LLM Gold Bound Failure Check Agent Skill

Trtllm Moe Develop

by NVIDIA

vendor

>- Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/modules/fused_moe, ConfigurableMoE, MoE backends, MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, routing, factories, MoE docs, or MoE tests. Also use when the user asks whether a MoE design follows the current architecture or whether a MoE refactor is reasonable.

LLM Gate

by rohitg00

LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.

Adversarial Review

by redis

vendor

>- Adversarially review a diff, patch, or plan for memtier_benchmark using the real review standards of the project's senior maintainers (Yossi Gottlieb / yossigo, Oran Agra / oranagra, Paulo Sousa / paulorsousa). Use when asked to "adversarially review", "review like the maintainers", "find what a reviewer would block on", or before opening/merging a PR. Emits skeptical, evidence- backed findings; assumes a problem is real until it can be refuted.

Fix Pr

by pytorch

vendor

Address CI failures and unresolved review comments on a Helion pull request. Auto-activate when the user mentions a URL like https://github.com/pytorch/helion/pull/<number>.

Huggingface Zerogpu

by lingxling

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process...

Woz

by WithWoz

WOZCODE utilities. Subcommands — login, logout, status, settings, update, share, review (deep multi-persona code review), benchmark (WOZCODE vs vanilla comparison). Invoke as `/woz <subcommand>`, e.g. `/woz login` or `/woz review`.

Alpha Evolve

by gaasher

> Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel proposers each apply one small SEARCH/REPLACE diff to a parent, scored by a cascade-evaluated training run, and children are kept in a MAP-Elites archive across islands (with migration + checkpointing) so diverse high performers survive. A finite, bounded-parallelism re-creation of AlphaEvolve/OpenEvolve, bent for ML autoresearch. Runs to a fixed compute budget or until interrupted. Not for the sequential single-thread autoresearch loops (one change → measure → keep/revert), and not for verifying a known bug or external claim — this is parallel, diversity-preserving search over a program.

Huggingface Webhooks

by hookdeck

> Receive and verify Hugging Face webhooks. Use when setting up Hugging Face webhook handlers, debugging X-Webhook-Secret verification, or handling events on models, datasets, and Spaces — repo updates, new commits and tags (repo.content), config changes (repo.config), discussions, Pull Requests, and discussion comments.