claude-tabs-debugging — for Claude Code claude-tabs-debugging, claude-tabs, community, for Claude Code, ide skills, Start with, event = "perf.span", sessionId, module, taps.jsonl

v1.0.0

このスキルについて

適した場面: Ideal for AI agents that need claude tabs debugging. ローカライズされた概要: Desktop app for managing multiple Claude Code CLI sessions in tabs # Claude Tabs Debugging Treat Claude Code as a moving target.

機能

Claude Tabs Debugging
Treat Claude Code as a moving target. Verify behavior from local Claude Code source before
Check C:\Users\jorda\PycharmProjects\claude code\src first for Claude Code behavior.
If behavior is still unclear, ask the user to reproduce in the debug build and inspect the logs
Debug observability is debug-build only. If a bug needs logs, reproduce it in the debug build.

# 主なトピック

gunba gunba
[1]
[0]
更新日: 4/9/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

適した場面: Ideal for AI agents that need claude tabs debugging. ローカライズされた概要: Desktop app for managing multiple Claude Code CLI sessions in tabs # Claude Tabs Debugging Treat Claude Code as a moving target.

このスキルを使用する理由

推奨ポイント: claude-tabs-debugging helps agents claude tabs debugging. Desktop app for managing multiple Claude Code CLI sessions in tabs # Claude Tabs Debugging Treat Claude Code as a moving target.

おすすめ

適した場面: Ideal for AI agents that need claude tabs debugging.

実現可能なユースケース for claude-tabs-debugging

ユースケース: Claude Tabs Debugging
ユースケース: Treat Claude Code as a moving target. Verify behavior from local Claude Code source before
ユースケース: Check C:\Users\jorda\PycharmProjects\claude code\src first for Claude Code behavior

! セキュリティと制限

  • 制約事項: Debug observability is debug-build only. If a bug needs logs, reproduce it in the debug build.
  • 制約事項: Do not ask for smaller logs by default. Filter the noisy logs instead of discarding them.
  • 制約事項: Log order Debug observability is debug-build only

About The Source

The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Labs デモ

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ とインストール手順

These questions and steps mirror the structured data on this page for better search understanding.

? よくある質問

claude-tabs-debugging とは何ですか?

適した場面: Ideal for AI agents that need claude tabs debugging. ローカライズされた概要: Desktop app for managing multiple Claude Code CLI sessions in tabs # Claude Tabs Debugging Treat Claude Code as a moving target.

claude-tabs-debugging はどうやって導入しますか?

次のコマンドを実行してください: npx killer-skills add gunba/claude-tabs。Cursor、Windsurf、VS Code、Claude Code など19以上のIDEで使えます。

claude-tabs-debugging の主な用途は?

主な用途は次のとおりです: ユースケース: Claude Tabs Debugging, ユースケース: Treat Claude Code as a moving target. Verify behavior from local Claude Code source before, ユースケース: Check C:\Users\jorda\PycharmProjects\claude code\src first for Claude Code behavior。

claude-tabs-debugging に対応するIDEは?

このスキルは Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer に対応しています。統一された導入には Killer-Skills CLI を使えます。

claude-tabs-debugging に制限はありますか?

制約事項: Debug observability is debug-build only. If a bug needs logs, reproduce it in the debug build.. 制約事項: Do not ask for smaller logs by default. Filter the noisy logs instead of discarding them.. 制約事項: Log order Debug observability is debug-build only.

このスキルの導入方法

  1. 1. ターミナルを開く

    プロジェクトディレクトリでターミナルまたはコマンドラインを開きます。

  2. 2. インストールコマンドを実行

    npx killer-skills add gunba/claude-tabs を実行してください。CLI がIDEまたはエージェントを自動検出し、スキルを設定します。

  3. 3. スキルを使い始める

    このスキルはすぐに有効になります。現在のプロジェクトで claude-tabs-debugging をすぐ使えます。

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

claude-tabs-debugging

Install claude-tabs-debugging, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

SKILL.md
Readonly
Upstream Repository Material
The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Claude Tabs Debugging

Treat Claude Code as a moving target. Verify behavior from local Claude Code source before assuming how it works.

Source of truth

  • Check C:\Users\jorda\PycharmProjects\claude_code\src first for Claude Code behavior.
  • If behavior is still unclear, ask the user to reproduce in the debug build and inspect the logs instead of guessing.

Log order

Debug observability is debug-build only. If a bug needs logs, reproduce it in the debug build.

Primary files:

  • %LOCALAPPDATA%\claude-tabs\observability\app.jsonl
  • %LOCALAPPDATA%\claude-tabs\sessions\<sessionId>\observability.jsonl
  • %LOCALAPPDATA%\claude-tabs\sessions\<sessionId>\taps.jsonl
  • %LOCALAPPDATA%\claude-tabs\sessions\<sessionId>\traffic.jsonl

Start with observability.jsonl. Use it as the correlated timeline. Read WARN, ERR, and event = "perf.span" first, then narrow by sessionId, module, event, and data.

Use:

powershell
1lnav "$env:LOCALAPPDATA\claude-tabs\observability\app.jsonl" "$env:LOCALAPPDATA\claude-tabs\sessions\<sessionId>\observability.jsonl"

to align app-wide and session-specific timestamps.

File roles

  • Use taps.jsonl to answer "what did Claude Code emit?"
  • Use traffic.jsonl to answer "what hit the proxy/network?"
  • When terminal behavior looks wrong, inspect terminal, PTY, and session spawn events before assuming a Claude Code regression.

Debug markers

The debug build exposes marker buttons in the Debug Panel. They emit event = "debug.marker" with data.markerId, data.markerIndex, and data.targetSessionId. Markers may land in either the app log or the target session log, so check both before concluding they are missing.

Working style

  • Do not ask for smaller logs by default. Filter the noisy logs instead of discarding them.
  • Prefer concrete dates, session IDs, and exact event names in debugging writeups.

関連スキル

Looking for an alternative to claude-tabs-debugging or another community skill for your workflow? Explore these related open-source skills.

すべて表示

openclaw-release-maintainer

Logo of openclaw
openclaw

ローカライズされた概要: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

333.8k
0
AI

widget-generator

Logo of f
f

ローカライズされた概要: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat. It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

149.6k
0
AI

flags

Logo of vercel
vercel

ローカライズされた概要: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
ブラウザ

pr-review

Logo of pytorch
pytorch

ローカライズされた概要: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review. It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
開発者