fund-summarizer
GitHub基于Morningstar数据源生成基金或ETF的简明摘要与报告。涵盖核心资料、评级、业绩风险及持仓等维度，支持Markdown及HTML格式输出，严格遵循数据规范且不提供投资建议。
Trigger Scenarios
Install
npx skills add openai/plugins --skill fund-summarizer -g -y
SKILL.md
Frontmatter
{
"name": "fund-summarizer",
"description": "Use when summarizing a fund or ETF with Morningstar ratings, returns, risk, holdings, fees, and caveats."
}
Fund Summarizer
Create a concise fund summary or report using the connected Morningstar app as the data source.
Guardrails
- Use only data returned by the Morningstar app in the current session.
- Do not infer missing values, add outside research, predict performance, or give investment advice.
- Show unavailable values as
N/Aand distinguish missing data from tool failure. - Supported investment types are ETFs, open-end funds, and closed-end funds. If the user asks for an equity or unsupported security, explain that this skill is fund-focused and ask for a supported fund.
- Preserve Morningstar terminology for ratings, categories, benchmarks, and analyst research.
Workflow
For broad summaries, detailed reports, or any HTML report, read references/full-workflow.md before retrieving data. It preserves Morningstar's partner-authored datapoint map, missing-data rules, structured report inputs, and renderer contract.
- Resolve the fund from ticker, name, or Morningstar identifier. Ask only if the match is ambiguous.
- Retrieve core profile data: name, ticker, category, investment type, inception date, benchmark, active/passive status, assets, fees, yield, manager tenure, and fund status.
- Retrieve ratings and research context: medalist rating, star rating, pillar ratings when available, portfolio risk score, analyst summary, and relevant disclosures.
- Retrieve performance and risk context: trailing returns, calendar-year returns, category ranks, standard deviation, Sharpe ratio, upside/downside capture, and flows when available.
- Retrieve portfolio context: asset allocation, sector/geography exposure, market-cap style, top holdings, turnover, and sustainability data when available.
- Build the smallest useful deliverable for the user request. Use Markdown by default; create self-contained HTML only if the user explicitly asks for an HTML report.
HTML Report Support
When creating an HTML report, use scripts/render.py. It reads assets/template.html, assets/icons/, and the Morningstar logo asset, with visual guidance in references/design_guide.md.
Report rendering always creates the HTML report and attempts a sibling PDF copy when the local environment supports it. If PDF export is unavailable, deliver the HTML report. For command-line PDF export from an existing HTML report, run scripts/export_report.py against the rendered report HTML.
Output
Use this order:
- Morningstar disclosure: AI-generated analysis using Morningstar data; informational only, not investment advice.
- Fund snapshot.
- Ratings and analyst context.
- Performance and category-rank context.
- Risk and portfolio context.
- Fees, flows, and operational details.
- Data-availability notes and caveats.
Keep the summary factual and skimmable. For broad requests, include the main tables and a short neutral narrative. For narrow questions, answer only the requested metric or section.
Version History
- 11c74d6 Current 2026-07-19 09:40
