variables or credentials. The script makes network calls to Wikipedia and uses the yfinance library (which queries Yahoo Finance) — appropriate for market-data tasks and proportionate to the stated purpose.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or global agent settings, and only writes a local canslim_results.json (parent directory if run from Scripts). Autonomous invocation is enabled by default but not combined with other red flags here.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install canslim-top100-us
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /canslim-top100-us 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
CANSLIM-Top100-US v1.0.0 Changelog - Initial release of the CANSLIM-Top100-US skill. - Enables analysis of the top 100 S&P 500 companies using CANSLIM-style signals. - Runs a local Python script to rank and summarize the strongest candidates in a Markdown table. - Provides clear execution steps, output format, guidance on interpreting results, and detailed error handling.
元数据
Slug canslim-top100-us
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

CANSLIM-Top100-US 是什么?

Analyze the top 100 S&P 500 companies by market capitalization using CANSLIM-style signals and return a ranked shortlist in Markdown. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 251 次。

如何安装 CANSLIM-Top100-US?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install canslim-top100-us」即可一键安装,无需额外配置。

CANSLIM-Top100-US 是免费的吗?

是的,CANSLIM-Top100-US 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

CANSLIM-Top100-US 支持哪些平台?

CANSLIM-Top100-US 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 CANSLIM-Top100-US?

由 lkmsteven(@lkmsteven)开发并维护,当前版本 v1.0.0。

💬 留言讨论