agentleFS
harshith-vaddiparthyharshith-vaddiparthy/finance-skills/skills/dunning-emails/SKILL.md

dunning-emails

Skill4 starsChanged 7 months agoMITView on GitHub

Use when drafting payment reminder or dunning email sequences from invoice, account, dispute, and customer context while preserving customer trust and requiring human approval before sending.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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
  1. Distinctive:

    Use this skill to draft polite, accurate, and escalation-aware payment reminder messages.

    line 8
  2. Distinctive:

    Verify whether the invoice is actually due and collectible.

    line 19
  3. Distinctive:

    If multiple invoices are involved, summarize totals and attach a statement table.

    line 27
  4. Distinctive:

    Never send the email directly.

    line 41
  5. Distinctive:

    Do not imply service suspension, collections agency referral, late fees, or legal action without explicit policy support.

    line 42
  6. Distinctive:

    Do not expose internal notes, customer health scores, or blame language in customer-facing drafts.

    line 43
  7. Distinctive:

    If there is an unresolved dispute, draft a resolution-focused message rather than a payment demand.

    line 44

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dunning Emails

Use this skill to draft polite, accurate, and escalation-aware payment reminder messages.

Inputs

  • Customer name, contact, invoice number, amount, currency, due date, and payment link or remittance instructions.
  • Prior outreach history and any promised payment date.
  • Dispute status, service issues, credit memos, or unapplied cash.
  • Brand voice and escalation policy.

Workflow

  1. Verify whether the invoice is actually due and collectible.
  2. Choose the correct tone based on aging stage:
    • Pre-due: helpful reminder.
    • 1-15 days overdue: operational nudge.
    • 16-45 days overdue: firmer request and ask for payment date.
    • 46+ days overdue: escalation with internal owner copied only if policy allows.
  3. Include only facts supported by the input.
  4. Provide subject line options and a concise email body.
  5. If multiple invoices are involved, summarize totals and attach a statement table.

Output

Return:

  • Suggested stage and rationale.
  • Email subject line.
  • Email body.
  • Internal note for the collector.
  • Missing data or approval needed before sending.

Guardrails

  • Never send the email directly.
  • Do not imply service suspension, collections agency referral, late fees, or legal action without explicit policy support.
  • Do not expose internal notes, customer health scores, or blame language in customer-facing drafts.
  • If there is an unresolved dispute, draft a resolution-focused message rather than a payment demand.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.