plugins/chronograph/skills/chronograph-cashflow-forecast/SKILL.md
Forecast private capital cashflows for existing portfolios using Chronograph MCP data and a Takahashi-Alexander style model. Use when Codex needs to analyze or forecast LP-level contributions, distributions, NAV, unfunded exposure, net cashflows, or Excel-style cashflow forecast outputs from existing Chronograph funds, commitments, groups, or portfolios.
npx skillsauth add openai/plugins chronograph-cashflow-forecastInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Requirements: The Existing Portfolio Forecast mode requires a connected Chronograph MCP server — these workflows are designed for permissioned Chronograph users to connect to their private investment data. The Future Commitment Pacing Overlay mode runs from user-provided assumptions and works without a connection.
Use the Chronograph MCP server as the source of truth for private capital commitment data, then forecast fund and portfolio cashflows with a Takahashi-Alexander style model. Prefer concise analysis in chat unless the user asks for a workbook, export, or model artifact.
Do not hard-code tool names — read the Chronograph MCP server's live tool descriptions to pick the appropriate tool for each data need.
references/model-methodology.md unless the user provides custom assumptions.Use one of these modes, or combine them when the user asks for a liquidity plan:
The skill needs three categories of data from the Chronograph MCP server: entity identifiers (fund and group IDs), fund metadata (name, type, vintage, reporting currency, geographic focus, GP, final reporting date), and net LP-level cashflow values (NAV, called, distributed, unfunded, commitment amount, net IRR, net MOIC, DPI, RVPI). Inspect the server's live tool descriptions and pick the appropriate tool for each category. Do not hard-code tool names.
Net vs gross — confirm with the user when ambiguous. This skill forecasts net LP cashflows. The Chronograph MCP server exposes separate tools for net LP-level performance and gross fund-level returns. User requests like "show me MOIC for these funds" are ambiguous — confirm net or gross before picking a tool. Gross returns (gross IRR, gross MOIC, cost, realized, unrealized) are not used in this forecast and live in a different tool.
Currency. Do not default currency to USD. For specific funds, resolve reporting currency from fund metadata before pulling cashflow values. If reporting currencies conflict across a multi-fund portfolio, ask the user.
Custom investment-level metrics. If a tool requires a discovery / help / schema-introspection call first (common pattern on the Chronograph MCP server), make that call to see which metric types are available, then query each line item.
See references/chronograph-mcp-map.md for data-need to tool mapping guidance.
Use references/model-methodology.md for the distilled forecast methodology. Load it when doing actual forecast math, explaining assumptions, building an Excel output, or debugging differences versus a reference workbook.
Core outputs:
A and forecast periods with E when producing Excel-style tables.When asked for Excel, use the spreadsheet skill and build a clean workbook rather than recreating the original workbook cell-by-cell. A good workbook shape is:
Inputs: scope, as-of date, currency, units, horizon, assumptions by fund type.Fund Forecast: one row per fund/period with actuals and forecast values.Portfolio Summary: annual totals, net cashflow, NAV, unfunded, exposure, charts when useful.Checks: reconciliation checks and source context.references/model-methodology.md: forecast formulas and default assumptions based on the Excel model.references/chronograph-mcp-map.md: Chronograph MCP data-need to tool mapping guidance for this workflow.development
Use when the user wants to spin up / create / launch / provision a DigitalOcean droplet (or "a remote dev box on DO") and connect to it from Codex as a remote SSH workspace.
data-ai
Search through Microsoft Teams chats or channels, triage unread or recent activity, draft follow-ups, and manage Planner tasks through connected Teams data.
tools
Motion / animation context for the `use_figma` MCP tool — animating Figma nodes via manual keyframes, animation styles, easing, and timeline duration. Load alongside figma-use whenever a task involves adding, editing, or inspecting animation on a node.
development
SwiftUI ↔ Figma translation. Use whenever the user mentions Swift, SwiftUI, iOS, iPhone, or iPad — in EITHER direction — translating a Figma design into SwiftUI (design → code), or pushing SwiftUI views / screens / tokens back into a Figma file (code → design). Triggers on phrases like 'implement this Figma design in SwiftUI', 'build this screen in Swift', 'push this SwiftUI view to Figma', 'mirror my Swift code in a Figma file', or whenever a Figma URL appears alongside `.swift` files / an `.xcodeproj`. Routes to a direction-specific reference doc; loads alongside `figma-use` for the code → design path.