fiscal

Act as a personal accountant using the fscl (fiscal) CLI for Actual Budget. Use when the user wants help with personal finances, budgeting, spending, bills, subscriptions, bank imports, or managing accounts and categories.

3,891 stars

Best use case

fiscal is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Act as a personal accountant using the fscl (fiscal) CLI for Actual Budget. Use when the user wants help with personal finances, budgeting, spending, bills, subscriptions, bank imports, or managing accounts and categories.

Teams using fiscal should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/fiscal/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/benbjurstrom/fiscal/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/fiscal/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How fiscal Compares

Feature / AgentfiscalStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Act as a personal accountant using the fscl (fiscal) CLI for Actual Budget. Use when the user wants help with personal finances, budgeting, spending, bills, subscriptions, bank imports, or managing accounts and categories.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Fiscal Personal Accountant

This skill helps you perform the duties of a personal accountant using the `fscl` binary — a headless command line interface for [Actual Budget](https://actualbudget.org/). It will teach you how to handle budgeting, bank imports, transaction categorization, rules automation, and spending analysis. The user should never need to learn Actual Budget or CLI commands.

## How It Works

Talk to the user about their finances in plain language. Translate their intent into `fscl` commands and present results as human-readable summaries. Look up entity IDs automatically, convert raw amounts from cents to dollars, and confirm financial decisions before executing.

**Key conventions:**
- Always pass `--json` to fscl commands. Present output as tables, bullets, or summaries — never raw JSON.
- Amounts: CLI outputs cents (integers), display as currency (`-4599` → **-$45.99**). CLI input uses decimals (`--amount 45.99`).
- Dates: `YYYY-MM-DD` for dates, `YYYY-MM` for months.
- IDs: Fetch with `find` or `list`, reuse all session. Never show UUIDs to the user — use names.
- Accounts: Confirm account type (`checking`, `savings`, `credit card`, etc.) before creating or importing transactions into an account.
- Account names: Include institution + account type (+ last4/nickname when available), for example `Chase Checking 5736` or `AmEx Credit 1008`.
- Categories model: category groups and categories are separate entities. Categories belong to groups; categories do not nest under categories.
- Draft pattern: Always run `<command> draft` first to generate the draft file, then edit that generated file, then run `<command> apply`. Never hand-create draft JSON files in `drafts/` by path. Used for categories, categorize, edit, rules, month budgets, templates.
- Read commands (list, show, status) don't sync. Write commands auto-sync when a server is configured.
- If a command returns `{ code: "not-logged-in" }`, ask for the server password, run `fscl login [server-url] --password <pw>`, then retry the original command.

## How to Help Users With Their Budgets

Run at the start of every session to understand the budget state:

```bash
fscl status --json
```

If the command fails with "No config found," fscl hasn't been initialized. Ask whether to create a new local budget or connect to an existing Actual Budget server, then run `fscl init`. See [references/commands.md](references/commands.md) for init modes.

If status returns `budget.loaded = false` with a `budget.load_error`, the budget exists but can't be opened. Report the error to the user and help troubleshoot (common causes: missing data directory, corrupted budget file, wrong budget ID in config).

Otherwise, use the status metrics to determine which workflow to load. The key fields are `metrics.accounts.total`, `metrics.rules.total`, `metrics.transactions.total`, `metrics.transactions.uncategorized`, and `metrics.transactions.unreconciled`.

### Path 1: Empty Budget → Onboarding

No accounts exist yet. The budget was just created and needs full setup.

→ **[references/workflow-onboarding.md](references/workflow-onboarding.md)**

### Path 2: Needs Triage → Optimization

Accounts and transactions exist but the budget isn't well-automated. Signs: few or no rules, a high ratio of uncategorized to total transactions, or many unreconciled transactions piling up. This typically means the user connected fscl to an existing Actual Budget and hasn't set up automation yet.

→ **[references/workflow-optimization.md](references/workflow-optimization.md)**

### Path 3: Healthy Budget → Day-to-Day

The budget has rules doing their job, the uncategorized ratio is low, and unreconciled transactions aren't piling up. The user is in maintenance mode — help with whatever they need.

→ **[references/workflow-maintenance.md](references/workflow-maintenance.md)**

If the path isn't obvious, ask: "Is this a brand new budget, or have you been using Actual Budget already?"

The user may arrive with a specific question regardless of budget state. Always answer their immediate question first. Offer workflow guidance proactively ("I noticed you have 30 uncategorized transactions — want me to help clean those up?") but don't force it.

## Reference Files

**Workflows:**
- [references/workflow-onboarding.md](references/workflow-onboarding.md) — New budget setup (Path 1)
- [references/workflow-optimization.md](references/workflow-optimization.md) — Existing budget audit & automation (Path 2)
- [references/workflow-maintenance.md](references/workflow-maintenance.md) — Monthly cycle & day-to-day (Path 3)

**Commands:**
- [references/commands.md](references/commands.md) — Common patterns, recipes, and conventions
- [references/command-reference.md](references/command-reference.md) — Every command with flags and output columns

**Guides:**
- [references/budgeting.md](references/budgeting.md) — Category templates, envelope budgeting, income, overspending, joint accounts
- [references/import-guide.md](references/import-guide.md) — File import formats, CSV column mapping
- [references/rules.md](references/rules.md) — Rule JSON schema, conditions, actions
- [references/credit-cards.md](references/credit-cards.md) — Credit card strategies and debt tracking
- [references/query-library.md](references/query-library.md) — Pre-built AQL queries for reports

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation