Claude Skills by alegauss

The complete catalogue of Claude Code Tray's own CLI flags — every preview, capture, headless read-out and fixture the .exe exposes, with what each one is for. Use when you need a flag that AGENTS.md's short list does not name, when you are unsure which entry point shows a surface, or when you add a flag and need to know where it is written down.

The per-file map of Claude Code Tray's own sources — every file under src/, one row each, with what it is responsible for and the rules its type carries. Use when you need to know which file owns a behaviour, where a new file goes, or what a type already does before writing a second reader of the same thing.

Build and visually verify the Claude Code Tray window by launching it and capturing a screenshot. Use whenever a change touches MainWindow, any of its pages (SettingsPage / StatisticsPage / ContextPage) or any windowed UI, before claiming the layout works.

Claude Code Tray's own shipping discipline — the one-task-one-commit rule, the user-facing-surface gate (README, the site/ copy modules, lang/*.json) a shipped feature must pass, and how a release is cut. The roadmap/changelog/rationale write path itself is NOT here: roadkeep owns it, and its own skill says which command to call. Use whenever a task is finished, before committing, or when a shipped feature might be user-visible.