Shadowtek team toolkit: SEO auditing, ads management, brand intelligence, email marketing (EDM), image generation, UI/UX design, coding standards, and project scaffolding
You are the Shadowtek Brand Agent. Your job is to run a structured brand intake, conduct
You are the Shadowtek Brand Architect. Your job is to run a structured brand guidelines intake and produce a professional, self-contained HTML brand guide deliverable plus a `brand.json` for the build pipeline.
You are a Google Ads campaign builder. Your job is to read a brand-agent output and
You are the Shadowtek Build Orchestrator. You receive project context from the intake phase and execute a multi-phase build pipeline using parallel agent teams.
Audit all zones in a Cloudflare account against the Shadowtek security standard. Produces a per-zone report and account-wide score, then offers to fix any failing zones.
Budget and bidding specialist. Audits budget allocation, bidding strategies, learning phase health, audience targeting, and campaign structure across LinkedIn, TikTok, and Microsoft.
Compliance and performance specialist. Audits regulatory compliance, ad policies, privacy requirements, campaign settings, and performance benchmarks across LinkedIn, TikTok, and Microsoft.
Creative quality specialist. Audits ad creative across LinkedIn, TikTok, and Microsoft for format diversity, fatigue signals, platform-native content, and spec compliance.
Google Ads audit specialist. Analyzes conversion tracking, wasted spend, account structure, keywords, Quality Score, ad assets, PMax, bidding, and settings.
Meta Ads audit specialist. Analyzes Pixel/CAPI health, EMQ scores, creative diversity and fatigue, account structure, learning phase, audience targeting, and Advantage+ campaigns.
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts. Generates health score per platform and aggregate score. Use when user says "audit", "full ad check", "analyze my ads", "account health check", or "PPC audit".
Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy appropriateness, scaling readiness, and identifies campaigns to kill or scale. Uses 70/20/10 rule, 3x Kill Rule, and 20% scaling rule. Use when user says "budget allocation", "bidding strategy", "ad spend", "ROAS target", "media budget", or "scaling".
Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative strategy, keyword targeting, estimated spend, and identifies competitive gaps and opportunities. Use when user says "competitor ads", "ad spy", "competitive analysis", "competitor PPC", or "ad intelligence".
Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates platform-native compliance, and provides production priorities. Use when user says "creative audit", "ad creative", "creative fatigue", "ad copy", "ad design", or "creative review".
Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74 checks across conversion tracking, wasted spend, account structure, keywords, ads, and settings. Use when user says "Google Ads", "Google PPC", "search ads", "PMax", "Performance Max", or "Google campaign".
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Private Claude Code plugin for the Shadowtek team. Provides skills, agents, commands, rules, and hooks for web design, hosting, and ads projects.
View Build Pipeline Diagram → Interactive reference —
/new-projectmain flow + all standalone commands. Download button included for sharing.
Requirement: GitHub access to the private shadowtek/shadowtek-claude-plugin repo.
claude plugin marketplace add shadowtek/shadowtek-claude-plugin
Registers the Shadowtek marketplace across all Claude Code interfaces — CLI, VS Code, and Desktop app.
claude plugin install shadowtek@shadowtek-claude-plugin/plugins in the Claude Code chat panel → find "shadowtek" → Install~/.claude/plugins/shadowtek/setup.sh
Installs everything-claude-code, which shadowtek depends on for agents and extended tooling.
claude plugins update shadowtekAdd to ~/.claude/settings.json to skip Step 1:
{
"extraKnownMarketplaces": {
"shadowtek-plugins": {
"source": {
"source": "github",
"repo": "shadowtek/shadowtek-claude-plugin"
}
}
}
}
Commands are designed to chain. Below are the standard flows and the preferred run order.
For Shadowtek brand/design/build engagements.
/new-project
↓
/brand-agent or /brand-guidelines (if brand work needed)
↓
/build-orchestrator
↓
/pre-flight
↓
/deploy
↓
/publish-brand (optional — publish deliverables to brand.shadowtek.com.au)
↓
/handoff (optional — engineering handoff doc)
/new-project auto-routes when SiteLaunch is selected at Step 0.
/new-project → /sitelaunch-build
↓
/pre-flight
↓
/deploy
Produces a ready-to-import Google Ads Editor CSV using brand data.
/brand-agent ← must run first to produce brand.json
↓
/brand-to-ads
New account / client onboarding (all zones at once):
/cf-harden-bulk
↓
/cf-overview ← verify everything scored correctly
Single zone setup or override:
/cf-harden
↓
/cf-audit ← confirm pass/fail per check
Audit only (no changes):
/cf-overview ← account-wide score, surfaces failing zones
↓
/cf-audit ← drill into a specific zone
For new city/niche deployments in the directory-network monorepo. Standalone — no dependencies.
/new-directory
/new-project — Project IntakeStructured intake that routes to the right build track. Always the starting point for any new client project.
/new-project
SHADOWTEK-AGENTS.md, STACK.md, and CONVENTIONS.md before making stack decisions/sitelaunch-build/brand-agent — Brand Intelligence AgentThree-tier brand deliverable system. Produces self-contained HTML files for client handoff.
/brand-agent
| Tier | Deliverables | Best for |
|---|---|---|
| Tier 1 — Brand Identity | Brand Guide HTML + brand.json | New clients, visual rebrand |
| Tier 2 — Brand + Positioning | + Audience Summary HTML | Strategy-focused engagements |
| Tier 3 — Full Brand Agent | + Marketing Strategy HTML | Full brand + go-to-market |
/new-project — skips already-known data/brand-guidelines — Standalone Brand GuideProduces a brand guide HTML + brand.json without the full brand-agent intake. Faster for clients with an existing brand direction.
/brand-guidelines
/new-project or /build-orchestratorbrand.json for use by /build-orchestrator and /brand-to-ads/brand-to-ads — Brand to Google Ads CSVnpx claudepluginhub shadowtek-dev/shadowtek-claude-pluginMJML-based email/EDM production system for Shadowtek client work. Three-skill chain: edm-new-project (brand intake + sequence scoping) → branded-edm-builder (MJML design system, brand kit tokens, R2/Pages hosting) → email-preflight (18-check QA at 4 viewports). email-components bundled — no separate clone needed. Shadowtek CF infrastructure pre-provisioned.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.