Skip to content
Back to skills

Mk 107

ASecurity

Member-benefit offer design. Use when the task requires differentiated treatment for existing members. Apply this method to the specified inputs and verify the deliverable

  • 259 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 23, 2026
ai-agentsgoaws

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 23, 2026

npx -y skills add backtrue/thinkwithblack-skill --skill mk-107 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 107?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Mk 107
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-107/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-107)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: mk-107
description: "Member-benefit offer design. Use when the task requires differentiated treatment for existing members. Apply this method to the specified inputs and verify the deliverable"
---

# MK-107 | Member-benefit offer design

For a regular chat, upload `packs/mk-107.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Differentiated treatment for existing members**

Do not fabricate discounts, gift inventory, countdown deadlines, limited quantities, or testimonials

## Required inputs

Raw inputs: valid member purchases/segmentation, actual needs/preferences, candidate benefits/eligibility, product and benefit costs, stock/capacity and existing policy

## Method

1. Fix the member task/eligibility and preserve approved benefits. Returning customers are not all high-value members, and analysis does not cancel existing commitments. Separate acquisition offers from repeat benefits
2. For each candidate list what/when the customer gets it, demand evidence and the business burden. Separate discounts, gifts, service, priority and bundles; high order value is not available contribution
3. Calculate same-cohort expected order contribution minus additional benefits/fulfillment and check stacking, stock/capacity. Exclude unsupported spending, resource failures or ineligible recipients. Honor existing policy while recording its cost issue
4. Choose a feasible, affordable candidate directly supporting observed member needs with reviewable outcomes. Mark new-purchase assumptions and limit trials when incremental evidence is absent; offer use does not mean a new order. A service response need not become a discount
5. Deliver costs, eligibility, evidence, selections/rejections and revision conditions. Rechoose after changed stacked costs, supply, member state or needs. Rising order value with falling total contribution withdraws a volume proposal

## Calculations and interpretation

Candidate order contribution is net order revenue minus variable costs not already deducted and added benefit cost, each counted once. Benefits on purchases that would already occur are subsidies, not incremental orders

Hypothetical check: two options meet the same member need; A contributes 120 and B 80, supporting A. Adding A's omitted shipping/service costs of 70 lowers it to 50; choose B. Previously promised benefits are still honored

Decision rules authored by ThinkWithBlack on 2026-10-14; original course sources are retained below

## Required output fields

| Order | Field | How to complete |
|---:|---|---|
| 1 | Goal | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 2 | Audience | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 3 | Plan/task | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 4 | Evidence and assumptions | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 5 | Prerequisites | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 6 | Resources | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 7 | Deliverables and acceptance | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 8 | Open issues | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |

## Verification cases

**MK-107-C05 | The budget is unknown, but materials can be organized first**

Expected: Deliver the parts of the plan that do not depend on the budget first; do not require a complete questionnaire

## Method sources

Source file: 行銷策略實戰學程Day4-佈局獲利 × 節奏變現 × 轉單收割

Location: Campaign

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/1dq3xqYVUnWvUCpzZKI91yDDOzvkyG0uHy3EOsOjtItA/edit

English translation of source excerpt:

> Consider consumers with active needs each month and bring campaign traffic to the campaign page for prompt conversion

Files in this skill

  • SKILL.md4.2 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json15.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.