Explore skills

Full multi-platform paid advertising audit with parallel subagent delegation. It analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts, generating a health score per platform and an aggregate score.

Comprehensive paid advertising audit and optimization for any business type. It includes multi-platform audits (Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, Microsoft Ads), deep analysis, conversion tracking, creative assessment, budget and bidding optimization, and compliance verification, with industry detection for SaaS and e-commerce.

Reads and implements a story file by loading the full context (story, GDD requirements, ADR guidelines, control manifest). It routes to the correct programmer agent, implements code and tests, and confirms acceptance criteria. This core implementation skill runs after /story-readiness and before /code-review and /story-done.

Audit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, hallucinated skill invocations, per-project skill stats, or token cost of installed skill metadata. Triggers on "what skills don't I use?", "clean up my skills", "why didn't this skill work?", "audit skills". Runs locally; reads ~/.claude session JSONL logs. No network calls.

Expert guide for crafting high-quality video prompts for Ozor.ai, the AI video generation platform. Use this skill whenever the user mentions Ozor, wants to create a launch video, product demo, feature announcement, explainer video, social ad, release notes video, investor update, tutorial, or any marketing video. Also trigger when the user asks for help writing video prompts, improving video outp

Browse, inspect, re-export, embed, or iterate on videos that already exist in the user's Ozor.ai account. Use this skill whenever the user wants to work with past or in-progress Ozor videos rather than create a new one — e.g. 'list my Ozor videos', 'show my recent videos', 'what's the status of my last video', 'get the embed code for that video', 'download my last Ozor video', 'share link for the

Diagnose why website traffic changed. Use when the user asks "why did traffic drop/spike", investigates an anomaly, or wants to separate tracking regressions from real behaviour changes. Walks a hypothesis tree (measurement → time-shape → channel → cohort → content), recognises common fingerprints (bot spike, tracking regression, deploy-correlated drop, SEO decay, campaign ramp), and applies sampl

Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust signals, form optimization, and conversion rate potential.

Create short mixed-cut videos from YouTube clips with automated analysis, clipping, and professional subtitle processing.

Judge whether traffic is actually valuable and whether funnel drop-off is real or expected. Use when comparing marketing channels, reading a conversion funnel, or deciding where to invest. Covers volume × engagement × conversion as a matrix, vanity-traffic detection, expected step drop-off by funnel type, cohort decomposition, and mix-shift (Simpson's paradox) handling.

Audit which MCP server tools your Claude Code sessions actually invoke. Use when the user wants to find dead MCP servers (configured but never called), hallucinated MCP tool calls, or per-project MCP usage. Triggers on "which MCP servers don't I use?", "clean up MCP config", "remove unused MCP servers", "audit MCP tools". Runs locally; reads ~/.claude session JSONL logs and ~/.claude.json. No netw

The spine of analytics investigation. Use whenever interpreting analytics numbers, answering "why did X change", reading funnels, comparing cohorts, or presenting findings. Teaches a five-step method (load profile, frame the question, build a MECE hypothesis tree, triangulate, present with Pyramid Principle), how to separate signal from noise, and how to spot Simpson's paradox before it misleads y