All skills

A reference skill explaining how TestDriver caches AI-vision-found UI elements for fast, deterministic test replays.

A reference skill teaching Claude how to verify screen state in plain English with TestDriver's AI assert().

A reference skill for using TestDriver's ai() method to drive UI test steps with plain-English instructions.

Audits and rescales a 2D character/prop baseline image with transparent action margin before motion generation.

Analyzes videos, frame sequences, spritesheets and Spine assets to build a reusable 2D motion knowledge base inside your project.

A consulting-grade framework for building competitor comparisons, market positioning decks and investment memos in any industry.

Delegates multi-step research to Google's Gemini Deep Research agent and returns detailed, cited reports from the command line.

Scans your current folder and turns PDFs, docs, or a source repo into a fully cross-linked Obsidian StudyVault with dashboards, concept notes, and practice questions.

A quiz tutor that reads your Obsidian StudyVault notes, asks four hint-free multiple-choice questions, and logs per-concept accuracy and error notes automatically.

Turns any repository into a live, human-legible architecture graph and drives that map during code walkthroughs.

Turns a skill idea into a complete, shippable skill folder — instructions, metadata, artwork, README wiring, and validation.

A sub-skill that turns a Balanced Coupling modularity analysis into matching Markdown and HTML review documents.

A severity-ranked code review skill that scans WordPress themes and plugins for performance anti-patterns.

PHPUnit and Playwright testing patterns, commands, and debugging flags for the WordPress ActivityPub plugin.

Autonomously scans a codebase for personal data, runs an all-99-article GDPR gap analysis, and generates pre-filled DPA, ROPA and operational compliance documents.

A routing skill that makes Claude use trace-mcp's semantic code tools instead of Read/Grep/Glob, cutting tokens while improving accuracy.

Forces Claude to use trace-mcp's apply_codemod for any edit pattern repeated 2+ times instead of firing off repetitive Edit calls.

A skill that turns your CLAUDE.md into AGENTS.md and wraps OpenAI Codex CLI calls so Claude Code and Codex work together.

Wires Claude Code hooks so sessions, turns, and every tool call are logged as hierarchical Braintrust traces.

A short rule set that tells Claude to delegate implementation work to sub-agents so the main conversation keeps its context.