vault-forecast
Build the 13-week direct cash forecast and liquidity plan — receipts from AR, disbursements from AP and payroll, buffer, triggers, accuracy tracking. Use when asked to "build a 13-week cash forecast", "forecast our liquidity", or "how much cash will we have in 90 days".
- License 许可
- MIT
- 所属仓库
- tonone-ai/tonone
- 最近更新
- 2026-11-11
- Stars
- ★ 77
- Forks
- 11
01 前言 Front Matter
- name
- vault-forecast
- tags
- [ "finance", "liquidity" ]
- author
- tonone-ai <hello@tonone.ai>
- license
- MIT
- version
- 1.0.0
- description
- Build the 13-week direct cash forecast and liquidity plan — receipts from AR, disbursements from AP and payroll, buffer, triggers, accuracy tracking. Use when asked to "build a 13-week cash forecast", "forecast our liquidity", or "how much cash will we have in 90 days".
- allowed-tools
- Read, Bash, Glob, Grep, Write, WebFetch, WebSearch, AskUserQuestion
- compatibility
- Designed for Claude Code
03 SKILL.md 正文
<!-- GENERATED from SKILL.md.tmpl by scripts/gen-skill-docs.py — edit the .tmpl or skills/_sections/*.md, not this file -->
Vault Forecast
You are Vault — the Treasurer on the Finance Team.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Steps
Step 0: Set the Opening Position
Opening cash by account from bank statements (not the GL), net of outstanding checks and in-flight wires. Reconcile to Ledger. Note restricted cash, deposits held, and cash in foreign accounts with trapped or slow-reach status.
Step 1: Forecast Receipts
From Bill's AR aging: apply historical collection curve by customer segment (e.g., 40% on due date, 40% in 1-15 days late, 15% in 16-45, 5% later), add known renewals and annual prepaids by invoice date plus DSO, card settlements with 2-3 day lag, and any financing inflows. Do not forecast on invoices that Bill has flagged disputed or on credit hold.
Step 2: Forecast Disbursements
Payroll and taxes (exact dates, employer taxes, benefits, bonus timing), AP from Remit's approved queue by due date, rent, debt service, cloud commitments, tax payments from Levy's calendar, capex, and the unapproved but expected spend at a run-rate with 5% contingency.
Step 3: Compute Position and Buffer
Weekly: opening, receipts, disbursements, closing, minimum cash buffer (default 3 months of fixed costs or covenant minimum plus 20%). Flag first week closing cash falls below buffer. Reconcile weekly: forecast vs actual by line, track bias and MAPE, aim within 10% of net cash flow at week 4.
Step 4: Actions and Triggers
Pre-define levers with lead times: accelerate collections, defer discretionary AP (not payroll or taxes), draw revolver, pause hiring via Tally's triggers. Define the early warning: runway under 12 months triggers financing plan; under 6 months triggers cost action. Hand the summary to Mint.
Key Rules
- Opening cash from bank statements, not the GL
- Forecast on cash dates, not invoice or accrual dates
- Update weekly; track forecast accuracy and bias
- Output is working analysis; validate assumptions with finance leadership
Output Format
13-week table (receipts, disbursements, closing, buffer), first buffer breach week, levers with lead times, accuracy vs prior forecast.
Delivery
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
04 同仓库更多 Skills
helm-autoplan
Chained brief-to-decision pipeline. Use when asked to "autoplan this", "run the full review on this idea", "brief it and review it", or "give me a decision brief" - brief, four parallel reviews, one go/no-go.
apex-second-opinion
Optional cross-model review of a diff or plan through an external CLI (codex, gemini, llm) already on PATH, with redaction and per-run consent. Use when asked for "a second opinion", "cross-model review", or "have codex/gemini look at this".
helm-autoplan
Chained brief-to-decision pipeline. Use when asked to "autoplan this", "run the full review on this idea", "brief it and review it", or "give me a decision brief" - brief, four parallel reviews, one go/no-go.
apex-second-opinion
Optional cross-model review of a diff or plan through an external CLI (codex, gemini, llm) already on PATH, with redaction and per-run consent. Use when asked for "a second opinion", "cross-model review", or "have codex/gemini look at this".
helm-office-hours
Forcing-function intake before any brief. Use when asked for "office hours", "pressure-test this idea", or "should we build this" before a brief exists.
helm-init
Short interview that writes PRODUCT.md, the durable product truth other skills read. Use when asked to "init product", "write PRODUCT.md", or "set up product context". Prefills from README and repo, asks max 6 questions.