agentleFS
MicrosoftKnown publishermicrosoft/new-copilot-studio-tech-guide-kr/sample/solution/src/BlastBoxAgents/botcomponents/cra24a45_skill_md_30aa9a7b2b7c/filedata/SKILL.md

prorated-refund-calculator

Skill0 starsChanged 4 months agoMITView on GitHub

Calculate the exact prorated refund when a customer cancels a BlastPass membership, and the net settlement when a defective unit is traded up to a pricier model. Use after the Store Policy Agent confirms the refund rule and the Membership MCP has returned the membership details. The skill runs a bundled Python script so the arithmetic is exact.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill in a BlastPass cancellation or trade-up, once you have:

    line 16
  2. Distinctive:

    Do not invent any of these numbers.

    line 24
  3. Very specific:

    Cooling-off (full refund): If within_cooling_off is true, refund the full annual_price.

    line 29
  4. Very specific:

    Add --nonrefundable-credit <n> for MEGA members, or --within-cooling-off when the membership is still within the cooling-off window.

    line 51
  5. Distinctive:

    When the cancellation happens alongside a console upgrade — the defective unit is credited under warranty and the customer puts the value …

    line 60
  6. Distinctive:

    Use after (a) the Store Policy Agent confirms the defective unit is credited at its purchase price with no restocking fee, (b) the …

    line 69

≈ “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

Prorated Refund Calculator (BlastPass)

This skill computes the exact refund owed when a customer cancels their BlastPass membership, and the net settlement when a defective unit is credited toward a pricier model. The math must be exact and consistent, so you run the bundled blastpass_refund.py script — never compute the refund in your head, and never write your own code.

When to use

Use this skill in a BlastPass cancellation or trade-up, once you have:

  1. The Store Policy Agent has confirmed the member's tier and that a prorated refund (or cooling-off full refund) applies.
  2. The Membership MCP (get_membership) has returned the membership record, including annual_price, months_remaining, cancellation_fee, nonrefundable_credit, and within_cooling_off.

Do not invent any of these numbers. They come from the Membership MCP and the Store Policy Agent.

The refund rules (single source of truth)

  1. Cooling-off (full refund). If within_cooling_off is true, refund the full annual_price. No fee, no proration.
  2. Prorated cancellation (the usual case). Otherwise refund the value of the whole unused months left on the 12-month term, then subtract the tier cancellation fee.
  3. Non-refundable credit. Subtract nonrefundable_credit (only the MEGA tier has one). For other tiers it is 0.
  4. The refund is never negative.

Workflow

1. Compute the membership refund

Take annual_price, months_remaining, cancellation_fee, nonrefundable_credit, and within_cooling_off from the get_membership result, and run:

python3 blastpass_refund.py refund \
  --annual-price 129.99 --months-remaining 8 --cancellation-fee 10

Add --nonrefundable-credit <n> for MEGA members, or --within-cooling-off when the membership is still within the cooling-off window. The script prints the breakdown and a REFUND DUE: $... line.

Worked example: BlastPass Plus Extra, annual_price 129.99, months_remaining 8, cancellation_fee 10 -> monthly $10.8325, prorated $86.66, minus $10 = $76.66.

2. (Trade-up only) Compute the upgrade settlement

When the cancellation happens alongside a console upgrade — the defective unit is credited under warranty and the customer puts the value toward a pricier model, applying the membership refund as store credit — run:

python3 blastpass_refund.py settle \
  --defective-credit 399.99 --upgrade-price 499.99 --membership-credit 76.66

Use after (a) the Store Policy Agent confirms the defective unit is credited at its purchase price with no restocking fee, (b) the Warehouse MCP returns the upgrade model's price, and (c) the prorated refund above is known. The script prints the breakdown and a NET DUE FROM CUSTOMER: $... (or REFUND TO CUSTOMER: $...) line.

Worked example: defective base console credited $399.99, MEGA edition $499.99, membership refund $76.66 applied as credit -> upgrade difference $100.00, net $23.34 due from the customer.

3. Report the result

  • State the refund due and (if a trade-up) the net due / refund clearly.
  • Show the breakdown lines so the associate can verify how it was derived.
  • Offer to cancel the membership via the Membership MCP (cancel_membership) and to hand the final numbers to the slip-pdf-generator skill to print the slip.

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.