一键导入
waccy-install
Check whether waccy is installed and the MCP server is registered, and fix anything that's missing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Check whether waccy is installed and the MCP server is registered, and fix anything that's missing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Show the balance sheet for the modelled periods — assets, liabilities, and equity.
Show the cash flow statement for the modelled periods — operating, investing, and financing activities.
Extract financial data from QuickBooks Online or SEC EDGAR and build the WACCY dataset.
Show the income statement (P&L) for the modelled periods — revenue, expenses, and net income.
Build a three-statement financial model (income statement, balance sheet, cash flow) from the extracted dataset.
Execute SQL against the WACCY financial dataset to answer specific questions about the data.
| name | waccy-install |
| description | Check whether waccy is installed and the MCP server is registered, and fix anything that's missing. |
Verify the installation is complete and working. Install or register anything that's missing.
npx skills add DecisionNerd/waccy for the first timewhich waccy && waccy --version
If missing, install via Homebrew (recommended):
brew tap DecisionNerd/tap && brew install waccy
If Homebrew isn't available, install from source:
cargo install --git https://github.com/DecisionNerd/waccy --bins
which waccy-mcp
If missing, re-run the install step — waccy-mcp is installed alongside waccy.
claude mcp list # Claude Code
codex mcp list # Codex
Look for waccy in the output. If it's not listed, register it:
Claude Code:
claude mcp add waccy $(which waccy-mcp)
Codex:
codex mcp add waccy -- $(which waccy-mcp)
waccy status
If no dataset is found, run the first extraction:
waccy extract quickbooks
# or
waccy extract edgar --option cik=0001234567
Summarise what was found and what (if anything) was fixed:
<path> ✓ / installed now ✓ / not found ✗If everything is good, offer to run /model to build a three-statement model.