mcp
Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.
Guide for Splitrail's terminal UI and file watching. Use when modifying the TUI, stats display, or real-time update logic.
Claude Code
$ npx -y skills add Piebald-AI/splitrail --skill tui --agent claude-code
Codex
$ npx skills add Piebald-AI/splitrail --skill tui -a codex -y
Cursor
$ npx skills add Piebald-AI/splitrail --skill tui -a cursor -y
Gemini CLI
$ npx skills add Piebald-AI/splitrail --skill tui -a gemini-cli -y
GitHub Copilot
$ npx skills add Piebald-AI/splitrail --skill tui -a github-copilot -y
OpenCode
$ npx skills add Piebald-AI/splitrail --skill tui -a opencode -y
Windsurf
$ npx skills add Piebald-AI/splitrail --skill tui -a windsurf -y
name: tui description: Guide for Splitrail's terminal UI and file watching. Use when modifying the TUI, stats display, or real-time update logic.
Splitrail provides a terminal UI with live updates when analyzer data files change.
Watches analyzer data directories for changes using the `notify` crate. Triggers incremental re-parsing on file changes and updates TUI via channels.
Coordinates real-time updates: background file watching, auto-upload to Splitrail Cloud (if configured), and stats updates to TUI via `tokio::sync::watch`.
Terminal interface using `ratatui`:
Implement `get_watch_directories()` in your analyzer to return root directories for file watching. See `src/analyzer.rs` for the trait definition.
Splitrail is a fast, cross-platform, real-time token usage tracker and cost monitor for: Gemini CLI (and Qwen Code) Claude Code Codex CLI Cline / Roo Code / Zoo Code / Kilo Code (VS Code extension + CLI) GitHub Copilot (VS Code) GitHub Copilot CLI OpenCode Pi
Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.
Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline,…
Performance optimization guidelines for Splitrail. Use when optimizing parsing, reducing memory usage, or improving throughput.
Guide for updating model pricing in Splitrail. Use when adding new AI model costs or updating existing pricing data.
Reference for Splitrail's core data types. Use when working with ConversationMessage, Stats, DailyStats, or other type…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.