For AI agents: Markdown version of this page · llms.txt
Setup guide

Transaction Categorization Agent for OpenClaw - transaction categorization with evidence attached

The free Transaction Categorization Agent runs on OpenClaw as three plain-text files: set it up once in your OpenClaw workspace, approve a sample-data test, then trigger each run with the usage prompt and this run's inputs.

Get the Transaction Categorization Agent - freeOpenClaw overviewWhat’s new on OpenClaw

What the Transaction Categorization Agent does

With OpenClaw, this agent meets you in the chat app you already live in. It proposes a category for every uncoded transaction with the evidence: date, payee, amount, proposed category, evidence, review status. You approve the batch.

Categorization errors compound into wrong reports. This assistant applies your category rules consistently, records the evidence per transaction, and lists only the genuinely ambiguous ones as questions. You review the edge cases instead of the whole pile, and the same vendor codes the same way every month.

Where the Included files go in OpenClaw

Drop the Included files into your OpenClaw workspace and point it at skill.md, then run the setup prompt over your usual chat channel. OpenClaw keeps its workspace persistent, so the agent's rules survive between asks, and its approval style matches the agents' stop-at-human-gates design.

What a run looks like on OpenClaw

A run looks like this: you message OpenClaw on your usual channel with this run's inputs, and it works through transaction-categorization from the workspace skill. The output - it proposes a category for every uncoded transaction with the evidence: date, payee, amount, proposed category, evidence, review status - comes back in chat for your approval.

Setup, step by step

  1. Drop skill.md, setup-prompt.txt and usage-prompt.txt into your OpenClaw workspace and point it at the skill file.
  2. Run the setup prompt over your usual chat channel (WhatsApp, iMessage, Slack, Telegram, Discord).
  3. The agent runs transaction-categorization on fictional sample data first - approve that test before real work.
  4. OpenClaw keeps its workspace persistent and its approval style matches the agent's stop-at-human-gates design: each real run is one message with this run's inputs.

Honest limits on OpenClaw

OpenClaw is self-hosted open-source software: you are responsible for your own install, keys and updates. Read its security docs before connecting real accounts.

Questions people ask

Does the Transaction Categorization Agent work on OpenClaw?

Yes - the agent is three plain-text files, and on OpenClaw they live in your OpenClaw workspace. The four setup steps below are the whole job: Drop skill.md, setup-prompt.txt and usage-prompt.txt into your OpenClaw workspace and point it at the skill file. Then run the setup prompt over your usual chat channel (whatsapp, imessage, slack, telegram, discord).

What does the Transaction Categorization Agent produce on OpenClaw?

It proposes a category for every uncoded transaction with the evidence: date, payee, amount, proposed category, evidence, review status. OpenClaw delivers it in your chat channel; you approve before anything is used. Every run waits for your approval before anything is sent, spent, published or scheduled.

Is this affiliated with OpenClaw?

No. AI Agent Skills is an independent store. We are not affiliated with, endorsed by, or sponsored by OpenClaw or its makers. Platform names belong to their owners; capabilities change, so check OpenClaw's current documentation.

Run this agent on another assistant

Microsoft Copilot Hermes Instinct Muse Perplexity ChatGPT ChatGPT Dots Claude DeepSeek Town Grok Gemini

More bookkeepers agents on OpenClaw

Reconciliation Agent Receivables Follow Up Agent Bills Invoices Agent

AI Agent Skills is an independent store, not affiliated with OpenClaw or its makers. Platform names belong to their owners.