Compute Env Setup

Playbook for standing up remote GPU/conda/Slurm/Modal compute environments

Works with setup

Test report

Verdict
Works with setup
Score
7.2/10
Tested
Jul 18, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 30, 2026 · b15b5aa

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 18, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Substantial, battle-scarred documentation -- the failure table maps real symptoms like 'no kernel image is available' and 'Read-only file system under CACHE_VAR' to specific fixes -- but every action verb routes through proprietary platform tools (compute_details, submit_job, build_env, the compute_provider kernel) that don't exist outside wisp-science, so a standalone user has nothing to execute and no delta can be measured. Useful only inside that platform; setup, not pass.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 4/5
  • Output vs. baseline 5/10
  • Docs & honesty 4/5

What Compute Env Setup does

A dense playbook for materialising a declarative compute-env spec across provider shapes (direct SSH/conda, Slurm/Apptainer, bridge runners, managed APIs like Modal/RunPod), plus weight-cache placement and a grep-able failure-diagnosis table. Triggers on standing up a new compute provider, building a GPU image, or wiring a weight cache. Assumes the wisp-science / Claude Science tool platform.

How to install Compute Env Setup

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Compute Env Setup

  • /compute-env-setup Playbook for standing up remote GPU/conda/Slurm/Modal compute environments

It also activates on plain-language prompts like these:

  • I need to stand up a GPU environment on our Slurm cluster for training.
  • Help me build a GPU image with a weight cache on Modal for this model.
  • Can you port our compute environment setup over to RunPod for me?

Frequently asked questions

Is the Compute Env Setup skill free?
Yes. The skill itself is free from xuzhougeng/wisp-science. SkillProof publishes the install command and an independent test verdict at no cost.
Does Compute Env Setup work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 18, 2026. Verdict: Works with setup. Substantial, battle-scarred documentation -- the failure table maps real symptoms like 'no kernel image is available' and 'Read-only file system under CACHE_VAR' to specific fixes -- but every action verb routes through proprietary platform tools (compute_details, submit_job, build_env, the compute_provider kernel) that don't exist outside wisp-science, so a standalone user has nothing to execute and no delta can be measured. Useful only inside that platform; setup, not pass.
What is the Compute Env Setup SkillProof Score?
7.2/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Compute Env Setup?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Compute Env Setup with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.