Types

Types is a Data skill for Claude Code, published by Piebald-AI in splitrail.

217 stars25 forkson Piebald-AI/splitrailAdded 2026/09/04Repository updated 2026/09/03

agenticanalyzerantigravity-cliblazing-fastccusageclaude-codeclinecodexgcusagekilo-codeopencodepi-agentpiebaldqwenqwen-coderavishingrustsplitrailusagezoo-code

Install in seconds

Install Types

Copy Types into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Piebald-AI/splitrail/tree/main/.claude/skills/types ~/.claude/skills/types

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Piebald-AI/splitrail.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/types/SKILL.md in Piebald-AI/splitrail
Installs to: ~/.claude/skills/types
Collection: One of 6 skills cataloged from this repository
Category: Data — 729 skills

What Types does

Types is a reference for Splitrail's core data structures. Use it when working with ConversationMessage, Stats, DailyStats, hashing, or daily aggregation.

Types is cataloged under Data on DirSkills. Types comes from a repository tagged agentic, analyzer, antigravity-cli, blazing-fast and ccusage.

Documentation

README

Excerpt

Key Types

Read src/types.rs for full definitions.

Core Types

ConversationMessage - Normalized message format across all analyzers. Contains application source, timestamp, hashes for deduplication, model info, token/cost stats, and role.
Stats - Comprehensive usage metrics for a single message including token counts, costs, file operations, todo tracking, and composition stats by file type.
DailyStats - Pre-aggregated stats per date with message counts, conversation counts, model breakdown, and embedded Stats.
Application - Enum identifying which AI coding tool a message came from.
MessageRole - User or Assistant.

Hashing Strategy

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Types

What else does Piebald-AI publish alongside Types?
Types is one of 6 skills that DirSkills catalogs from Piebald-AI/splitrail, the repository it ships in. Its siblings there include New Analyzer, Performance and Pricing. Each one is a separate skill with its own page in this directory, installs the same way Types does, and is maintained by Piebald-AI in that same repository. The rest of the collection is listed on the Piebald-AI/splitrail page.
How does Types compare to other Data skills?
Types ranks #661 by stars among the 729 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Types against them. Open each page to compare what they document and how they install.