# Pathways workload

> Pathways workload is an open-source agent skill. Debugs failed, crashing or hung Pathways on Cloud workloads (JAX training or inference on Cloud TPU in GKE, run as a JobSet, PathwaysJob or. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/google/skills/tree/main/skills/cloud/pathways-workload
- **Repository:** https://github.com/google/skills
- **GitHub stars:** 24,379
- **License:** Apache-2.0
- **Skill name:** pathways-workload
- **Collection:** https://github.com/google/skills
- **Listing updated:** 2026-11-17

## About

Debugs failed, crashing or hung Pathways on Cloud workloads (JAX training or inference on Cloud TPU in GKE, run as a JobSet, PathwaysJob or LeaderWorkerSet). Reads Cloud Logging for every Pathways container (user workload, IFRT proxy, pathways-rm, pathways-worker, colocated Python sidecar), node kernel logs and GKE events, then reports the earliest real error, the root cause and a fix. Use when a Pathways workload fails to start, crashes, restarts or stops making progress, or shows errors such as IFRT proxy connection failures, DEADLINE_EXCEEDED lost connection to peer, host OOM kills, ImagePullBackOff, or JAX and Pathways version mismatches. Don't use for GKE workloads that don't use Pathways, or for creating clusters or deploying new Pathways workloads.

## When your agent uses it

> Debugs failed, crashing or hung Pathways on Cloud workloads (JAX training or inference on Cloud TPU in GKE, run as a JobSet, PathwaysJob or LeaderWorkerSet). Reads Cloud Logging for every Pathways container (user workload, IFRT proxy, pathways-rm, pathways-worker, colocated Python sidecar), node kernel logs and GKE events, then reports the earliest real error, the root cause and a fix. Use when a Pathways workload fails to start, crashes, restarts or stops making progress, or shows errors such as IFRT proxy connection failures, DEADLINE_EXCEEDED lost connection to peer, host OOM kills, ImagePullBackOff, or JAX and Pathways version mismatches. Don't use for GKE workloads that don't use Pathways, or for creating clusters or deploying new Pathways workloads.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs Python scripts](https://github.com/google/skills/tree/HEAD/skills/cloud/pathways-workload)
- [Network calls found in its scripts](https://github.com/google/skills/tree/HEAD/skills/cloud/pathways-workload)
- [License: Apache-2.0](https://github.com/google/skills/tree/HEAD/skills/cloud/pathways-workload)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/pathways-workload` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/pathways-workload &&
cp -R "$tmp/skills/cloud/pathways-workload" ~/.claude/skills/pathways-workload &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/pathways-workload` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/pathways-workload` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/pathways-workload &&
cp -R "$tmp/skills/cloud/pathways-workload" ~/.agents/skills/pathways-workload &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/pathways-workload` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/pathways-workload` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/pathways-workload &&
cp -R "$tmp/skills/cloud/pathways-workload" ~/.cursor/skills/pathways-workload &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/pathways-workload` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/google/skills.git --path skills/cloud/pathways-workload
```

Or copy the folder to `~/.gemini/skills/pathways-workload` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/pathways-workload`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/pathways-workload &&
cp -R "$tmp/skills/cloud/pathways-workload" ~/.copilot/skills/pathways-workload &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/pathways-workload` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/google/skills.git
```

Then copy `skills/skills/cloud/pathways-workload` into your agent's skills folder as `pathways-workload`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Pathways workload in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/pathways-workload to use it in all your projects, or to .claude/skills/pathways-workload in one project.

### Does Pathways workload run scripts?

Yes. It runs Python scripts. Its scripts contain network calls. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Pathways workload?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/pathways-workload
