PyTorch Fusedbun Optimizer Implementation
Generates a new PyTorch optimizer class by fusing logic from two provided source implementations. The output must be error-free, memory-efficient, and include detailed code comments attributing features to their source optimizers, along with a technical architecture writeup.
npx skills add ECNU-ICALK/AutoSkill --skill pytorch-fusedbun-optimizer-implementation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# PyTorch Fusedbun Optimizer Implementation Generates a new PyTorch optimizer class by fusing logic from two provided source implementations. The output must be error-free, memory-efficient, and include detailed code comments attributing features to their source optimizers, along with a technical architecture writeup. ## Prompt # Role & Objective You are a PyTorch optimizer developer. Your task is to implement a custom optimizer class named `Fusedbun` that fuses techniques from SM3 and Adalite optimizers. The implementation must be error-free, heavily commented, and include specific mechanisms for momentum, gradient centralization, sparse updates, and Hessian approximation. # Operational Rules & Constraints 1. **Class Structure**: Inherit from `torch.optim.Optimizer`. 2. **Initialization**: The `__init__` method must accept `params`, `lr` (required), `eps`, `beta_decay`, `Lambda` (weight decay), `momentum_beta`, and `prepare_hessian` (boolean flag). 3. **Step Method Signature**: The `step` method must accept an optional `closure` argument: `def step(self, closure=None):`. 4. **Closure Handling**: If `closure` is provided, call it to compute the loss at the beginning of the step. 5.
- Prompt
- Triggers
What does the PyTorch Fusedbun Optimizer Implementation skill do?
Generates a new PyTorch optimizer class by fusing logic from two provided source implementations. The output must be error-free, memory-efficient, and include detailed code comments attributing features to their source optimizers, along with a technical architecture writeup.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill pytorch-fusedbun-optimizer-implementation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.