ml-training-recipes agent skill by Orchestra-Research
Provides PyTorch training recipes for LLMs, vision, diffusion, and genomics, covering training loops, optimizers, learning rate schedules, mixed precision, debugging, and GPU throughput.
At a glance
| Publisher | Orchestra-Research |
|---|---|
| Repository | Orchestra-Research/AI-Research-SKILLs (81 listed skills) |
| Category | AI Agents and LLM Engineering |
| License | MIT |
| Last commit | June 15, 2026 (repository) |
| SKILL.md | 309 lines, 1,453 words |
| Bundled files | 7 files, including references |
| Quality score | 77/100 · C Passes all seven graded checks |
| Security scan | Not scanned |
| README badge | Get the listing badge and raise the score |
Before you install
Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.
- Bundled scripts: none.
- License: MIT, an open-source or open-content license.
Install ml-training-recipes
The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.
npx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/main/10-optimization/ml-training-recipestmp="$(mktemp -d)"
git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"10-optimization/ml-training-recipes .claude/skills/
rm -rf "$tmp"python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo Orchestra-Research/AI-Research-SKILLs \
--path 10-optimization/ml-training-recipesOrchestra-Research/AI-Research-SKILLs is third-party code. Read SKILL.md and any bundled scripts before you install it.
How the author describes it
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
From the description field of SKILL.md. Agents read this line to decide when to load the skill.
Sections in SKILL.md
- Reference files (read when needed)
- Architecture Selection
- Scaling Laws
- Chinchilla rule (Hoffmann et al., 2022)
- Training Loop
- Key principles
- Optimizer Configuration
- Rules of thumb
- Learning Rate Scheduling
- Time-based (autoresearch style)
- Cosine decay
- Guidance
- Mixed Precision & Compilation
- Memory & Performance
- Meta device init (large models)
- MFU (Model FLOPs Utilization)
Files in the skill folder
SKILL.mdreferences/architecture.mdreferences/biomedical.mdreferences/domain-specific.mdreferences/experiment-loop.mdreferences/optimizers.mdreferences/scaling-and-selection.md
Suede Skill Check: 77/100 · C
Report snapshot · · graded-v2
The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.
Source revision: 773a52944ba4. Report version ee4797cd6823. Badge URLs follow the latest listing; save the report to keep this version.
Download report · Request a fresh review
What to review next
- Recent maintenance: 3 of 9 points. 9 for a repository commit within 30 days of the snapshot; 6 within 90; 3 within 180; 1 within 365.
- Boundary clause: 0 of 4 points. 4 when the description says when not to use the skill (“Not for …”, “Do not use …”, “Use … instead”).
- Example request: 0 of 3 points. 3 when the description quotes an example request (3–60 characters in quotation marks).
Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.
ml-training-recipes passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.
See the checks and points
| Check | Result |
|---|---|
| Frontmatter parses and declares a name and a description | Pass |
| Name uses lowercase letters, digits and hyphens, 64 characters or fewer | Pass |
| Name matches the skill's folder name | Pass |
| Description is between 50 and 1,024 characters | Pass |
| Description says when an agent should use the skill | Pass |
| SKILL.md body is 500 lines or fewer | Pass |
| A license is declared in the frontmatter or the repository | Pass |
| Repository has a commit in the last 12 months | Pass |
| Score component | Points |
|---|---|
| Structural checks | 56 of 56 |
| Description length | 5 of 5 |
| Boundary clause | 0 of 4 |
| Example request | 0 of 3 |
| Instruction depth | 7 of 7 |
| Reference files | 3 of 3 |
| Bundled scripts | 0 of 2 |
| Recent maintenance | 3 of 9 |
| Curated-list citations | 3 of 7 |
| Tool permissions declared | 0 of 2 |
| Compatibility declared | 0 of 2 |
Show the listing and raise the score
ml-training-recipes is listed with 77/100 · C. This badge links to its Suede listing. Skills scoring 80–99 add a numeric and a letter quality shield; the largest open points for ml-training-recipes are recent maintenance (6), boundary clause (4) and example request (3). Send your repository and the points you want to raise, then request a fresh review after updating the skill.
[](https://skills.suedeai.ai/directory/orchestra-research/ai-research-skills/ml-training-recipes/)<a href="https://skills.suedeai.ai/directory/orchestra-research/ai-research-skills/ml-training-recipes/"><img src="https://skills.suedeai.ai/directory/badge.svg" alt="Suede Skills Directory: listed" height="20"></a>Where this skill is cited
Orchestra-Research/AI-Research-SKILLs appears in 2 curated lists: VoltAgent/awesome-agent-skills, skillmatic-ai/awesome-agent-skills.