amax-remote-experiment
Skill1 starsChanged 5 months agoNo licenceView on GitHub
Run, debug, and test ML experiments on the user's shared remote GPU servers: ganpa/AMAX (ssh -p 22 ganpa@10.103.68.253) and rtxpro6000 (ssh yunlong@166.111.73.159). Use when the user asks to run ML experiments, train models, debug runtime failures, execute tests, build data/cache artifacts, or use GPU jobs remotely. Covers Windows-host SSH access, server selection, local WSL vs remote code-editing rules, git sync, avoiding scp/rsync source-code drift, conda environments, data/cache setup, GPU selection, tmux sessions, logs, and shared-server safety. DO NOT USE for unrelated local-only coding tasks.
- Reads credentials
- Deletes or force-pushes
- Installs packages
- Commits and pushes
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- paper-writing-skill/CLAUDE.mdCLAUDE.md
- 802-paper-writingSkill
- academic-plottingSkill
- experiment-report-recorderSkill
- git-worktree-experiment-isolationSkill
- humanizer-academic-zhSkill
- microsoft-foundrySkill
- ml-paper-writingSkill
- model-arch-mermaidSkill
- paper-writingSkill
- presenting-conference-talksSkill
- progress-recorderSkill
- research-paper-writingSkill
- software-design-patternsSkill
- systems-paper-writingSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
52 rules. About 0 are common, 39 are distinctive, and 13 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈39
Distinctive · estimate
This author's own choices. Worth a look.
13
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

