job-env-check — Claude Code skill: what it does, how to install
job-env-check — a skill for Claude Code tests whether bare python3 imports PyTorch before helper tools execute. It runs at the start of each evaluation loop on a GPU host.
Apache-2.0 ★ 339 updated 2026-11-11
~/.claude/skills/job-env-check/SKILL.mdWhat job-env-check does
The tool verifies that executing python3 directly can import torch. GPU tasks executed over SSH frequently run in non-login shells where the default system Python lacks machine learning dependencies, even when the accelerator itself has configured drivers.
A driver executes python3 notes/job_env_check.py once per loop start. The script returns exactly one line: either JOB-ENV-OK python3=<path> torch=<version> or JOB-ENV-FAIL python3=<path> <reason>, outputting the traceback above the failure flag.
The logic expects the ForgeKernel repository layout. Sibling tools launch via python3 notes/<tool>.py and re-spawn python3 eval/bench.py, so all steps fail immediately if the shell interpreter cannot import PyTorch.
What it helps with
- verify PyTorch imports under the default python3 binary on GPU hosts
- diagnose non-login SSH shell environment mismatches
- log the active Python interpreter path and torch version in one line
Example prompts for the agent
- Check if python3 imports torch before launching the benchmark suite
- Run python3 notes/job_env_check.py to verify the remote GPU environment
How to install job-env-check
Manually: put the files in place
~/.claude/skills/job-env-check/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/job-env-check/
Manually: put the files in place
.agents/skills/job-env-check/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/job-env-check/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OpenBMB/ForgeKernel skills/job-env-check2Manually: put the files in place
.github/skills/job-env-check/SKILL.mdPlatform CLI
gemini skills install https://github.com/OpenBMB/ForgeKernel --path skills/job-env-checkManually: put the files in place
.devin/skills/job-env-check/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about job-env-check
How to install job-env-check in Claude Code?
Save the skill file to ~/.claude/skills/job-env-check/SKILL.md.
What does job-env-check do?
It runs python3 notes/job_env_check.py to confirm the default python3 command can import torch.
What is required to run job-env-check?
It requires a working python3 installation and the torch package present in that interpreter's environment.
Source text
SKILL.md · Apache-2.0
# job-env-check Whether a GPU job's bare `python3` can run the other skills. They are started as `python3 notes/<tool>.py` and re-spawn `python3 eval/bench.py`, so they all need that interpreter to import torch; on an ssh host the job runs in a non-login shell, where `python3` may be the system one even though the kernel itself evaluates fine through the card's own interpreter. The driver runs it once per loop start (`python3 notes/job_env_check.py`). It prints exactly one line, `JOB-ENV-OK python3=<path> torch=<version>` or `JOB-ENV-FAIL python3=<path> <reason>`, with the failing import's own text above a FAIL.
© OpenBMB · Apache-2.0 · OpenBMB/ForgeKernel