create-adapter

Build and debug chat-history adapters with caching, incremental parsing, and watch/FD management.

1.0k|79|Updated Dec 26, 2025
One-click install
npx skills add https://github.com/marcus/sidecar --skill create-adapter
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-adapter
Source: https://github.com/marcus/sidecar/tree/main/.claude/skills/create-adapter
Command: npx skills add https://github.com/marcus/sidecar --skill create-adapter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Build and debug adapters that import AI chat history from multiple tools, ensuring a consistent interface and robust data handling across sources.

Core Features & Use Cases

  • Define the adapter.Adapter interface and standardize caching, incremental parsing, and watch/FD management for chat-history adapters.
  • Reference the common adapters (claudecode, codex, cursor) to guide new implementations and ensure compatibility.
  • Use cases include creating new adapters, modifying behavior, and diagnosing performance issues across tools like Claude Code, Cursor, Warp, and Codex.

Quick Start

Implement a new adapter and validate it against the reference implementations.

Frequently Asked Questions about create-adapter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an adapter to import AI chat history from different tools?

To create an adapter for importing AI chat history, implement the standardized adapter.Adapter interface and validate your implementation against reference adapters like claudecode, codex, and cursor.

What is the standard interface for building chat-history adapters?

The standard interface for chat-history adapters requires satisfying rigorous contracts including ID, Name, Icon, Detect, Capabilities, Sessions, Messages, Usage, and Watch, ensuring consistent behavior across different data sources.

How do I debug performance issues with incremental parsing in chat history adapters?

Debug performance issues in chat history adapters by diagnosing incremental parsing, interface consistency, caching mechanisms, and watch/FD management to ensure they meet established performance benchmarks.

Can I use existing adapters as a reference to add support for a new AI tool?

You can reference common adapters such as claudecode, codex, and cursor to guide new implementations, ensuring your new adapter maintains compatibility and consistent data handling across sources.

Why does my chat history adapter experience file descriptor leaks during watching?

File descriptor leaks during watching occur when watch/FD management is not properly handled within the adapter lifecycle, requiring diagnosis of the watch implementation against performance benchmarks.