eddiebelaval

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.

Expert guide for writing comprehensive API documentation including OpenAPI specs, endpoint references, authentication guides, and code examples. Use when documenting APIs, creating developer portals, or improving API discoverability.

Expert iOS App Store submission and approval system. 9 specialized agents providing senior App Review Team-level expertise across compliance, design, privacy, monetization, metadata, technical requirements, timing, rejection recovery, and learning. Triggers on keywords like app store, iOS submission, apple review, app rejection, aso, privacy manifest, privacy labels, ATT, iap, in-app purchase, subscription, storekit, review guidelines, HIG, testflight, app store connect.

Execute a feature from description to committed code using three parallel sub-agents: Architect, Builder, and Validator.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

The ultimate landing page builder. Through a conversational interview, autonomously produces a complete, deployable Next.js landing page with TypeScript, Tailwind CSS, SEO metadata, JSON-LD structured data, and conversion-optimized copy. Consolidates intelligence from landing-page-designer, copywriting, page-cro, form-cro, schema-markup, seo-audit, layout-designer, ab-test-designer, and more. Use when the user says "build a landing page," "create a landing page," "I need a landing page for," or "build me a page for [product]." For optimizing an EXISTING landing page, use landing-page-optimizer or page-cro instead.

When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' or 'competitive landing pages.' Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. Emphasizes deep research, modular content architecture, and varied section types beyond feature tables.

Automated content publishing pipeline for ID8Labs. Generates essays in Eddie's voice, publishes to id8labs.app, and distributes to social media (X, LinkedIn).

First-run setup wizard that personalizes the Claude Code OS to the user's identity, business type, and LLC purpose

Run a structured, read-only codebase audit using parallel agents. Surfaces dead code, security gaps, wiring issues, type safety problems, and UI shells. Produces a prioritized fix plan. Use for ship-readiness checks, pre-launch reviews, or periodic hygiene sweeps.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Expert guide for building CI/CD pipelines with GitHub Actions, Vercel, and other platforms. Use when automating builds, tests, deployments, or release workflows.

Expert guide for building command-line interfaces with Node.js (Commander, Inquirer, Ora) or Python (Click, Typer, Rich). Use when creating CLI tools, terminal UX, argument parsing, or interactive prompts.

Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.

Expert guide for managing application configuration including environment variables, config files, secrets management, and multi-environment setups. Use when handling .env files, config validation, or configuration architecture.

Automated content publishing pipeline for ID8Labs. Generates essays in the user's voice, publishes to your-domain.app, and distributes to social media (X, LinkedIn).

The hard grader for 90 Day production writing. Adversarial, decoupled from generation — its job is to REJECT, not to help. Runs a deterministic slop gate, then format conformance against the golden set, then the 105-pt rubric, then an adversarial pass. Use before any beat sheet, outline, INTV set, KO sheet, or director roadmap goes to an EP. Triggers on "eval", "grade this", "score it", "is this EP ready", "hard eval", "does this read like AI", "run the gate", "check against golden set".

The red-pen editor for 90 Day production writing. Takes findings from 90day-eval and fixes them in Eddie's voice, editing the existing draft rather than rewriting it. Never scores its own output — hands back to the grader. Use after an eval returns blocking findings, or when a draft needs a voice pass. Triggers on "red pen", "edit this", "fix the notes", "apply the eval findings", "voice pass", "make it sound like me", "clean it up".

Generates production paperwork from existing story materials — post-handoff packages, production kick-off sheets, and story transfer documents. Uses established templates and populates them from beat sheets, scene breakdowns, and cast information. Use when creating handoff docs, kick-off sheets, story transfers, or any production documentation that follows a standard template. Triggers on "handoff", "kick-off sheet", "story transfer", "production docs", "wrap docs", "post-production package", "prep the paperwork", "get this ready for handoff", "transfer document", "kick off", or when transitioning between production phases.

Diagnoses and surgically trims bloated 90 Day Fiancé scenes using the signal-to-noise reduction workflow. Identifies bloat type, tests scene function, performs three-level surgical cuts, and delivers a tighter version. Use when scenes run over 800 words, feel repetitive or sluggish, have too much process detail, or need trimming before EP review. Triggers on "scene refinement", "trim this", "too long", "bloated", "cut the undergrowth", "signal to noise", "tighten this up", "needs trimming", "over word count", or when any scene exceeds the 600-800 word target.

Quality filter that catches AI-sounding language and enforces TLC voice standards before content reaches EPs or network. Use this skill whenever reviewing beat sheets, scene expansions, or any production writing for voice compliance. Triggers on "voice check", "quality gate", "EP ready", "sounds too AI", "too verbose", "slop check", "voice pass", "clean this up", "network ready", "before we send", or any request to review/polish production content before submission. Also use proactively as a final pass after 90day-story-development or 90day-scene-refinement completes work.