Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options.
Install Select Trainer
$ npx skills add PINA-org/PINA --skill select-trainer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install PINA-org/PINA select-trainer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/PINA-org/PINA.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/select-trainer .claude/skills/select-trainer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "select-trainer" agent skill from https://github.com/PINA-org/PINA/tree/master/.opencode/skills/select-trainer into .claude/skills/select-trainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "select-trainer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/PINA-org/PINA/tree/master/.opencode/skills/select-trainerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add PINA-org/PINA --skill select-trainer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install PINA-org/PINA select-trainer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PINA-org/PINA.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/select-trainer .agents/skills/select-trainer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "select-trainer" agent skill from https://github.com/PINA-org/PINA/tree/master/.opencode/skills/select-trainer into .agents/skills/select-trainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "select-trainer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PINA-org/PINA --skill select-trainer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install PINA-org/PINA select-trainer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PINA-org/PINA.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/select-trainer .cursor/skills/select-trainer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "select-trainer" agent skill from https://github.com/PINA-org/PINA/tree/master/.opencode/skills/select-trainer into .cursor/skills/select-trainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "select-trainer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/PINA-org/PINA.git --path .opencode/skills/select-trainer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add PINA-org/PINA --skill select-trainer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install PINA-org/PINA select-trainer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PINA-org/PINA.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/select-trainer .gemini/skills/select-trainer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "select-trainer" agent skill from https://github.com/PINA-org/PINA/tree/master/.opencode/skills/select-trainer into .gemini/skills/select-trainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "select-trainer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install PINA-org/PINA select-trainerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add PINA-org/PINA --skill select-trainer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/PINA-org/PINA.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/select-trainer .github/skills/select-trainer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "select-trainer" agent skill from https://github.com/PINA-org/PINA/tree/master/.opencode/skills/select-trainer into .github/skills/select-trainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "select-trainer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PINA-org/PINA --skill select-trainer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install PINA-org/PINA select-trainer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PINA-org/PINA.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/select-trainer .opencode/skills/select-trainer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "select-trainer" agent skill from https://github.com/PINA-org/PINA/tree/master/.opencode/skills/select-trainer into .opencode/skills/select-trainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "select-trainer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
select-trainer- GitHub stars
- 797
- Token cost
- ~1.3k tokens
- SKILL.md length
- 423 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options.
- Works in 3 steps: Understand what the trainer needs → Configure the trainer → Train and test
- The user asks how do I train
- SKILL.md covers Step 1 — Understand what the…, Step 2 — Configure the trainer, Step 3 — Train and test and Templates, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Select Trainer is an agent skill from PINA-org/PINA. Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options. Use when the user asks "how do I train", "how to train", "set up training", "trainer", "Trainer", "train my model", "fit", "training loop", or similar. Also triggers when the user mentions batching, training configuration, train/val/test split, or is confused about how to start training.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: opencode, codex, claude
It sits in AI & LLM Engineering, covering Deep learning. The repository describes itself as: Physics-Informed Neural networks for Advanced modeling. The licence is MIT.
When your agent uses it
- The user asks how do I train
- Set up training
- The user mentions batching
- Training configuration
Example prompts
- “how do I train”
- “how to train”
- “set up training”
- “/select-trainer”
Requirements
- Python 3
- Compatibility (from SKILL.md): opencode, codex, claude
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 0cd8afb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
opencode, codex, claude
From compatibility in the SKILL.md frontmatter.
Context cost
Select Trainer loads about 1.3k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 423 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from PINA-org/PINA at commit 0cd8afb, republished under its MIT licence (© PINA-org). 423 words, ~1,299 tokens.
Download SKILL.mdSave it as
.claude/skills/select-trainer/SKILL.md (or your agent's skills folder).- name
- select-trainer
- description
- Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options. Use when the user asks "how do I train", "how to train", "set up training", "trainer", "Trainer", "train my model", "fit", "training loop", or similar. Also triggers when the user mentions batching, training configuration, train/val/test split, or is confused about how to start training.
- compatibility
- opencode, codex, claude
- license
- MIT
- metadata.audience
- users
- metadata.workflow
- training-setup
Configure Training for a PINA Solver
[!IMPORTANT] Read RULES.md before using this skill — it applies to all skills.
Use this skill to set up and run training once a solver has been chosen.
PINA's Trainer wraps Lightning's Trainer with PINA-specific defaults:
data splitting across conditions, batching strategies, device placement for
inverse parameters, and gradient tracking for physics-informed solvers.
Step 1 — Understand what the trainer needs
The trainer needs three things. If any are missing, ask the user:
- Solver (required) — already chosen and instantiated.
- Domain discretisation — all
DomainEquationConditiondomains must be sampled before the trainer can create dataloaders. - Training config — epochs, batch size, accelerator, device.
Domain discretisation
Physics-informed problems use domain=... in their conditions. The trainer
requires every such domain to have been sampled:
problem.discretise_domain(n=1000, mode="random")If you forget, the trainer raises a clear error listing which domains are missing.
Step 2 — Configure the trainer
The constructor has two groups of parameters: PINA-specific and Lightning
**kwargs passed through to the parent class.
PINA-specific parameters
| Parameter | Default | What it controls |
|---|---|---|
solver | — (required) | The solver instance to train |
batch_size | None | None = full batch; int = mini-batches |
train_size / val_size / test_size | 1.0 / 0.0 / 0.0 | Fraction split per condition |
batching_mode | "common_batch_size" | How batches are built across conditions (see below) |
automatic_batching | False | True = Lightning's default collation; False = direct subset retrieval |
num_workers | 0 | Dataloader workers |
pin_memory | False | Pin memory for faster GPU transfer |
shuffle | True | Shuffle before splitting |
Show full SKILL.md (193 more words)Show less
Batching modes
The mode controls how condition data is assembled into batches:
| Mode | Behaviour | When to use |
|---|---|---|
"common_batch_size" | Each condition supplies batch_size points per batch | Default — works for most cases |
"proportional" | Batch sizes are scaled by condition dataset sizes | Unbalanced datasets (e.g., many interior points but few boundary points) |
"separate_conditions" | Iterates through each condition separately | Each condition's data is heterogeneous (e.g., one is pointwise, another is a graph) |
Common Lightning kwargs
These are passed as **kwargs and fully documented by PyTorch Lightning.
Key ones for PINA users:
| Kwarg | What it does |
|---|---|
max_epochs | Number of training epochs |
accelerator | "cpu", "gpu", "mps" (Apple Silicon) |
devices | Device index or count (e.g., 1, [0], "auto") |
precision | "16-mixed", "32", "64", "bf16-mixed" |
enable_progress_bar | True / False |
gradient_clip_val | Gradient clipping threshold |
callbacks | List of Lightning callbacks (e.g., ModelCheckpoint, EarlyStopping) |
Step 3 — Train and test
Usage is uniform regardless of solver type:
from pina import Trainer
trainer = Trainer(
solver=solver,
max_epochs=1000,
batch_size=32,
accelerator="cpu",
train_size=0.8,
val_size=0.1,
test_size=0.1,
)
trainer.train() # Lightning fit()
trainer.test() # Lightning test() — optionalTemplates
Full-batch physics-informed
problem.discretise_domain(n=5000, mode="random")
trainer = Trainer(
solver=solver,
max_epochs=10000,
batch_size=None, # full batch — no mini-batching
accelerator="cpu",
)
trainer.train()Mini-batch supervised
trainer = Trainer(
solver=solver,
max_epochs=500,
batch_size=64,
train_size=0.8,
val_size=0.1,
test_size=0.1,
accelerator="gpu",
devices=1,
num_workers=4,
shuffle=True,
)
trainer.train()
trainer.test()Unbalanced conditions (proportional batching)
trainer = Trainer(
solver=solver,
batch_size=512,
batching_mode="proportional",
max_epochs=1000,
)Checklist
- Solver already chosen and instantiated (see select-solver skill)
- All domains discretised:
problem.discretise_domain(n=..., mode="...") - Batch size decided:
Nonefor full-batch, an int for mini-batches - Batching mode selected based on condition balance
- Train/val/test split configured
- Accelerator and device chosen
- Training started:
trainer.train()
© PINA-org, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .opencode/skills/select-trainer of PINA-org/PINA.
Open the folder on GitHubat commit 0cd8afb
Compare with similar skills
Select Trainer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Select Trainer this skillPINA-org/PINA | 797 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Add Oponnx/onnx | 22k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Add Function Bodyonnx/onnx | 22k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
Add Op
onnx/onnx
Add a new ONNX operator or update an existing operator to a new opset version.
CLIP Image-Text Matching
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
Add Function Body
onnx/onnx
Add a function body definition to an ONNX operator, defining how it decomposes into simpler ops.
Paddle Design Distributed
PaddlePaddle/Paddle
A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…
More from PINA-org/PINA
All 10 skills in this repoCreate Skill
PINA-org/PINA
Create, modify, and improve PINA skills. An agent skill from PINA-org/PINA.
Pina Workflow
PINA-org/PINA
Orchestrates a complete session from problem definition through trained solver.
Select Model
PINA-org/PINA
Guides users through selecting, configuring, or creating a PyTorch model for a PINA problem.
Select Solver
PINA-org/PINA
Guides users through selecting the right PINA solver for their problem, or creating a custom solver when no built-in fits.
Skill Sync Checker
PINA-org/PINA
Audits SKILL.md files in this repo's skills directory for references to functions, classes, or modules (mentioned by name in prose, e.g.
Condition Setup
PINA-org/PINA
Set up conditions for PINA problems. An agent skill from PINA-org/PINA.
Related
Categories
Questions about Select Trainer
What does Select Trainer do?
Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options. Select Trainer is an agent skill from PINA-org/PINA. Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options.
When should I use Select Trainer?
Select Trainer fits situations like: the user asks how do I train; set up training; the user mentions batching; training configuration.
How do I install Select Trainer in Claude Code?
Run `npx skills add PINA-org/PINA --skill select-trainer -a claude-code`. Or copy the skill folder (.opencode/skills/select-trainer in PINA-org/PINA) into .claude/skills/select-trainer in your project. Claude Code loads it when a task matches its description.
How do I install Select Trainer in Codex?
Run `npx skills add PINA-org/PINA --skill select-trainer -a codex`. Or copy the skill folder (.opencode/skills/select-trainer in PINA-org/PINA) into .agents/skills/select-trainer in your project. Codex loads it when a task matches its description.
Can I use Select Trainer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PINA-org/PINA --skill select-trainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/select-trainer, .gemini/skills/select-trainer, .github/skills/select-trainer and .opencode/skills/select-trainer in your project.
What does Select Trainer need to run?
SKILL.md names no scripts, command-line tools or credentials: Select Trainer is instructions for the agent only. Our summary lists: Python 3. Compatibility (from SKILL.md): opencode, codex, claude.
Does Select Trainer access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Select Trainer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Select Trainer use?
Select Trainer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Select Trainer use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Select Trainer?
Skills that share tags, products or a category with Select Trainer: Add Uint Support (pytorch/pytorch, 104k stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Add Op (onnx/onnx, 22k stars) and CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Select Trainer?
PINA-org (a GitHub organization) maintains it in PINA-org/PINA, which has 797 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 6, 2026.
Source: PINA-org/PINA on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.