financial-forecastlisted

# Financial Forecast A thin orchestration layer over the **planfi MCP** (https://ai.planfi.app/mcp, public, no auth). All math + the 150-year Shiller market dataset live server-side. This skill only gathers inputs and calls the tools — it does **not** compute anything locally. Read-only; it never changes the user's data. ## Step 0 — Make sure the planfi tools are connected This skill uses these tools (may be namespaced, e.g. `mcp__planfi__generate_financial_plan`): `generate_financial_plan`, `start_plan_intake`, `get_completed_plan`, `wait_for_completion`, `generate_financial_insights`, `generate_action_plan`, `generate_financial_commentary`, `run_backtesting`, `get_asset_allocation`, `get_savings_variations`, `solve_goal`, `compare_plans`, `check_model_completeness`, `explain_plan_state`, plus optional `analyze_*` deep-dives. Use whichever name your environment exposes (bare or `mcp__planfi__`-prefixed); below they are written bare. If they're NOT available, tell the user to connect the MCP, then continue: ``` claude mcp add --transport http planfi https://ai.planfi.app/mcp ``` (On claude.ai: add a custom connector pointing at https://ai.planfi.app/mcp — no auth.) ## Step 1 — Gather inputs (only two areas are strictly required) **REQUIRED — ask if not volunteered:** 1. **Each earner's age + annual salary** (household, 1–4 earners). 2. **Stock / investment portfolio**: `current_value` + `monthly_contribution`. **Forecast-driving inputs you may not have (retirement ag