Skip to content
Back to skills

Mk 117

ASecurity

Assessing weekend or time-slot campaigns. Use when the task requires deciding whether a campaign is needed from time-slot data first. Apply this method to the specified inputs and verify the deliverable

  • 259 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added October 23, 2026
ai-agentsgo

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-117 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 117?

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

Security grade badge for Mk 117
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-117/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-117)

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-117
description: "Assessing weekend or time-slot campaigns. Use when the task requires deciding whether a campaign is needed from time-slot data first. Apply this method to the specified inputs and verify the deliverable"
---

# MK-117 | Assessing weekend or time-slot campaigns

For a regular chat, upload `packs/mk-117.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Deciding whether a campaign is needed from time-slot data first**

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

## Required inputs

Raw inputs: matched weekdays/time slots with opening status, valid traffic, orders/net revenue, products/offers, costs, tracking/refund maturity and surrounding periods

## Method

1. Align weekday, duration, opening, products and tracking. Record closures/missing data rather than treat zero revenue as a promotion signal; separate event periods and product mixes
2. Split traffic, conversion and order value under matched conditions, then check valid orders/costs. Low traffic with a working destination supports a traffic candidate; checkout/page issues need fixing; adequate task results support retaining the setup rather than assuming weekends need promotions
3. Compare actual offers, communication/timing changes and no promotion, including contribution and fulfillment. Include discounts/shipping/gifts subsidizing orders that would already occur; slot revenue growth is not net benefit
4. Use surrounding periods and comparable controls to check shifted demand. Supported incremental contribution covering added costs supports continuation; transfer-only results, insufficient contribution or failed supply call for stopping/changing. Observe immature results
5. Deliver comparability, weak-stage evidence and retain/fix/traffic/bounded-promotion actions with revision conditions. Recompute for opening, denominators, refunds or surrounding-period updates. Missing critical costs remain fillable comparisons without invented discount levels

## Calculations and interpretation

Candidate event net benefit is added order contribution across the complete window minus subsidies to existing orders and added campaign costs. Do not deduct amounts already included in net revenue/variable costs

Hypothetical check: zero weekend orders from a closed store do not warrant promotion. Corrected open-store records with working checkout but insufficient matched traffic support a bounded traffic candidate. Five added weekend orders offset by five fewer weekday orders and lower contribution call for stopping that purported growth plan

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

## Required output fields

| Order | Field | How to complete |
|---:|---|---|
| 1 | Unit of analysis | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 2 | Original clue | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 3 | Classification definition | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 4 | Classification result | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 5 | Support/counterexample | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 6 | Unknown | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 7 | Downstream use | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |

## Verification cases

**MK-117-C05 | One record meets opposing conditions**

Expected: Mark it contradictory or undetermined; do not arbitrarily assign the most common category

## Method sources

Source file: 營業額提升主要關鍵(三)從數據來提升 ROI 的策略

Location: Weekend

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/1lwpCxF1cMgaK7Gnvngw8NzytDLYD8MK-p91g8dwSytU/edit

English translation of source excerpt:

> Weekend/evening flash sale

Files in this skill

  • SKILL.md4.2 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json17.9 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.