Cyclone-SS

Use this skill whenever Claude is reasoning, analyzing, recommending, or generating content that involves factual claims, metrics, prices, dates, platform behavior, or any "current" information. This is the canonical guard against fabricated certainty. Activate it on every complex operation — ad spend decisions, store edits, market analysis, copy claims, research outputs. If Claude is about to produce a number, date, statistic, or "typically/usually" statement, this skill must govern that output.

Use this skill when the user asks Claude to research competitor ads, look up top-performing ads in a category, analyze spied-on brands, or pull ad library data through GetHookd. Activates whenever Jake mentions "competitor ads," "winning ads," "ad library," "spy on [brand]," or references GetHookd by name.

Use this skill when the user asks Claude to search, read, or organize files in Google Drive — particularly AI Com Academy course transcripts, coach feedback docs, brand research, and shared spreadsheets. Activate when Jake mentions Drive, "my course materials," "coach review," or references a specific Google Doc.

Use this skill when the user asks Claude to generate AI images for ad creatives, product visuals, or brand assets via the Higgsfield API. The Higgsfield API is connected to Claude Code in Jake's Cursor setup. Activate whenever Jake mentions Higgsfield, "generate an image," "make me a visual for [ad/PDP/post]," or needs static creative assets.

Use this skill when the user asks Claude to read, create, update, or search Notion pages and databases. Jake's existing setup includes an "Ad Creation Progress Tracker" database and other DTC workflow trackers. Activate when Jake mentions Notion by name, "my tracker," "update my Notion," or "log this to my workspace."

Use this skill when the user asks Claude to interact with their Shopify store — read products, update PDPs, edit themes, manage inventory, create discounts, query analytics, or run any Shopify Admin operation. This skill documents the 25 dedicated Shopify connector tools, the Shopify AI Toolkit plugin (Claude Code), and the safety rules around write operations.

Use this skill when the user asks Claude to track competitor brands, find similar shops, analyze a niche, run a daily brand radar, find winning products in a category, search active Meta ads, or analyze marketing emails. Activates whenever Jake mentions TrendTrack by name, "tracked brands," "competitor radar," "winning products in [niche]," or similar.

Use this skill on every response. It defines Jake's preferred voice, formatting, and response structure. Apply when generating any output — strategic analysis, copy, code commentary, plans, briefings, or conversational replies. The operator voice is confident, structured, precise, and direct. No fluff, no apologizing, no hedging unless the answer genuinely isn't known.

Use this skill when the user asks Claude to define, build, or refine customer avatars for a brand. Goes beyond demographics into psychographics, beliefs, current behavior, and target behavior. Outputs 2-3 distinct avatars per brand that downstream modes can target with avatar-specific ads, copy, and content.

Use this skill when the user asks Claude to define or refine a brand's core DNA — mission, USP, core promise, voice, visual identity, archetype mapping. Outputs the foundational brand-pack.md that all downstream creative work depends on.

Use this skill when the user asks Claude to map an avatar to Eugene Schwartz's 5 awareness levels, sequence creative across awareness stages, or diagnose why an ad isn't converting (often because it's pitched at the wrong awareness level). Encodes the canonical model from Schwartz's Breakthrough Advertising.

Use this skill when the user asks Claude to identify or refine the Necessary Beliefs that gate purchase for a brand — the 5-7 things a cold prospect must believe before they'll buy. Encodes the Mark Builds Brands methodology. Each belief becomes a creative angle, a PDP section, or a sales-funnel touchpoint.

Use this skill when the user asks Claude to build, refine, or audit a StoryBrand BrandScript for a brand. Enforces the customer-as-hero, brand-as-guide structure across all 7 BrandScript elements. Activates whenever StoryBrand is named or when copy is drifting into brand-as-hero patterns.

Use this skill whenever the user asks Claude to set up, compile, or query a DTC brand brain. Defines the canonical raw/ → wiki/ → outputs/ structure, the six core wiki articles, the cross-linking rules, and the source-citation requirements. Activates on /compile-wiki, /scaffold-brain, and any brand-brain question.

Use this skill when the user runs /health-check or asks for a brain audit. Reviews every wiki article, flags contradictions, finds topics mentioned but never explained, lists claims without sources, and suggests new article candidates. Runs monthly to catch errors before they compound.

Use this skill when running /compile-wiki or when the user asks Claude to update, rebuild, or refresh the brand brain wiki articles. Executes the canonical compile pass — reads every file in raw/, synthesizes the six core wiki articles, updates INDEX.md, and reports back. Pairs with the brand-brain-schema skill.

Use this skill when the user asks Claude to plan, structure, or launch a Meta ad campaign — from pre-launch brief through PAUSED ad creation via Meta Ads MCP. Encodes the AI Com Academy testing framework, ad set structure, and the coach-approval gates that govern Jake's launches.

Use this skill when the user asks Claude to design a creative testing plan, structure a hook/angle/format test, or decide what to test next. Encodes the principle of isolating one variable per test, batch sizes for statistical confidence, and the iteration cycle that compounds learnings.

Use this skill when the user asks Claude to review live Meta campaign performance — Day 3, Day 7, or Day 14 reviews, kill/scale/iterate decisions, or any "how is my campaign doing" question. Encodes the Scale DTC Statistical Analysis Hierarchy and the AI Com Academy decision tree.

Use this skill at the start of any Shopify store build session, ad creative session, or design task that needs brand-consistent output. It defines exactly how Claude ingests a brand pack from brands/<brand>/brand-pack.md and applies it to copy, colors, typography, pricing, and section content. Activates whenever a brand-pack.md is in context or a new build session begins.

Use this skill when a Shopify store or PDP is approaching launch. Runs a structured pre-launch QA across desktop, mobile, checkout, analytics, legal, and brand consistency. Activates when Jake asks "is this ready to launch?" or "run launch QA."

Use this skill when the user asks Claude to build, edit, or audit a product detail page (PDP) on Shopify. Encodes the AI Com locked section order, content rules per section, and StoryBrand-governed copy patterns. Activates whenever a PDP build session starts or a specific section needs work.

Use this skill when the user asks Claude to edit, build, or modify a Shopify Shrine theme — adding sections, updating settings_data.json, editing main-product blocks, or working with templates/product.json. Encodes Shrine's specific file structure and schema patterns so Claude doesn't guess at file locations or section formats.

Use this skill when the user asks Claude to generate ad concept directions, brainstorm new creative angles, or plan a batch of ads before any image generation happens. Concept-first work — produces strategic directions grounded in avatar + offer + awareness level, not generic prompts.

Use this skill when the user has a validated winning ad (or a high-conviction concept) and wants to build a "family" of variants around it for systematic A/B testing. Encodes the principle that you scale by exploiting one winner's pattern across controlled axes, not by generating 10 random ads.

Use this skill when the user asks Claude to generate ad images via Higgsfield. Defines the briefing format that produces brand-consistent outputs (not generic AI slop), the iteration loop for refining toward a winner, and the per-brand aesthetic rules.

Use this skill when the user asks Claude to analyze a winning competitor ad, extract its structural patterns, and translate those patterns into Jake's brand. Outputs a structural breakdown + variant prompts. Strict rule — never copy the competitor's literal copy or claims; only the underlying pattern transfers.

Use this skill when the user asks Claude to generate or refresh a TikTok slideshow hook bank for a brand. Produces 20-25 hooks across pattern interrupt / listicle / curiosity / pain-first / identity / POV / before-after categories, scored on hook strength and brand fit.

Use this skill when the user asks Claude to convert a single hook from the hook bank into a complete TikTok slideshow draft — hook slide + 4-6 body slides + soft CTA final slide, with image direction per slide and TikTok-native text styling.

Use when building an ad family, scaling a winning ad, or applying Motion Methodology to generate creative variants from a single concept.

Configure AWS Bedrock authentication for Claude Code in Replit environments. Use when setting up Claude Code with AWS Bedrock, troubleshooting authentication issues, or when the user mentions Bedrock, AWS credentials, Replit, or Claude Code setup.

Use when the user wants to queue a ComfyUI workflow, check generation status, or interact with the local ComfyUI instance.

Use when the user asks to create a new n8n workflow, scaffold a workflow template, or stub out automation logic.

Use when the user wants to download or export a workflow from n8n cloud to the local repo.

Use when the user uploads an image and wants structured JSON output for AI image recreation or prompt engineering.

Use when the user wants to import a workflow JSON file into the local n8n instance at localhost:5678.

Use when converting structured JSON (from image-to-json) into ComfyUI-ready prompts and workflow settings.

Use when the user asks to see, list, or overview all n8n workflows in the repository.

Use when the user wants to validate an n8n workflow for health, credentials, or issues before importing.

Sequential 5-sub-agent pipeline for ad creative production — Competitor Researcher → Creative Brief Writer → Hook Generator → Ad Copy Writer → Performance Reporter. Use when the user says "run the marketing team", "build a brief", "generate hooks", "write ad variations", or wants a full creative production cycle from competitive scan through copy variants.