Organize Your Business Finances

Organize your business finances — skill template

Turn this template into a working skill by resolving every TODO. The seed prompt below is the published Anthropic example this template was derived from; your skill should generalize it for repeated, hands-off use.

Outcome

Create spreadsheets that bring clarity to your finances. Spot trends, filter what matters, and understand what your numbers are telling you.

TODO: Restate the outcome for YOUR context in one sentence: who runs this, on what input, producing what artifact, how often.

Seed prompt (verbatim from source, © Anthropic PBC)

I need help organizing my freelance invoices from this year. I'm uploading my invoice file. It has the date, client name, what the project was, and how much I invoiced. Formatting is inconsistent because I've been adding to it all year.

Can you create a cleaner version with a dashboard that shows my total income, breaks it down by month, and lists my clients by who's paid me the most. Add sparklines and data visualizations showing trends over time at a glance. I want to be able to filter and sort to find specific invoices when I need them. If you notice nuance in the data, leave cell comments for more context.

Make this a sophisticated financial dashboard with a 'quiet luxury', editorial aesthetic—muted sage green accent, abundant whitespace, restrained typography. You may need to write a Python script using xlsxwriter to get the sparklines and advanced features working.

Required context and inputs

• Invoice spreadsheet or CSV file upload
• Optional: Extended Thinking (recommended)
• Python/xlsxwriter capability for advanced features
• TODO: exact file paths / folders / message formats this skill should expect
• TODO: domain context the model cannot infer (naming conventions, thresholds, house style)

Tools, connectors, APIs, and authentication

• No connectors detected on the source page; base Claude capabilities only
• TODO: confirm which connectors are enabled in the runtime that will execute this skill
• Authentication: connectors authenticate via their own OAuth flows — this skill must

NEVER ask for, store, or echo credentials, tokens, or API keys. If auth is missing, stop and tell the user which connector to enable.

Permissions and sensitive actions

• Reads: TODO (folders, channels, records this skill may read)
• Writes: TODO (what it may create/modify, and where)
• Held back for the primary agent / human: sending external communications, financial

transactions, deleting or overwriting originals, submitting web forms

Workflow

1. Describe the task
2. Give Claude context (upload spreadsheet/CSV with invoice data)
3. What Claude creates (organized data with spreadsheet features)
4. Follow-up prompts (request additions/revisions; update with new data)
5. Tricks, tips, and troubleshooting

TODO: adapt the steps above (from the source page) into imperative instructions for the executing agent, including what to do between steps.

Decision points

• TODO: list each point where the skill must choose between paths, with the rule to apply
• Default rule: prefer the reversible option; when two readings of the input are

plausible, surface both rather than picking silently.

Validation criteria

• Output matches the outcome statement above (spot-check against the seed prompt's asks)
• Every factual claim is traceable to a provided input, connector record, or cited source
• All figures reconcile to source statements/workbooks; totals recomputed programmatically, not by eye
• Flag (never silently correct) discrepancies between model and source data
• TODO: add one domain-specific check a reviewer in your org would apply

Failure modes and fallbacks

• Ambiguous or missing input → ask one targeted question; if unattended, state the assumption inline and proceed
• Any step would take a sensitive/irreversible action → stop and hand back to the user (see Delegation)

Delegation

Apply the repo's delegation policy (docs/delegation-policy.md — bundle or restate it if you install this skill outside the repo). Defaults for this template:

• Run single-agent unless a step fans out over independent items (files, records,

vendors, channels). Only independent work parallelizes.

• Each delegated task must ship with: the minimal context slice it needs, an explicit

output contract, a validation check the primary agent runs on the result, and a fallback if it returns empty or fails.

• Final review, synthesis, and every sensitive action listed above stay with the

primary agent.

• TODO: name the concrete subtasks (if any) that qualify for delegation here.

Attribution

Derived from Organize your business finances (retrieved 2026-07-26). Seed prompt and workflow content © Anthropic PBC. Scaffold structure original to this repository.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: iankiku
• Source: iankiku/agent-skill-factory
• License: MIT

Install and usage instructions live in the source repository linked above.