New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pina Workflow

by PINA-org in PINA-org/PINA

Orchestrates a complete session from problem definition through trained solver.

MITAuto-check passedAI & LLM Engineering

Install Pina Workflow

skills CLI
$ npx skills add PINA-org/PINA --skill pina-workflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install PINA-org/PINA pina-workflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/PINA-org/PINA.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/pina-workflow .claude/skills/pina-workflow && rm -rf skills-src

Use ~/.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/

Facts

Skill name
pina-workflow
GitHub stars
798
Token cost
~1.1k tokens
SKILL.md length
387 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Orchestrates a complete session from problem definition through trained solver.

  • Works in 5 steps: Problem definition → Model selection → Solver selection → …
  • The user has a vague open-ended request like I have a differential equation
  • SKILL.md covers Hard rule for every stage, Pipeline, Stage 1 — Problem definition and Stage 2 — Model selection, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pina Workflow is an agent skill from PINA-org/PINA. Orchestrates a complete session from problem definition through trained solver. This is the entry point for solving differential equations or physics problems with neural networks. Use when the user has a vague open-ended request like "I have a differential equation", "I want to solve a PDE", "I have a physics problem", "I need to model a system", "help me solve an ODE", "I want to use neural networks for my equations", "I have some data and equations", or "let's build physics-informed neural networks". Also…

Its SKILL.md is about 1.1k 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 has a vague open-ended request like I have a differential equation
  • I want to solve a PDE
  • I have a physics problem
  • I need to model a system

Example prompts

  • “I have a differential equation”
  • “I want to solve a PDE”
  • “I have a physics problem”
  • “/pina-workflow”

Requirements

  • Compatibility (from SKILL.md): opencode, codex, claude

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Problem definition
  2. Model selection
  3. Solver selection
  4. Trainer configuration
  5. Train

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.

    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

Pina Workflow loads about 1.1k tokens when it runs. Until then it costs about 207 tokens; SKILL.md has 387 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~207
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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). 387 words, ~1,052 tokens.

Download SKILL.mdSave it as .claude/skills/pina-workflow/SKILL.md (or your agent's skills folder).
name
pina-workflow
description
Orchestrates a complete session from problem definition through trained solver. This is the entry point for solving differential equations or physics problems with neural networks. Use when the user has a vague open-ended request like "I have a differential equation", "I want to solve a PDE", "I have a physics problem", "I need to model a system", "help me solve an ODE", "I want to use neural networks for my equations", "I have some data and equations", or "let's build physics-informed neural networks". Also triggers on mentions of specific equations (Navier-Stokes, Burgers, Poisson, heat equation, wave equation, etc.) or when the user describes a physical system they want to simulate. This skill will guide the user through the full workflow step by step, loading the right sub-skills at the right time.
compatibility
opencode, codex, claude
license
MIT
metadata.audience
users
metadata.workflow
pina-workflow

PINA Workflow — End-to-End Agentic Session

[!IMPORTANT] Read RULES.md before using this skill — it applies to all skills.

Orchestrates a full PINA session. Does not duplicate sub-skill content — each stage below requires actually reading the referenced file(s) in full, not acting from memory, summary, or a prior pass over this conversation.

Hard rule for every stage

Before doing anything in a stage:

  1. Read every file path listed for that stage, in full, with the view tool.
  2. If a stage lists multiple sub-skills, read all of them — the list is mandatory, not illustrative.
  3. Do not advance to the next stage until the current stage's checklist (below) is satisfied.
  4. If you already read a file earlier in this session and the file hasn't changed, you may skip re-reading it — but only if you can state which stage/turn you read it in. If in doubt, re-read.

Pipeline

Stage 1 — Problem definition    → create-problem
  ├── Domain creation           →   define-domains
  ├── Equation definition       →   define-equations
  └── Condition binding         →   condition-setup
Stage 2 — Model selection       → select-model
Stage 3 — Solver selection      → select-solver
Stage 4 — Trainer configuration → select-trainer

Stage 1 — Problem definition

Read ../create-problem/SKILL.md in full now.

create-problem itself delegates to three sub-skills. Read all three in full, in this order, following whatever instructions create-problem gives for sequencing:

  • ../define-domains/SKILL.md
  • ../define-equations/SKILL.md
  • ../condition-setup/SKILL.md

Exception: if the user already has a working problem object, skip directly to Stage 2 — do not read Stage 1 files.

Stage 1 checklist (must all be true before moving on):

  • create-problem read in full
  • define-domains read in full, domains defined
  • define-equations read in full, equations defined
  • condition-setup read in full, conditions bound
  • a problem object exists
Show full SKILL.md (150 more words)Show less

Stage 2 — Model selection

Read ../select-model/SKILL.md in full now.

Input/output dimensions are known from the Stage 1 problem object — use them, don't re-derive or guess.

Stage 2 checklist:

  • select-model read in full
  • model instantiated with correct input/output dims

Stage 3 — Solver selection

Read ../select-solver/SKILL.md in full now.

Check the condition types from the problem object (set in Stage 1) — they drive which solver is valid. Do not pick a solver without checking this.

Stage 3 checklist:

  • select-solver read in full
  • condition types checked against solver requirements
  • solver instantiated

Stage 4 — Trainer configuration

Read ../select-trainer/SKILL.md in full now.

Verify all domains are discretised before configuring the trainer — if not, go back to define-domains, don't silently proceed.

Stage 4 checklist:

  • select-trainer read in full
  • all domains confirmed discretised
  • trainer configured

Stage 5 — Train

The user runs trainer.train(). Offer to inspect results afterwards (forward pass, loss curves, discovered unknown parameters for inverse problems).

© 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/pina-workflow of PINA-org/PINA.

Open the folder on GitHubat commit 0cd8afb

Compare with similar skills

Pina Workflow 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.

Pina Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pina Workflow this skillPINA-org/PINA798—~1.1kAutomated safety check: PassMIT
Add Uint Supportpytorch/pytorch104k2 repos~2.3kAutomated safety check: PassCustom licence
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
Add Oponnx/onnx22k—~1.2kAutomated safety check: PassApache-2.0
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs13k7 repos~1.7kAutomated safety check: PassMIT
Add Function Bodyonnx/onnx22k—~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • Add Uint Support

    pytorch/pytorch

    Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

    104k GitHub starsUsed in 2 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • 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.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Add Op

    onnx/onnx

    Add a new ONNX operator or update an existing operator to a new opset version.

    22k GitHub stars~1.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • 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.

    13k GitHub starsUsed in 7 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed

  • Add Function Body

    onnx/onnx

    Add a function body definition to an ONNX operator, defining how it decomposes into simpler ops.

    22k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • 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…

    24k GitHub stars~660 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from PINA-org/PINA

All 10 skills in this repo

  • Create Skill

    PINA-org/PINA

    Create, modify, and improve PINA skills. An agent skill from PINA-org/PINA.

    798 GitHub stars~1.8k tokensUpdated 3 days ago
    Auto-check passed

  • Select Model

    PINA-org/PINA

    Guides users through selecting, configuring, or creating a PyTorch model for a PINA problem.

    798 GitHub stars~2.4k tokensUpdated 3 days ago
    Auto-check passed

  • 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.

    798 GitHub stars~2.9k tokensUpdated 3 days ago
    Auto-check passed

  • Select Trainer

    PINA-org/PINA

    Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options.

    798 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • 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.

    798 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed

  • Condition Setup

    PINA-org/PINA

    Set up conditions for PINA problems. An agent skill from PINA-org/PINA.

    798 GitHub stars~1k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Pina Workflow

What does Pina Workflow do?

Orchestrates a complete session from problem definition through trained solver. Pina Workflow is an agent skill from PINA-org/PINA. Orchestrates a complete session from problem definition through trained solver.

When should I use Pina Workflow?

Pina Workflow fits situations like: the user has a vague open-ended request like I have a differential equation; I want to solve a PDE; I have a physics problem; I need to model a system.

How do I install Pina Workflow in Claude Code?

Run `npx skills add PINA-org/PINA --skill pina-workflow -a claude-code`. Or copy the skill folder (.opencode/skills/pina-workflow in PINA-org/PINA) into .claude/skills/pina-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Pina Workflow in Codex?

Run `npx skills add PINA-org/PINA --skill pina-workflow -a codex`. Or copy the skill folder (.opencode/skills/pina-workflow in PINA-org/PINA) into .agents/skills/pina-workflow in your project. Codex loads it when a task matches its description.

Can I use Pina Workflow 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 pina-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pina-workflow, .gemini/skills/pina-workflow, .github/skills/pina-workflow and .opencode/skills/pina-workflow in your project.

What does Pina Workflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Pina Workflow is instructions for the agent only. Compatibility (from SKILL.md): opencode, codex, claude.

Does Pina Workflow 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 Pina Workflow 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 Pina Workflow use?

Pina Workflow 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 Pina Workflow use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Pina Workflow?

Skills that share tags, products or a category with Pina Workflow: 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 Pina Workflow?

PINA-org (a GitHub organization) maintains it in PINA-org/PINA, which has 798 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.