ar-collections
Skill4 starsChanged 7 months agoMITView on GitHub
Use when reviewing accounts receivable aging, prioritizing overdue invoices, preparing collector worklists, identifying disputed balances, and recommending next collection actions for finance operators.
In this repository8 other files it gives its agents.
- cfo-briefingSkill
- contract-to-invoiceSkill
- dunning-emailsSkill
- finance-close-checklistSkill
- invoice-health-checkSkill
- payment-reconciliationSkill
- revenue-recognition-qaSkill
- usage-billing-reviewSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill to turn an AR aging report and account context into a prioritized, source-backed collections plan.
- Distinctive: line 12
Ask for the missing items only when they are necessary:
- Distinctive: line 39
Do not threaten suspension, legal action, or credit reporting unless the user's policy explicitly allows it.
- Distinctive: line 40
Do not mark invoices as collectible if source data shows an active dispute, billing error, or unapplied payment.
- Distinctive: line 41
Keep customer-facing language factual and calm.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
AR Collections
Use this skill to turn an AR aging report and account context into a prioritized, source-backed collections plan.
Inputs
Ask for the missing items only when they are necessary:
- AR aging export with customer, invoice, due date, amount, currency, aging bucket, and owner.
- Customer notes, payment promises, dispute status, and prior outreach.
- Materiality threshold, collection policy, and escalation rules.
- Customer health context, contract status, open support tickets, or renewal timing.
Workflow
- Normalize the aging view by customer, invoice, due date, amount, aging bucket, and dispute status.
- Separate true collection work from administrative cleanup: unapplied cash, credits, duplicate invoices, invalid contacts, and invoices already under dispute.
- Rank accounts by action priority using amount, days overdue, relationship risk, dispute status, payment history, and upcoming renewal or churn risk.
- Assign a recommended next action for each account: reminder, statement resend, dispute resolution, sales/customer-success escalation, executive escalation, payment plan, write-off review, or no action.
- Flag missing evidence and assumptions. Do not invent payment commitments or customer history.
Output
Return:
- Executive summary: total past due, material exposure, urgent accounts, and main blockers.
- Priority table with customer, invoice count, past-due amount, oldest due date, status, owner, next action, and evidence.
- Dispute and cleanup queue.
- Outreach drafts only when requested.
- Approval list for sensitive actions such as executive escalation, service hold, payment plan, write-off, or legal referral.
Guardrails
- Do not threaten suspension, legal action, or credit reporting unless the user's policy explicitly allows it.
- Do not mark invoices as collectible if source data shows an active dispute, billing error, or unapplied payment.
- Keep customer-facing language factual and calm.
- Clearly distinguish recommendations from actions already taken.
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.

