Skill UI

Governs stable domain language in a scoped CONTEXT.md and routes hard-to-reverse decisions to the existing architecture-decision-records skill. Use when terms need repeated explanation, one term has multiple meanings, or unclear language causes module-boundary mistakes.

Designs bilingual Chinese-English motion captions and typography for the informal launch event template, including gradient text, light sweeps, keyword animations, and video-aware layout in HTML/CSS.

Migrates TypeScript projects from the v1 MCP SDK (@modelcontextprotocol/sdk) to v2 client, server and core packages. Runs the official codemod, resolves @mcp-codemod-error markers, and fixes manual breakages in imports, symbols, handlers, auth and transports.

Ten rules that keep coding agents from re-sending bloated context on every call: locate before reading, compute instead of dumping data, bound noisy command output, never re-read, batch parallel calls and answer lean. Cuts token cost ~32% with unchanged pass rates.

This skill enables splitting extracted text into optimized chunks for LLM context windows or RAG ingestion pipelines. It supports configurable chunk sizes, overlap settings, and various chunker types including text, markdown, YAML, and semantic splitting. Users can utilize token-based sizing for specific models or standalone commands for pre-existing text. Ideal for preparing documents for vector stores or summarization tasks.

Extract text from scanned PDFs, images, and photographed pages using OCR backends, language packs, force-OCR, and performance tuning with the Xberg CLI.

Learn how to configure xberg's --format and --content-format flags to optimize document extraction for different consumers. Covers LLM context, RAG indexing, JSON parsing, and token reduction strategies for efficient data pipelines.

Drive native desktop apps through an Automation REPL: bind applications, inspect accessibility trees, type text, click, and capture screenshots while honoring OS permissions and user stop requests.

Audit saved OutreachGenie prospect lists against an outreach flow to identify missing template values, text limits, and incomplete data. Uses read-only MCP snapshots and generates local JSON/Markdown reports without modifying any data or initiating campaigns.

Install, check, restyle, and remove the agy-powerline statusline for Antigravity CLI. Shows model, quotas, reset times, context window, git status, and tokens.

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.

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.