Risk Scoring
Businessrisk-scoringRisk Scoring is an Agent Skill for business published in the microsoft/agent-framework repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Score how concentrated and risky a portfolio is on a 0-100 scale from its position weights. Use when the user asks how risky their portfolio is, whether it is too concentrated, or for a diversification check.
QUICK START
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.
Prompt to paste
Inspect the Agent Skill at https://github.com/microsoft/agent-framework/blob/HEAD/python/samples/02-agents/harness/build_your_own_claw/skills/risk-scoring/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/risk-scoring, 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.
Usage
When the user asks about portfolio risk or concentration:
- Read
references/risk-bands.mdto understand the score bands and what drives them. - Compute each holding's market value (shares × price) — use the
get_stock_pricetool for current prices if you do not already have them. - Run
scripts/risk_score.pywith one--position VALUEargument per holding, e.g.--position 18518 --position 17201 --position 16177. - Report the 0-100 score, the band it falls in, and the largest single-position weight, then suggest (in general terms) whether the portfolio looks well diversified or concentrated.
Remind the user this is a crude concentration measure, not a complete risk model, and not advice.