$ loading_
Frames retirement scenarios with conservative, base, and higher-volatility assumptions.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "retirement-scenario" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/solutions/portfolio-rebalancing/manual/skills/aibast_retirement-scenario_05/SKILL.md 2. Save it as ~/.claude/skills/aibast_retirement-scenario_05/SKILL.md 3. Reload skills and tell me it's ready
Please prepare scenario inputs for this synthetic retirement case: provide lower-return, base, and higher-volatility assumptions; do not invent a success probability; and separate observed evidence, calculated/heuristic results, and next steps.
Outputs three retirement scenario assumptions and clearly omits any success probability.
Using the provided synthetic operating snapshot, extract source-backed evidence for retirement scenarios and briefly note the basis and limitations of each assumption.
Produces concise, traceable scenario notes with source-backed evidence.
Please review this retirement scenario description and add the required disclaimer: state that it is not legal, regulatory, insurance, lending, tax, investment, or financial advice; and confirm that no external action occurred.
Produces compliant wording emphasizing no advice and no external action.
Use it when a team needs input for the synthetic pilot of the Portfolio Rebalancing Agent. It helps split retirement modeling into lower-return, base, and higher-volatility assumptions without inventing a success probability.
Use it when a user needs a reviewable retirement scenario note. It separates observed evidence, calculated or heuristic output, and proposed next steps for easier human review.
Use it for internal demos or documentation. It can add standard disclaimers and clearly state that no approval, communication, account change, payment, or transaction occurs.
The README describes a skill for framing retirement modeling inputs in a synthetic portfolio rebalancing pilot. It covers lower-return, base, and higher-volatility assumptions, and requires separating observed evidence, calculated or heuristic output, and next steps. The document also states that the result is not professional advice, no external action occurs, and authorized human review is required before any action.
Frames assumptions for lower-return, base, and higher-volatility retirement modeling without asserting success.
Persona: Retirement Planning Specialist
Prompt: Frame the retirement scenarios we need to model without inventing a success probability.
Expected synthetic evidence: 25 years, No success probability.
It is used to organize and phrase retirement scenario inputs for the synthetic Portfolio Rebalancing Agent pilot. It focuses on lower-return, base, and higher-volatility assumptions, and separates evidence, calculated output, and next steps.
The document requires identifying the exact fictional record or report scope and using the synthetic operating snapshot plus source-backed evidence. If inputs are insufficient, output only what is supported by the available information.
No. The document requires stating that the result is not legal, regulatory, insurance, lending, tax, investment, or financial advice, and that no approval, communication, filing, account change, payment, order, transaction, or external action occurred.
Generate sentiment splits and recent excerpts from synthetic records.
Prioritize churn reviews with transparent evidence and suggested next steps.
Extract a source-coded problem list from synthetic clinical evidence deterministically.
Helps assess request context and approval level from synthetic procurement records.
Extract and summarize medication inventories from packaged synthetic clinical evidence.
Summarize recovery conversion metrics with benchmarks, forecasts, and assumptions.
Generates illustrative tax impact estimates for professional review.
Generate portfolio rebalancing candidates for licensed advisor review.
Generates controlled implementation checklists for human review.
Analyze portfolio drift and identify allocation threshold breaches.
Prepare reviewable retention and service-recovery options for churn-related customer cases.
Compare synthetic cross-sell portfolio value scenarios for human-reviewed decision support.