UCSB-NLP-Chang/Skill-Usage

This repository also configures its own agents. See what Skill-Usage tells them →

48Stars on the repository
197Mods indexed here, across every type
5mo agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

This skill should be considered when you need to answer reflow machine maintenance questions or provide detailed guidance based on thermocouple data, MES data or defect data and reflow technical handbooks. This skill covers how to obtain important concepts, calculations, definitions, thresholds, and others from the…

not rated 48 5mo ago A 77 tokens

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

This skill should be considered when you need to repair an infeasible or non-optimal flexible job scheduling planning schedule into a downtime-feasible, precedence-feasible one while keep no worse policy budget.

not rated 48 5mo ago A 52 tokens

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Extract key frames (I-frames) from video files using FFmpeg command line tool. Use this skill when the user needs to pull out keyframes, thumbnails, or important frames from MP4, MKV, AVI, or other video formats for analysis, previews, or processing.

not rated 48 5mo ago A 64 tokens

image_editing

100

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Comprehensive command-line tools for modifying and manipulating images, such as resize, blur, crop, flip, and many more.

not rated 48 5mo ago B 29 tokens

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Define custom distance/similarity metrics for clustering and ML algorithms. Use when working with DBSCAN, sklearn, or scipy distance functions with application-specific metrics.

not rated 48 5mo ago A 36 tokens

parallel-processing

103

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Parallel processing with joblib for grid search and batch computations. Use when speeding up computationally intensive tasks across multiple CPU cores.

not rated 48 5mo ago A 28 tokens

pareto-optimization

104

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Multi-objective optimization with Pareto frontiers. Use when optimizing multiple conflicting objectives simultaneously, finding trade-off solutions, or computing Pareto-optimal points.

not rated 48 5mo ago A 36 tokens

mhc-algorithm

105

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with doubly stochastic matrices via Sinkhorn-Knopp algorithm. Based on DeepSeek's 2025 paper (arXiv:2512.24880).

not rated 48 5mo ago A 64 tokens

modal-gpu

106

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading inside functions, and result handling.

not rated 48 5mo ago A 51 tokens

nanogpt-training

107

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Train GPT-2 scale models (124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.

not rated 48 5mo ago A 61 tokens

FFmpeg Media Info

110

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Analyze media file properties - duration, resolution, bitrate, codecs, and stream information.

not rated 48 5mo ago A 21 tokens

TTS Audio Mastering

113

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Practical mastering steps for TTS audio: cleanup, loudness normalization, alignment, and delivery specs.

not rated 48 5mo ago A 27 tokens

docx

114

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Word document manipulation with python-docx - handling split placeholders, headers/footers, nested tables.

not rated 48 5mo ago A 22 tokens

file-organizer

115

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

not rated 48 5mo ago A 46 tokens

planning-with-files

116

UCSB-NLP-Chang/Skill-Usage

Skill Claude Code

Implements Manus-style file-based planning for complex tasks. Creates taskplan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

not rated 48 5mo ago A 47 tokens

memory-optimization

118

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Optimize Python code for reduced memory usage and improved memory efficiency. Use when asked to reduce memory footprint, fix memory leaks, optimize data structures for memory, handle large datasets efficiently, or diagnose memory issues. Covers object sizing, generator patterns, efficient data structures, and memory…

not rated 48 5mo ago A 60 tokens

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Transform sequential Python code into parallel/concurrent implementations. Use when asked to parallelize Python code, improve code performance through concurrency, convert loops to parallel execution, or identify parallelization opportunities. Handles CPU-bound (multiprocessing), I/O-bound (asyncio, threading), and…

not rated 48 5mo ago A 68 tokens

workload-balancing

120

UCSB-NLP-Chang/Skill-Usage

Skill Claude CodeCodex

Optimize workload distribution across workers, processes, or nodes for efficient parallel execution. Use when asked to balance work distribution, improve parallel efficiency, reduce stragglers, implement load balancing, or optimize task scheduling. Covers static/dynamic partitioning, work stealing, and adaptive load…

not rated 48 5mo ago A 63 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: