optimization skills

237 tagged optimization, measured the same way as everything else here.

Browse within: performance 35awesome 21copilot 21gemini 20hpc 19simulations 19profiling 17cuda 15Quantization 14python 13sql 13agentic-skills 12data 12PyTorch 11

cuopt-developer

01

NVIDIA/cuopt

Skill Claude CodeCodex

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

1.0k 3d ago B 47 tokens original Apache-2.0

NVIDIA/cuopt

Skill Claude CodeCodex

After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.

1.0k 3d ago A 33 tokens original Apache-2.0

cuopt-user-rules

03

NVIDIA/cuopt

Skill Claude CodeCodex

Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.

1.0k 3d ago B 42 tokens original Apache-2.0

autoreview

04

vincentkoc/tokenjuice

Skill Claude CodeCodex

Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer.

513 2mo ago A 25 tokens original MIT

backtest

05

marketcalls/vectorbt-backtesting-skills

Skill Claude CodeCodex

Quick backtest a strategy on a symbol. Creates a complete .py script with data fetch, signals, backtest, stats, and plots.

200 1mo ago A 32 tokens

vectorbt-expert

07

marketcalls/vectorbt-backtesting-skills

Skill Claude CodeCodex

VectorBT backtesting expert. Use when user asks to backtest strategies, create entry/exit signals, analyze portfolio performance, optimize parameters, fetch historical data, use VectorBT/vectorbt, compare strategies, position sizing, equity curves, drawdown charts, or trade analysis. Also triggers for openalgo.ta…

200 1mo ago A 85 tokens

fix-ci

08

CliMA/ClimaAtmos.jl

Skill Claude CodeCodex

Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…

125 3d ago A 84 tokens original Apache-2.0

EtaYang10th/spark-skills

Skill Claude CodeCodex

Solve MATPOWER-format grid dispatch tasks by building a DC optimal power flow with generator energy dispatch, spinning reserve allocation, transmission constraints, and structured JSON reporting.

111 2mo ago A 42 tokens

memory-estimation

11

Red-Hat-AI-Innovation-Team/training_hub

Skill Claude CodeCodex

Use when the user wants to estimate GPU memory (VRAM) requirements for a training configuration, check if a model will fit on their GPUs, or plan GPU allocation for training.

92 4d ago A 40 tokens original Apache-2.0

setup-guide

12

Red-Hat-AI-Innovation-Team/training_hub

Skill Claude CodeCodex

Use when the user wants to set up LLM training for the first time, or when traininghub is not yet installed/configured in the current environment.

92 4d ago A 35 tokens original Apache-2.0

training-hub-guide

13

Red-Hat-AI-Innovation-Team/training_hub

Skill Claude CodeCodex

Guides users through LLM post-training with Training Hub, including installation, algorithm selection (SFT, OSFT, LoRA), hyperparameter tuning, troubleshooting OOM errors, interpreting loss curves, and leveraging backend-specific features. Use when the user is working with traininghub, fine-tuning language models…

92 4d ago A 88 tokens original Apache-2.0

tao-run-automl

14

NVIDIA-TAO/tao-skill-bank

Skill Claude CodeCodex

Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation…

86 3d ago A 235 tokens original Apache-2.0

skill-opt-lite

15

rexleimo/aios

Skill Claude CodeCodex

Train and optimize skill documents using the SkillOpt methodology — the agent acts as both target and optimizer, running tasks, reflecting on failures, proposing edits, and validating improvements in a self-contained training loop. TRIGGER: optimize skill, train skill, improve skill, skill training, skill…

52 2d ago A 79 tokens original MIT

contentful/skills

Skill Claude CodeCodex

Synchronize the Contentful Optimization SDK's public API, behavior, and implementation guidance into concise, runtime-specific references for the contentful-personalization skill. Use when the optimization repository or SDK documentation changes, when modern SDK guidance appears stale, or when validating that the…

39 2d ago A 64 tokens original MIT

skill-authoring

18

contentful/skills

Skill Claude CodeCodex

Create, modify, review, and fix Agent Skills in the contentful/skills repository. Use when creating a new skill from scratch, editing an existing SKILL.md or package.json, reviewing skill structure for correctness, fixing skill formatting or naming issues, or looking up skill conventions. Also triggers on "create a…

39 2d ago A 166 tokens original MIT

contentful/skills

Skill Claude CodeCodex

Write and run Contentful content model migration scripts using the contentful-migration library and the Contentful CLI. Covers creating, editing, and deleting content types and fields, validations, editor interface configuration, editor layouts, sidebar widgets, entry transformations, tags, annotations, and the…

39 2d ago A 199 tokens original MIT

PBI-Guy/Power-BI-Optimization-Skill

Skill Claude CodeCodex

Expert Power BI optimization: DAX performance, semantic model design, report UX, query performance. Analyzes measures, relationships, visuals, storage modes. Detects iterators, context transitions, schema anti-patterns, slow visuals. Provides before/after code, metrics, prioritized fixes. Supports Import, DirectQuery…

23 2mo ago A 135 tokens original MIT

claude-md-optimizer

21

wrsmith108/claude-md-optimizer

Skill Claude CodeCodex

Optimize oversized agent instruction files using progressive disclosure. Handles CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex / GitHub Copilot agents), and copilot-instructions.md (GitHub Copilot). Auto-detects all three formats in your repo, analyzes content tiers, creates sub-documents using each format's native…

22 2mo ago A 128 tokens

ai-md

22

sstklen/ai-md

Skill Claude CodeCodex

AI.MD — Convert any human-written CLAUDE.md into AI-native structured format. Your CLAUDE.md is read by AI every single turn, not by you — so write it in AI's language. Battle-tested: 5 rounds, 4 models (GPT-5.3, Gemini 2.5 Pro, Grok-4, Claude Opus 4.6). Structured-label format raised Codex compliance from 6/8 → 8/8…

11 5mo ago B 173 tokens copy · 88% MIT