← ClaudeAtlas

kelly-adslisted

Personal App-in-Skill ad-campaign command desk (投放指挥台) for a cross-border e-commerce seller running Amazon Ads, Meta (FB/IG), TikTok Ads, and Google Ads. Use when the user invokes $kelly-ads or /kelly-ads, or asks about 投放, ad campaigns, ad spend, ACOS, ROAS, Amazon Ads, TikTok ads, Meta ads, Google Ads, search terms, negative keywords, bid adjustment, budget pacing, CPC spikes, rejected ads, ad anomaly detection, 广告优化, or reviewing agent-proposed adjustment cards (negative keyword, bid down/up, pause target, budget shift, creative refresh).
mr-kelly/skills · ★ 3 · AI & Automation · score 74
Install: claude install-skill mr-kelly/skills
# Kelly Ads ## Overview Use this skill as Kelly's ad-campaign command desk. It aggregates spend and performance from Amazon Ads, Meta (FB/IG), TikTok Ads, and Google Ads into one file-backed App-in-Skill board (spend, impressions, clicks, conversions, revenue, ROAS, ACOS per campaign), detects anomalies deterministically (ACOS above target for N days, budget exhausted before day end, high-spend zero-conversion search terms/creatives, sudden CPC spikes, paused/rejected campaigns), and turns them into agent-proposed adjustment cards with evidence and expected impact. The human approves; the agent executes approved adjustments outside the app via the platform APIs. Default interaction mode: App UI. Unless the user explicitly asks for chat-only handling, check onboarding/config, refresh the ads snapshot with the ingest/check scripts, start/reuse the local app with `app/start.sh`, and give the actual local URL. Use chat-only mode only when the user says "纯聊天", "chat only", "不要打开 UI", or similar; then present numbered adjustment cards (`Adjustment #1`) and take verdicts in chat. ## App UI Screenshots <table> <tr> <td width="50%"><img src="assets/screenshots/overview.webp" alt="Kelly Ads overview"></td> <td width="50%"><img src="assets/screenshots/campaigns.webp" alt="Kelly Ads campaigns"></td> </tr> <tr> <td><strong>Overview</strong><br>Cross-platform ads board: blended ROAS/ACOS vs target, per-platform cards, spend vs revenue bars, and worst offenders.</td>