AI Skills

Takes an MLS listing/Listing URL and drafts an ad instance directly in TikTok Ads

Viral Creative Rewrite Skill helps advertisers turn a reference ad into a new product ad video instead of starting from scratch. The reference ad provides a proven creative structure, including the opening hook, pacing, shot order, product moments, satisfaction points, and ending rhythm, while the advertiser’s product image provides the source of truth for the new product. After the user invokes the skill, it asks them to choose a flow, select default or custom media, and provide product identity, must-keep selling points, target audience, and campaign goal. The skill supports a no-cost rehearsal with built-in example assets, so advertisers can review the guided flow, rewrite brief, detailed analysis, and example result before using real generation. For real use, the skill first prepares an analysis preview. It explains what can be borrowed from the reference ad, what must not be inherited, how the product image anchors the new video, output settings, and risk controls before any video generation step. Final video generation only happens after the user reviews and confirms the prepared brief. This helps ecommerce and performance advertisers adapt a proven ad structure to their own product while avoiding inherited brands, unsupported claims, captions, UI elements, or unrelated template products. This skill was created through a conversational Claude Code skill workflow and defaults to Claude 4.7 as the host agent. The ZIP includes built-in rehearsal and example video assets; if a standard upload flow enforces a 30 MB file-size limit, the same skill can be registered through the Claude skill path or submitted as a size-adjusted package with large example assets externalized.

When videos are following the top trends on TT, they are much easier to get views/clicks/likes/comments, however, following trend is time-consuming and difficult for self-serve advertisers. Utilize the hot trends on TT (music, video, hashtags) to help 1) new customers to guide how to create hot videos and get started on campaign creation; 2) active existing customers when they facing creative fatigue to refresh videos at ease; 3) inactive existing customers to know where to pick up and what their existing assets can be used at ease. Not only provide the trends and ideas on how, but also generate new videos for users to use directly.

Many TikTok Shop merchants who have gone LIVE struggle to clearly identify the core bottlenecks of their LIVE GMV Max ad campaigns. They cannot tell if the issue lies in insufficient LIVE infrastructure (such as stream duration and frequency), shortcomings in traffic acquisition (such as ad delivery reach and initial stream viewership), or problems in scaling and inventory conversion (such as budget utilization, creative variety, and price competitiveness). This leads to blind optimization efforts and low growth efficiency. This Skill aims to translate complex LIVE GMV Max ad delivery strategies into a clear, actionable diagnostic framework, helping merchants quickly identify issues and obtain targeted optimization recommendations.

A read-only creative-fatigue detector and rotation planner. It compares each running ad's recent engagement against a non-overlapping prior baseline AND against its current same-objective peers, then classifies every ad Retire / Scale / Watch with the size of the drop and the spend at risk. It picks the right engagement metric per objective (conversion ads on CVR / CPA, video-views on cost-per-view, reach on CPM, click ads on CTR), so it never flags a video-view ad for having ~0 clicks by design. The output is a one-screen rotation plan with a "spend at risk" headline; the actual creative swap is routed to manage-creative. Read-only - it never uploads, swaps, or pauses.

Advertisers routinely misread campaign performance because they lack a proper baseline. A CPM of $3 could be excellent for a brand-awareness objective and poor for a conversion campaign in the same account. Existing dashboards show absolute numbers with no within-account context. This skill solves the baseline problem: 1. Fetches real report data via `tt-ads` MCP — no synthetic substitutes, no fabricated numbers. 2. Restricts the benchmark pool to the same advertiser + same objective + same grain — apples-to-apples only. 3. Runs deterministic local computation (P25 / P50 / P75 + percentile rank) via bundled local scripts — Node.js first, Python fallback, no LLM math, fully reproducible. 4. Surfaces conclusions in advertiser-facing language: "CPC is better than 75% of comparable Campaigns" or "CPA is worse than 88% of comparable Campaigns" rather than raw percentile numbers.

Creatiads is a TikTok MCP-first advertising orchestration skill for account inspection, campaign reporting, performance diagnosis, creative analysis, audience optimization, landing page and app-path analysis, budget and bid recommendations, measurement review, GMV Max and TikTok Shop reporting, and guarded campaign operations. The skill initializes and uses the TikTok MCP server as the default data plane for platform access. It follows a structured 8-step analysis workflow: MCP readiness, account information, classification seed collection, user type classification, metric preset selection, formal report data pulling, enrichment, and HTML report generation with audit validation. Creatiads supports common TikTok advertising workflows including daily pulse reports, weekly reports, best and worst performer discovery, vertical classification, creative fatigue analysis, audience breakdowns, activity changelog analysis, review and error diagnosis, cross-account rebuild planning, and Smart+, Spark Ads, Pangle, catalog, shop, Product GMV Max, and GMV Max analysis. The skill is designed for read-first and safety-conscious operations. For create, update, activation, budget, or status changes, it reads the target object first, summarizes the intended payload and risk, and requires explicit user approval before acting. Scripts are compute-only and never make platform API calls directly; the agent performs MCP calls and passes raw data into local scripts for normalization, analysis, HTML generation, and audit.

Reviews real estate ad copy across text, emojis, hashtags, and audio to help identify potential Fair Housing considerations and explains potential risk areas.

Evaluates email campaigns for alignment with industry regulations, deliverability risks, accessibility guidelines, and best practices.