running-cluster-experiments SKILL.md skillA

running-cluster-experiments from chgagne/claude-skills-research is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add chgagne/claude-skills-research/running-cluster-experiments@git:20260812.12926b4

Pins git:20260812.12926b4 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
chgagne/claude-skills-research
Path
running-cluster-experiments/SKILL.md
Versions recorded
2
Latest version
git:20260812.12926b4, committed Aug 12, 2026
First version recorded
Aug 12, 2026
Size
24,824 bytes
Repository stars
5
License
MIT

Use when planning, budgeting, submitting or resuming a multi-job experiment campaign on a Slurm/HPC cluster — sizing walltime, shaping jobs and arrays, deciding what to submit first, or after a job hit its walltime, produced no results, silently ran the wrong configuration, or got the wrong number of GPUs.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Running Cluster Experiments

## Overview

This is the **methodology** of experiment campaigns on shared clusters. For the
mechanics — MFA, account strings, gres names, quotas, partitions, rsync flags —
**REQUIRED BACKGROUND: use `using-drac-clusters`.**

**Core principle: a scheduler will kill your job at an arbitrary point, and a
cluster will hand you less than you asked for. Design for both, or your
allocation buys nothing.** Every rule below is a consequence.

The expensive failures are never "the code crashed". They are: the job ran
perfectly and wrote nothing; the job ran a different experiment than its name
says; the allocation was spent before the first useful instruction.

## Never compute on a login node — use an interactive allocation

Login nodes are shared by hundreds of people and staff kill offenders. `squeue`,
`ls`, `sacct`, `diskusage_report`, editing, `sbatch`, file transfer: fine.
**Anything that loops over data, parses a large file, trains, plots, or runs for
more than a few seconds: not fine** — including "just this once to check
something", and including work you started before realising how big it was.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add chgagne/claude-skills-research/running-cluster-experiments@sha256:7f78fbb87bcf190d

The line at the top of this page pins the label git:20260812.12926b4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6bgvjytily6z4xnb.svg)](https://markdownregistry.com/a/art_6bgvjytily6z4xnb)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, all committed on Aug 12, 2026.

versioncommittedcommitsizeaudit
git:20260812.12926b4 latest2026-08-12 12926b4 24,824 BA view · diff
git:20260812.4c0299b2026-08-12 4c0299b 23,238 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (24824 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

chgagne/claude-skills-research · 5 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6bgvjytily6z4xnb
GET https://markdownregistry.com/api/v1/resolve?ref=chgagne/claude-skills-research/running-cluster-experiments
GET https://markdownregistry.com/api/v1/blob/7f78fbb87bcf190db8678a5b4a0badb2b7d068e1d99e3b10ab527f7d9416bff6

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from chgagne/claude-skills-research

self-surveying-literature SKILL.md skill
chgagne/claude-skills-research · _evals/surveying-literature/self-skill/SKILL.md · Audit a research paper draft (LaTeX sources + .bib) for related work it should cite but does not, above all close prior…
git:20261009.6f52569 · audit A · 5 stars
self-verifying-bibliography SKILL.md skill
chgagne/claude-skills-research · _evals/verifying-bibliography/self-skill/SKILL.md · Check a BibTeX bibliography against the real published record. Finds fabricated or non-existent references, wrong…
git:20261009.3a873fd · audit A · 5 stars
collaborating-on-research SKILL.md skill
chgagne/claude-skills-research · collaborating-on-research/SKILL.md · Use when working with a researcher on a long-running research project across many sessions — opening or closing a…
git:20260817.136fa75 · audit A · 5 stars
comparing-papers SKILL.md skill
chgagne/claude-skills-research · comparing-papers/SKILL.md · Use when comparing a draft against specific prior work head to head — checking whether a baseline was trained at the…
git:20260812.4c0299b · audit A · 5 stars
explaining-derivations SKILL.md skill
chgagne/claude-skills-research · explaining-derivations/SKILL.md · Use when a proof or derivation needs to be made explicit step by step — expanding a paper's algebra for a reader…
git:20260816.89dabff · audit A · 5 stars
proofreading-paper-writing SKILL.md skill
chgagne/claude-skills-research · proofreading-paper-writing/SKILL.md · Use when asked to proofread, polish, or critique the writing of an academic paper from its LaTeX sources — grammar and…
git:20261009.2091ec8 · audit A · 5 stars
reviewing-paper-sources SKILL.md skill
chgagne/claude-skills-research · reviewing-paper-sources/SKILL.md · Use when asked to review, critique, or assess an academic paper from its LaTeX sources — including pre-submission…
git:20260926.af6ea48 · audit A · 5 stars
surveying-literature SKILL.md skill
chgagne/claude-skills-research · surveying-literature/SKILL.md · Use when finding related work a draft may have missed, checking whether a contribution has already been published, or…
git:20261016.40659e0 · audit A · 5 stars
using-drac-clusters SKILL.md skill
chgagne/claude-skills-research · using-drac-clusters/SKILL.md · Use when working on a Digital Research Alliance of Canada (DRAC, Alliance, formerly Compute Canada) HPC cluster such as…
git:20260814.fdf4923 · audit B · 5 stars
verifying-bibliography SKILL.md skill
chgagne/claude-skills-research · verifying-bibliography/SKILL.md · Use when checking a .bib or reference list for incorrect or fabricated entries — wrong titles, invented co-authors…
git:20261009.18f8d6d · audit A · 5 stars
verifying-proofs SKILL.md skill
chgagne/claude-skills-research · verifying-proofs/SKILL.md · Use when checking the mathematics of a paper rather than its claims — verifying a theorem's proof, an algebraic…
git:20260817.78f3c11 · audit A · 5 stars

Every file in chgagne/claude-skills-research

Browse by kind, by grade A, or by owner.