experiment-queue SKILL.md skillA
experiment-queue from wanshuiyin/auto-claude-code-research-in-sleep is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wanshuiyin/auto-claude-code-research-in-sleep/experiment-queue@git:20260810.6be7b60Pins git:20260810.6be7b60 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wanshuiyin/auto-claude-code-research-in-sleep
- Path
skills/skills-codex/experiment-queue/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260810.6be7b60, committed Aug 10, 2026
- First version recorded
- Jul 2, 2026
- Size
- 16,375 bytes
- Repository stars
- 18,690
- License
- MIT
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "队列实验", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is insufficient for 10+ jobs that need orchestration.
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
# Experiment Queue Orchestrate large batches of ML experiments on SSH remote GPU servers with proper state tracking, OOM retry, stale cleanup, and wave transitions. ## When to Use This Skill Use when `/run-experiment` is insufficient: - **≥10 jobs** that need batching across GPUs - **Multi-seed sweeps** (e.g., 21 seeds × 12 cells) - **Wave transitions** (run wave 1, wait, run wave 2, wait, run wave 3...) - **Teacher+student chains** (train teacher then distill; auto-trigger student after teacher done) - **OOM-prone configs** where you need to retry with different GPU or wait - **Mixed seed grids** where failed cells need re-running Do NOT use for: - Single ad-hoc experiment (use `/run-experiment`) - Modal/Vast.ai deployments (those have their own orchestration) - Experiments that need manual inspection between runs ## Why This Exists Based on session audit (2026-04-16), the major wall-clock sinks in multi-seed grid experiments are: 1. **Stale screens** — python finishes, wandb uploads, screen hangs, next wave blocked 2. **OOM on shared GPU** — previous job's memory not yet released 3. **Wave race** — new wave launches before previous wave fully settles …
Read the whole file at its exact version.
How to install
mdr add wanshuiyin/auto-claude-code-research-in-sleep/experiment-queue@sha256:3a66fbd5f7684d32The line at the top of this page pins the label git:20260810.6be7b60, 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.
[](https://markdownregistry.com/a/art_lti65glxrcuhlzae)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 2, 2026 and Aug 10, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260810.6be7b60 latest | 2026-08-10 | 6be7b60 | 16,375 B | A | view · diff |
| git:20260713.e67ae16 | 2026-07-13 | e67ae16 | 15,858 B | A | view · diff |
| git:20260710.c3f9813 | 2026-07-10 | c3f9813 | 15,856 B | A | view · diff |
| git:20260702.569dd51 | 2026-07-02 | 569dd51 | 15,821 B | A | view · diff |
| git:20260702.0b5ddb9 | 2026-07-02 | 0b5ddb9 | 15,469 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (16375 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
wanshuiyin/auto-claude-code-research-in-sleep · 18,690 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lti65glxrcuhlzae GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/auto-claude-code-research-in-sleep/experiment-queue GET https://markdownregistry.com/api/v1/blob/3a66fbd5f7684d3279bb91eb5d4ec64245f86da3ba507a7b60e357c7d8dfd00f
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 wanshuiyin/auto-claude-code-research-in-sleep
Every file in wanshuiyin/auto-claude-code-research-in-sleep