Fund Comparison
Businessfund-comparisonFund Comparison is an Agent Skill for business published in the openai/plugins repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use when comparing 2 to 4 funds or ETFs with Morningstar ratings, returns, risk, and holdings data.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/openai/plugins/blob/HEAD/plugins/morningstar/skills/fund-comparison/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/fund-comparison, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Fund Comparison
Compare 2 to 4 funds side by side 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, backfill, rank suitability, 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. Exclude unsupported securities and explain why.
- If funds span broad asset classes, stop and ask for comparable funds instead of mixing incompatible metrics.
Workflow
Before running a real comparison, read references/full-workflow.md. It preserves Morningstar's partner-authored rules for fund resolution, exclusions, datapoints, broad-asset-class checks, holdings overlap, disclosures, and table formats.
- Resolve each ticker, name, or identifier to the intended Morningstar fund. Ask only if the result is ambiguous.
- Validate that 2 to 4 active supported funds remain after exclusions.
- Retrieve the smallest complete data set needed for the comparison: category, broad asset class, rating, medalist rating, expense ratio, assets, inception date, benchmark, return periods, category ranks, risk metrics, and top holdings when available.
- For equity funds, compare top holdings and show overlaps. For other asset classes, omit holdings overlap unless Morningstar returns meaningful holdings data.
- Present comparison tables with funds as columns and metrics as rows.
Output
Use this order:
- Disclosure banner.
- Resolution/exclusion notes, if any.
- Snapshot table.
- Performance table.
- Category-rank table with a note that lower percentile rank is better.
- Risk table.
- Holdings overlap for equity funds only.
- Brief caveats about category or data-availability differences.