BFCM Campaign Kit

Before. This is the public data for a UK activewear brand (GBP) on 3 Oct 2026:

• median price £42
• 69 of 250 products (27.6%) already show compare-at prices, at a median depth of 70%
• an announcement bar already running "BUY 3 QUALIFYING ITEMS FOR 15% OFF"

The merchant's brief: "We don't want to go deeper than 20% off sitewide." The obvious move is a flat 20% off everything. At a 55% margin that needs 57% more units just to break even, and it would stack on top of products already 70% off.

After. The skill's recommendation (excerpt):

Primary: a tiered offer, 10% off 1 item / 15% off 2 / 20% off 3 or more.

• It applies to full-price products only and never goes past your 20% cap.
• It replaces the current "3 for 15%" for the sale window.

Exclude the 69 products that already carry compare-at prices. Their 70% median depth is already far past your cap. Stacking would break the cap, and it makes any "was" claim risky.

Cyber Monday extra (optional): free UK Standard delivery over £[50], which you should confirm. It costs about 9.5% of a £42 order at £3.99 shipping.

The skill wrote three SMS for this plan, each 154 characters or fewer and each starting with the brand name and ending "Reply STOP to opt out". It used UK dates: early access Mon 23 Nov, Small Business Saturday UK Sat 5 Dec. It flagged that Royal Mail's 2026 Christmas dates weren't published yet, so it left [order-by date] as a placeholder and didn't guess. The full test log is kept in our internal test records.

Black Friday 2026 is Fri 27 Nov. Cyber Monday is Mon 30 Nov. Give this skill your Shopify store URL and it reads your real catalogue, prices, existing discounts and policies. It then gives you:

1. An offer strategy with honest maths. It compares a % discount, a bundle, a gift with purchase and a free-shipping threshold, using your real prices. For each one it shows the extra sales needed just to break even. It never predicts revenue.
2. A dated campaign calendar: teaser, early access, Black Friday, Small Business Saturday, Cyber Monday and last chance, with US and UK variants. It includes USPS's published 2026 holiday cutoffs, and marks UK carriers' dates as "not yet published" where they aren't out.
3. Ready-to-paste copy:
   • 5 emails (two subject lines each, with an unsubscribe and address footer)
   • 3 SMS (160 characters or fewer, with your brand name and "Reply STOP to opt out")
   • a homepage banner and announcement bar for each phase
   • product-page lines
4. A pre-BFCM ops checklist: discount stacking, code testing, shipping cutoffs, returns wording, site speed and support peak. For support replies it points to support-macro-writer, and for disputes to chargeback-response-writer.

Only true urgency. No resetting countdowns, no "only 2 left" without real stock numbers (Shopify's public data doesn't show them), and no inflated "was" prices. The rules follow the UK DMCC Act 2024, CMA guidance and the FTC's pricing guides (sources in references/compliance.md). This is not legal advice.

Tested on 4 real public Shopify stores (US and UK, low to high price points). Final version: 9/10 on all four.

Tested on 4 real public Shopify stores:

Final version scored 9/10 on all four. Every price, product and policy fact was checked against the live store data, every break-even figure was re-derived, and every SMS length was checked mechanically. The test logs (inputs, raw outputs, scores) are kept internally.

The tests ran on real public data, never made-up cases, and were scored against a written rubric. A skill in this range ships only when every test scores 8/10 or more.

How we test, what we do not do, and which assistants we ran it on.

• It works from your store's public data and the margin you give it. Without a margin it shows the break-even maths with a placeholder.
• It never predicts revenue. It shows the extra sales each offer needs to break even.
• UK carriers' 2026 holiday dates are marked "not yet published" where they weren't out when the skill was built.
• It is not legal advice. The pricing and urgency rules follow the sources listed in the skill.

Works with any assistant that reads SKILL.md skills (Claude, Codex, Gemini CLI, Cursor and others), plus a paste-in prompt version for ChatGPT or any chatbot. We run our release tests on Claude Sonnet and Opus. Use your assistant's strongest model: in our tests, a small, fast model added facts that were not in the source data. The helper script needs Python 3 (standard library only) and web access. On claude.ai, turn code execution on; without it the skill reads the store with web fetch and says so.

1. Unzip the download. It holds the bfcm-campaign-kit folder, ready-made zips for claude.ai in a claude-ai folder, a README and the licence.
2. Put the bfcm-campaign-kit folder where your assistant looks for skills. The generic path is .agents/skills/ (or npx skills add from a folder). Tool-specific paths:
   • Claude Code: ~/.claude/skills/ (or .claude/skills/ inside one project)
   • OpenAI Codex, Gemini CLI, Cursor and others: .agents/skills/ or the skills folder their docs name
   • claude.ai: Customize, Skills, then the plus button, Create skill, Upload a skill, and upload the zip from the claude-ai folder without unzipping it (code execution must be on in Settings, Capabilities)
   • ChatGPT or any chatbot: open the skill's prompt.md, paste it into the chat, then paste your own text or link
   • Steps for each tool, with links to its official docs: how to install Agent Skills
3. Ask for the job in plain words, for example: "Plan Black Friday for mystore.com. We don't want to go deeper than 20%.". The skill loads by itself.