Skill UI

Ax is a command-line interface designed to replace curl and parsing scripts for fetching URLs, exploring web pages, and extracting structured data from HTML. It simplifies web scraping with features like outline discovery, selector location, and structured output formats. The tool caches repeated requests and includes safety warnings for untrusted data and credentials. Ideal for developers needing efficient web data interaction without writing complex scripts.

Guides production frontend design and UI/UX review using Better Design MCP, covering components, design systems, accessibility, responsive layouts, motion, and cross-platform interfaces.

This skill detects and recovers text accidentally typed using the Taiwanese Bopomofo keyboard while the input method was stuck in English mode. It maps garbled keystrokes like su3cl3a8 back to Traditional Chinese characters using a decoder script and context analysis. It is designed for Taiwanese developers who forget to switch input methods when prompting AI, ensuring requests are understood without retyping. It excludes technical strings like code or URLs.

Capture a full DevTools-protocol trace of any browser automation run — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets for debugging, auditing, and agent feedback loops.

Prepare an AI outbound phone call end-to-end: research the callee, define the objective and fallback, draft a natural branching script with guardrails, and generate a post-call summary template.

Runs Cantera homogeneous ideal-gas reactors for constant-volume or constant-pressure ignition, computes temperature-based ignition delay, checks conservation, and refines numerical settings with mechanism provenance.

Statistical gate for agent, prompt, model and tool changes: repeated trials, per-case paired comparison against a baseline, trajectory grading, flake detection and blocking exit codes before shipping.

This skill enables users to generate AI audiobooks from manuscripts or course text using the Beatra service. It supports voice cloning and text-to-speech narration. The package is pinned and verified for security. Users must authorize access before use. It works within Claude Code environments.

Classify marketing and GTM decisions into AI-primary, collaborative, or human-primary zones by reversibility, exposure, and frequency, with governance rules and misclassification costs.

Enhance AI-generated portraits, product images, and marketing visuals by fixing plastic skin, malformed hands and faces, repeated textures, and inconsistent lighting. Works with Claude Code, Codex, and OpenClaw via paid Beatra service. Requires explicit user approval for paid operations.

Turn YouTube videos, channels, or playlists into text using the Apify youtube-transcript-scraper Actor. Get plain text, timestamped segments, SRT/VTT captions, and translated transcripts with video metadata for summaries, quotations, and research.

This command executes a single experiment iteration for autoresearch workflows. Users review history, decide changes, edit code, commit, and evaluate results. It follows strategy escalation rules to optimize performance systematically without modifying the evaluator.