FI

f3-insights/automation-toolbox

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る

1 stars 品質 59 トレンド 16NOASSERTION

The back office, run by agents: 198 agents and 152 skills for Claude Code that close the books, forecast, report to executives, run engagements and ship software.

概要

What you get · Quick start · Departments · How it works · Getting started · Security · License Agents and skills for Claude Code that run the recurring work of a finance and operations practice: closing the books, forecasting, reporting to executives, running client engagements, mapping processes, and shipping software. Built and used by F3 Insights . Most agent collections give you prompts. This one gives you : each recurring job a finance and operations team does, written down as a workflow an agent can run, reviewed by a second agent, and finished by plain code you can read. A month-end close, a 13-week cash forecast, a board package, a client update, a process map, an issue-to-pull-request factory, a nightly email sweep. Each one is an that runs the job end to end the way a lead runs a small team. 65 of the 67 workflows end in an independent or reviewer that reads the output against its sources only and returns PASS or FAIL with fixes.

README

以下は原文 README の抜粋です。原文を見る。

What you get · Quick start · Departments · How it works · Getting started · Security · License

Agents and skills for Claude Code that run the recurring work of a finance and operations practice: closing the books, forecasting, reporting to executives, running client engagements, mapping processes, and shipping software. Built and used by F3 Insights.


What you get

Most agent collections give you prompts. This one gives you the back office as a working system: each recurring job a finance and operations team does, written down as a workflow an agent can run, reviewed by a second agent, and finished by plain code you can read.

67 ready workflows

A month-end close, a 13-week cash forecast, a board package, a client update, a process map, an issue-to-pull-request factory, a daily plan. Each one is an orchestrator that runs the job end to end the way a lead runs a small team.

Checked before you see it

65 of the 67 workflows end in an independent checker or reviewer that reads the output against its sources only and returns PASS or FAIL with fixes. Figures trace to a ledger pull or a file, not to a model’s memory.

Nothing writes behind your back

Agents never touch a live system. They leave a change set of proposed writes; you approve it, and a plain Python script applies it after the session.

GitHub で README 全文を見る

推奨ツール

別のキーワードを試すか、フィルタを外してください。

インストール

npx skillfish add f3-insights/automation-toolbox
MCP 初心者?mcpskill.org のガイドから始めましょう →