Skill UI

This skill ensures AI models generate complete, unabridged code and files without placeholders, TODOs, or skipped sections. It enforces strict completeness for deliverables like full implementations or exhaustive lists. It prevents shortcuts like '...' or descriptions instead of code, ensuring every requested item is fully realized within token limits.

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.

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.

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.

Generate practical shot lists and one to four storyboard key-frame images from a script, scene, or ad brief via the paid Beatra hosted service, directly inside Claude Code, Codex, or OpenClaw.

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.

Shared vocabulary and principles for designing deep modules with small interfaces, clean seams, and testable, AI-navigable codebases.

Roll out Claude Code to a team or organization: lint shared and managed settings, inventory MCP servers and plugins, audit layered CLAUDE.md, and track adoption with four deterministic scripts.

Analyzes Claude Code and Codex usage logs to surface cost drivers such as low cache hit rates, unpaid cache writes, top-tier sub-agents, reasoning share, and bloated sessions, with evidence and what-if savings to help cut AI coding spend.

This tool provides a unified cost view for AI agents like Claude Code, Codex, and Grok. It reads local logs to calculate spend, token usage, and cache hit ratios per provider and model. It flags unpriced models and supports filtering by time range, project, and provider. Output can be JSON or Markdown. All data stays local, ensuring privacy. Ideal for auditing AI usage costs and comparing provider pricing.