ClaudSkills / Engineering / observability

Debug Distributed Hang

Q: What is a Claude Code skill and how does the Debug Distributed Hang skill fit in?

A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Debug Distributed Hang is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Engineering category. Learn more at https://claudskills.com/learn/what-is-skill-md/.

Category: Engineering · Sub-category: observability · Last updated: 2026-05-29

lang:python type:debug

Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP). Covers identifying hang locations via py-spy/watchdog/cuda coredump, per-rank logging to find state divergence, binary-search methodology for locating the first diverge point, and fix patterns. Use when a multi-GPU SGLang run hangs, freezes, or times out during collective operations.

What this skill does

Debug Distributed Hang is a community-contributed Claude Code skill in the observability sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/debug-distributed-hang/ and loads when your prompt matches the skill's trigger.

When to invoke it: Use when a multi-GPU SGLang run hangs, freezes, or times out during collective operations.

Who uses this skill

The Debug Distributed Hang Claude Code skill is built for software engineers, backend developers, full-stack teams, and technical leads building and maintaining production systems. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 97,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).

How to install

Free

Manual install (2 steps)

mkdir -p ~/.claude/skills/debug-distributed-hang
curl -L https://claudskills.com/skills/debug-distributed-hang/SKILL.md \
  -o ~/.claude/skills/debug-distributed-hang/SKILL.md

Or just download SKILL.md directly and drop it into ~/.claude/skills/debug-distributed-hang/. Claude Code auto-discovers it on next session.

Skills live at ~/.claude/skills/debug-distributed-hang/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\debug-distributed-hang\SKILL.md on Windows. See the full install guide for step-by-step instructions.

📱 Install from your phone or desktop Telegram

Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →

Pro

One-click install via the desktop app

The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.

Pro

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

See pricing → Download desktop app

Frequently asked questions

How do I install the Debug Distributed Hang Claude Code skill?

Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/debug-distributed-hang/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.

What does the Debug Distributed Hang skill do?

Is this skill free to install?

Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.

When should I use the Debug Distributed Hang skill?

Use Debug Distributed Hang when your Claude Code task falls under the Engineering category — specifically in the observability area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Debug Distributed Hang" or describe the task and let Claude pick). Browse related skills at /category/engineering/.

What is a Claude Code skill and how does the Debug Distributed Hang skill fit in?

A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Debug Distributed Hang is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Engineering category. Learn more at /learn/what-is-a-claude-skill/.

Attribution & license

Source: https://github.com/FutureMLS-Lab/OSCAR/blob/HEAD/sglang-research/.claude/skills/debug-distributed-hang/SKILL.md
Author: FutureMLS-Lab
Website: https://oscar-quantize.github.io/

Cite this skill

If you reference this skill in a blog post, paper, or documentation, you can cite it as:

APA

FutureMLS-Lab. (2026). Debug Distributed Hang [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/debug-distributed-hang/

BibTeX

@misc{debug-distributed-hang-2026,
  author    = {FutureMLS-Lab},
  title     = {Debug Distributed Hang [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/debug-distributed-hang/}
}

Embed this skill

Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →

Badge

[![ClaudSkills](https://claudskills.com/badge/debug-distributed-hang.svg)](https://claudskills.com/skills/debug-distributed-hang/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)

More Engineering skills

Browse all Engineering skills in the ClaudSkills registry, or explore these other picks from the same category:

Browse all Engineering skills → Top 100 skills

Part of ClaudSkills — the open registry for Claude Skills & Claude Code Skills. · What's New · Install guide · About · llms.txt

Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel · Telegram @acreatorstore