菜单
Use when auditing or optimizing an ecommerce store for COD (Cash on Delivery) markets — MENA, North Africa, Pakistan, SE Asia. Covers checkout UX, trust signals, RTO reduction, COD-to-prepaid conversion, mobile-first design, and RTL architecture.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Methodology for designing, refactoring, and evaluating AI agents — when to use a tool vs a skill vs a subagent, how to keep system prompts lean, and how to improve agents through eval-driven hill climbing. Use this skill whenever the user is building a new agent, refactoring or debugging an existing one, complains that an agent "got worse" or "is inconsistent", asks about system prompt length, tool design, multi-agent/subagent architecture, or wants to create evals for an LLM app — even if they don't use the word "agent" (e.g., "my Claude workflow keeps messing up", "should I add another tool?", "how do I test my prompt changes?").
Run an adversarial review→fix loop on a GitHub PR using BMAD adversarial agents until the reviewers find nothing actionable, then stop and report. Never auto-merges. Use after opening a PR, or when the user says "adversarially review", "hammer this PR", "review until clean", or /adversarial-pr-review.
Generate and send invoices through the Invoice Ninja API. Triggers on invoice creation, billing, generating a quote/devis.
Write professional emails with proper context gathering before drafting. Triggers on email writing, reply drafting, cold outreach.
Resolve git merge conflicts in an Obsidian vault that's synced via git (e.g. across multiple devices, or with iCloud/Drive on top). Defaults to keeping the most recent block in daily notes.
Brand guidelines, voice, and design system for Clip2Earn — EMEA creator program infrastructure (sub-brand of Bakchich). Use when creating ANY content or UI for Clip2Earn — pitch decks, presentations, blog posts, ad copy, social captions, video scripts, creative briefs, landing pages, email campaigns, web app screens, or component code. Covers both audiences (creators + brands/SaaS founders), two distinct voice calibrations, the full HeroUI-based color system, Chakra Petch/Inter/Fira Code typography, shadows, radii, and iconography. Trigger this skill whenever the user mentions Clip2Earn, clip2earn.money, or asks to write content / build UI for an underground UGC marketplace OR a B2B creator-program infrastructure pitch.
| name | ecommerce-cod-ux |
| description | Use when auditing or optimizing an ecommerce store for COD (Cash on Delivery) markets — MENA, North Africa, Pakistan, SE Asia. Covers checkout UX, trust signals, RTO reduction, COD-to-prepaid conversion, mobile-first design, and RTL architecture. |
| Metric | Data |
|---|---|
| MENA ecommerce 2025 | $135B → $518B by 2032 (21.2% CAGR) |
| COD share of MENA transactions | 76% |
| Mobile share of ecommerce traffic | 68% |
| Smartphone penetration UAE/KSA | 95-97% |
| Mobile cart abandonment | 80.2% |
| Trust in online payments (MENA) | Only 56% trust it — 44% don't |
| Country | COD Preference |
|---|---|
| Egypt | 72% (53% of all transactions) |
| Saudi Arabia | 72% |
| UAE | 51-75% |
| Pakistan | ~60-70% |
| Indonesia | Up to 80% |
| Kuwait | 41% |
| Market | COD RTO | Prepaid RTO |
|---|---|---|
| MENA average | 25-40% | 5-8% |
| UAE (fulfillment data) | 19.6% | 2.9% |
| India D2C | 28-35% (rural: 40-45%) | 4-8% |
| Pakistan | 20-40% | — |
| LATAM | 12-30% | — |
Every RTO doubles shipping cost with zero revenue. The primary causes:
1. Phone number (with inline OTP verification)
2. Full name
3. Address (autocomplete via Google Maps)
4. Area/District (dropdown)
5. Landmark (mandatory text field)
6. Delivery slot (morning / evening dropdown)
7. Payment method (COD selected, prepaid discount banner inline)
Block 80% of prank/bot orders before submission. Keep it inline, never redirect to a new page. Show: "We'll send you a code to confirm your order."
Send automated WhatsApp 12-24h before dispatch with:
Add morning/evening dropdown at checkout. Result: up to 50% reduction in "not available" failures.
| Approach | Conversion Rate |
|---|---|
| Flat discount (e.g. 50 EGP / 5$) | 31-38% COD → prepaid |
| Percentage discount (5-10%) | 18-23% |
| Use flat amount, not percentage — more tangible. |
Place adjacent to "Place Order" button (never footer):
inputMode="numeric" on phone/card fields → correct keyboard auto-opens| Touchpoint | Method | Conversion |
|---|---|---|
| Checkout inline | Flat discount nudge | 31-38% |
| 30-60min post-order | WhatsApp + payment link | 15-30% |
| AI voice call | Verify high-value orders + upsell prepaid | 10-20% |
| 2-3 days post-delivery | WhatsApp loyalty offer next order | 64-71% permanent switch |
When auditing a COD ecommerce store, check:
| Mistake | Fix |
|---|---|
| OTP redirects to new page | Inline OTP in checkout flow |
| Forced account registration | Guest checkout as default |
| Generic address fields | Pin drop + landmark field |
| Trust badges in footer | Move next to Place Order CTA |
| Percentage prepaid discount | Use flat amount (₹50 / 5$ / 50 EGP) |
| COD available for all pin codes | Gate high-RTO zones |
| No pre-shipment confirmation | WhatsApp 12-24h before dispatch |
| No delivery slot | Morning/evening dropdown at checkout |
| Translation-only Arabic | Full RTL architectural mirror |
| 15-field checkout form | Reduce to 6-8 essential fields |
| KPI | Benchmark |
|---|---|
| Checkout abandonment (mobile) | 80.2% global avg — aim for <65% |
| COD RTO (before optimization) | 25-40% |
| COD RTO (after full optimization) | Target <15% |
| COD → prepaid via inline nudge | 31-38% |
| Fake orders blocked by OTP | ~80% |
| RTO reduction via WhatsApp confirm | 30-40% |
| Delivery slot booking impact on RTO | Up to 50% reduction |