cleaning-up-bookkeeping
Skill0 starsChanged 9 days agoMITView on GitHub
Tidies up SuperBooks transactions and receipts: categorizes or recategorizes transactions, fixes a transaction's category or status, finds uncategorized spending, matches receipts and bills in the inbox to transactions, and finds documents. Use when the user asks to 'categorize last month's transactions', 'match the receipts in my inbox', 'find uncategorized expenses', 'fix this transaction's category', 'reconcile my receipts', or 'find the receipt for this purchase'.
In this repository66 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adding-uptime-monitorsSkill
- analyzing-page-performanceSkill
- booking-meetingsSkill
- building-onboarding-workflowsSkill
- building-study-guidesSkill
- capturing-tasksSkill
- capturing-web-pagesSkill
- chasing-unpaid-invoicesSkill
- checking-domain-connectionsSkill
- checking-email-deliverabilitySkill
- checking-notification-deliverySkill
- checking-uptime-statusSkill
- connecting-customer-domainsSkill
- discussing-buildsSkill
- drafting-invoicesSkill
- drafting-social-postsSkill
- editing-demosSkill
- editing-page-draftsSkill
- extracting-document-textSkill
- finding-meeting-timesSkill
- handling-flaky-changesSkill
- investigating-tasksSkill
- making-demo-videosSkill
- managing-bookingsSkill
- managing-content-calendarSkill
- managing-demosSkill
- managing-voice-librarySkill
- planning-revisionSkill
- preflighting-domainsSkill
- publishing-pagesSkill
- reading-financial-reportsSkill
- reading-text-aloudSkill
- reading-web-pagesSkill
- reporting-snapvisor-usageSkill
- researching-course-materialSkill
- researching-summary-librarySkill
- responding-to-incidentsSkill
- reviewing-email-performanceSkill
- reviewing-notification-workflowsSkill
- reviewing-social-performanceSkill
- reviewing-visual-buildsSkill
- reviewing-workloadSkill
- searching-getitdone-api-docsSkill
- sending-email-campaignsSkill
- sending-notificationsSkill
- setup-bioflowSkill
- setup-calySkill
- setup-demofySkill
- setup-dodomainSkill
- setup-getitdoneSkill
- setup-notiflySkill
- setup-postifySkill
- setup-sendlySkill
- setup-shortySkill
- setup-snapvisorSkill
- setup-superbooksSkill
- setup-unotesSkill
- setup-upapiSkill
- setup-uptimelySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Operations listed by name: call them directly, for example superbooks:invoices_list.
- Very specific: line 24
If the connection lists the operations by name instead (the per-tool surface), call them directly without the external_ prefix.
- Very specific: line 45
If a category the user wants does not exist, offer to create it with external_categories_create first.
- Very specific: line 61
Check the real argument names in the superbooks:search_tools declaration before running this.
- Distinctive: line 65
No change without the user's approval of that specific change.
- Very specific: line 66
Never guess a category slug.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Generated from plugins/superbooks/skills/cleaning-up-bookkeeping/SKILL.md by scripts/sync-skills.mjs. Edit the plugin copy, then run the script. -->Bookkeeping cleanup in SuperBooks
Work through transactions that need a category or status, and connect receipts to the transactions they belong to. Every change is shown to the user before it is made.
Connecting and calling the tools
Every operation in this skill comes from the superbooks MCP server, the SuperBooks connector. The server defaults to Code Mode, so the operations below are written as the external_* functions you call inside superbooks:execute_typescript. On a server set to the per-tool surface, the same operation is listed as superbooks:<name> without the external_ prefix, for example superbooks:invoices_list.
- Only
superbooks:search_toolsandsuperbooks:execute_typescriptlisted (Code Mode, the default): callsuperbooks:search_toolsfirst, then call each tool insidesuperbooks:execute_typescriptasexternal_<tool>(for exampleexternal_invoices_list); the program mustreturnits result. Scopes, confirmations and gates are identical on both surfaces. - Operations listed by name: call them directly, for example
superbooks:invoices_list. - "Tool not found": switch to the Code Mode route instead of retrying the direct call. If
superbooks:search_toolsdoes not return the tool either, its OAuth scope was not granted; the user reconnects SuperBooks and approves that scope. - No
superbookstools at all: SuperBooks is not connected yet. Follow thesetup-superbooksskill.
Tools you will use
The superbooks MCP server has two tools: superbooks:search_tools (call it first, for example with transaction, categor, inbox, to get the exact input shapes) and superbooks:execute_typescript (run a short program calling the declared external_* functions; the program must return its result).
If the connection lists the operations by name instead (the per-tool surface), call them directly without the external_ prefix.
Operations this skill uses:
external_transactions_list: transactions for a period (for examplefrom: "2026-09-01"), with amount, merchant andcategory_slug.external_transactions_get: one transaction in full.external_categories_list: the team's categories and their slugs.external_categories_createadds one the user asks for.external_transactions_update_category: set a transaction's category by slug.external_transactions_update_status: set a transaction's workflow status.external_tags_listandexternal_tags_create: labels the user may want.external_inbox_list: incoming receipts and bills waiting to be matched.external_inbox_match: attach an inbox item to a transaction.external_documents_search,external_documents_list,external_documents_get: receipts and documents already stored.
Workflow
- Agree the period (default: last calendar month). In one program, fetch
external_transactions_listfor it andexternal_categories_listwithawait Promise.all. - List the transactions that are uncategorized or that the user flagged. For each, propose a category slug from the category list, based on the merchant and amount.
- Show the proposals as a table (date, merchant, amount, current category, proposed category) and let the user approve all, some, or edit them.
- Apply the approved ones in one program: one
external_transactions_update_categorycall per transaction, each wrapped so one failure does not hide the others. Report what changed and what failed. - For receipts: fetch
external_inbox_list, pair each item with the transaction of the same amount and a close date, show the pairs, and applyexternal_inbox_matchfor the ones the user approves. - If a category the user wants does not exist, offer to create it with
external_categories_createfirst.
Code Mode pattern
const approved = [{ id: "txn_1", slug: "design_software" }];
const results = await Promise.all(
approved.map((t) =>
external_transactions_update_category({ id: t.id, category_slug: t.slug })
.then(() => ({ id: t.id, ok: true }))
.catch((e) => ({ id: t.id, error: String(e) })),
),
);
return results;Check the real argument names in the superbooks:search_tools declaration before running this.
Rules
- No change without the user's approval of that specific change. Batches are fine once the user approves the batch.
- Never guess a category slug; use one returned by
external_categories_list. - Deleting transactions, receipts, or categories is not offered here. Destructive operations are off by default for the team; do not ask the user to turn them on.
- Each credential is limited to 120 calls a minute. For large batches, work in chunks of about 50 and report progress between them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

