Code Review & Quality

Code review, refactoring, debugging, maintainability, and engineering quality

skills in category: 15,957
pages available: 665

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse code review & quality skills

Showing 11,281–11,304 of 15,957 skills

Deita What Makes Good Data For Alignment Arxiv 2312 15685v2AUse this skill when you want to select the best alignment data from a large pool using complexity and quality scoring. Avoid it when you do not have a large pool of alignment data to select from.code-qualitygoperformanceVotes: 0GitHub stars: 9
Curriculum Learning Crossref Icml 2009 CurriculumAUse this skill when you want to order training examples from easy to hard during training to improve convergence and final performance. Avoid it when random data ordering works well for your task.code-qualitygoperformanceVotes: 0GitHub stars: 9
Are More Llm Calls All You Need Towards Scaling Laws For Compound Ai Systems Arxiv 2403 02419v2AUse this skill when you want to understand scaling behavior when using multiple LLM calls in compound systems for tasks like data generation or evaluation. Avoid it when you use single LLM calls and do not build compound systems.code-qualitygoawsVotes: 0GitHub stars: 9
Vlmo Unified Vision Language Pre Training With Mixture Of Modality Experts Arxiv 2111 02358v3AUse this skill when you want to train a unified VLM using mixture-of-modality-experts that can serve as both dual-encoder and fusion-encoder. Avoid it when you prefer simpler single-mode architectures.code-qualitygoVotes: 0GitHub stars: 9
Video Llama An Instruction Tuned Audio Visual Language Model For Video Understanding Arxiv 2306 02858v4AUse this skill when you want to create instruction data for a VLM that understands both visual and audio content in videos. Avoid it when you only need visual understanding without audio.code-qualitygoVotes: 0GitHub stars: 9
Tokenflow Unified Image Tokenizer For Multimodal Understanding And Generation Arxiv 2412 03069v2AUse this skill when you want a unified image tokenizer that supports both understanding and generation tasks in VLMs. Avoid it when separate tokenizers for understanding and generation work for you.code-qualitygoVotes: 0GitHub stars: 9
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Sigmoid Loss For Language Image Pre Training Arxiv 2303 15343v4AUse this skill when you want a contrastive loss that handles noisy image-text pairs better by using sigmoid instead of softmax. Avoid it when you are already using softmax contrastive loss successfully on clean data.code-qualitygoperformanceVotes: 0GitHub stars: 9
Siglip 2 Multilingual Vision Language Encoders With Improved Semantic Understanding Localization And Dense Features Arxiv 2502 14786v1AUse this skill when you want an improved vision-language encoder with better localization, dense features, and multilingual support. Avoid it when SigLIP v1 or CLIP is sufficient for your needs.code-qualitygoVotes: 0GitHub stars: 9
Scaling Vision With Sparse Mixture Of Experts Arxiv 2106 05974v1AUse this skill when you want to scale vision models efficiently using sparse Mixture-of-Experts for handling more training data per compute. Avoid it when dense models are sufficient for your scale.code-qualitygoawsVotes: 0GitHub stars: 9
Qwen Vl A Versatile Vision Language Model For Understanding Localization Text Reading And Beyond Arxiv 2308 12966v3AUse this skill when you need a multi-stage data pipeline covering pretraining, multi-task training, and instruction tuning with grounding and OCR data. Avoid it when you need only basic image understanding without grounding or OCR capabilities.code-qualitygoperformanceVotes: 0GitHub stars: 9
Mplug Owl2 Revolutionizing Multi Modal Large Language Model With Modality Collaboration Arxiv 2311 04257v2AUse this skill when you want to improve VLM training through modality-adaptive modules and curated multi-task data that promotes vision-language collaboration. Avoid it when you are using a simple vision-language projection without modality adaptation.code-qualitygoperformanceVotes: 0GitHub stars: 9
Mplug Owl Modularization Empowers Large Language Models With Multimodality Arxiv 2304 14178v2AUse this skill when you want a modular VLM training approach using visual abstractor and two-stage training on alignment then instruction data. Avoid it when you prefer simpler projection approaches.code-qualitygoVotes: 0GitHub stars: 9
Llava Next Video Scaling Video Understanding To Strong Image Level Performance Arxiv 2410 02713v1AUse this skill when you want to transfer strong image understanding from LLaVA-NeXT to video through efficient frame sampling and video-specific data. Avoid it when you are building a video-from-scratch VLM.code-qualitygoperformanceVotes: 0GitHub stars: 9
Llava Next Improved Reasoning Ocr And World Knowledge Arxiv 2401 06209v1AUse this skill when you want to scale up instruction tuning data with higher quality and diversity for improved VLM reasoning. Avoid it when you have limited compute and cannot handle dynamic high-resolution image processing.code-qualitygobackendVotes: 0GitHub stars: 9
Llama Adapter Efficient Fine Tuning Of Language Models With Zero Init Attention Arxiv 2303 16199v2AUse this skill when you want to efficiently add visual instruction-following to LLaMA using lightweight adapters with zero-initialized attention. Avoid it when full fine-tuning is feasible or you prefer other PEFT methods.code-qualitygoperformanceVotes: 0GitHub stars: 9
Instructblip Towards General Purpose Vision Language Models With Instruction Tuning Arxiv 2305 06500v2AUse this skill when you want to curate multi-task instruction data and make the vision encoder instruction-aware for better VLM fine-tuning. Avoid it when you have a single task and do not need instruction-conditioned visual feature extraction.code-qualitygoperformanceVotes: 0GitHub stars: 9
Improving Multimodal Learning With Multi Loss Gradient Modulation Arxiv 2405 07930v2AUse this skill when you want to optimize multi-task VLM training by dynamically modulating gradients from different loss functions. Avoid it when single-loss training is sufficient.code-qualitygoperformanceVotes: 0GitHub stars: 9
Grounding Dino Marrying Dino With Grounded Pre Training For Open Set Object Detection Arxiv 2303 05499v4AUse this skill when you need an open-set object detector trained on grounded text-image data to detect any object described in natural language. Avoid it when you only need closed-set detection on fixed categories.code-qualitygoexpressVotes: 0GitHub stars: 9
Git A Generative Image To Text Transformer For Vision And Language Arxiv 2205 14100v5AUse this skill when you want a simple generative image-to-text model trained on large-scale image-text data with minimal architectural complexity. Avoid it when you need a more complex architecture with cross-attention or dual encoders.code-qualitygogitVotes: 0GitHub stars: 9
Direct Preference Optimization Your Language Model Is Secretly A Reward Model Arxiv 2305 18290v2AUse this skill when you want to align a language/vision-language model using preference data without training a separate reward model. Avoid it when you prefer RLHF with explicit reward models or do not have preference data.code-qualitygoVotes: 0GitHub stars: 9
Dino Emerging Properties In Self Supervised Vision Transformers Arxiv 2104 14294v2AUse this skill when you want to train a self-supervised ViT that learns rich visual features with emerging object segmentation properties. Avoid it when CLIP-supervised features are sufficient for your VLM.code-qualitygoVotes: 0GitHub stars: 9
Data Juicer A One Stop Data Processing System For Large Language Models Arxiv 2309 02033v5AUse this skill when you need a configurable data processing pipeline with 50+ operators for cleaning, filtering, and preparing LLM/VLM training data. Avoid it when you have a simple dataset that does not need complex multi-stage processing.code-qualitygodebuggingVotes: 0GitHub stars: 9
Convnext V2 Co Designing And Scaling Convnets With Masked Autoencoders Arxiv 2301 00808v2AUse this skill when you want to pre-train ConvNet vision encoders using masked autoencoder self-supervised learning for VLM pipelines. Avoid it when ViT-based encoders are preferred.code-qualitygoVotes: 0GitHub stars: 9
Cogvlm Visual Expert For Pretrained Language Models Arxiv 2311 03079v2AUse this skill when you want to add visual expert modules to an LLM with a two-stage data pipeline covering alignment and multi-task training. Avoid it when you are using a simpler linear projection approach.code-qualitygoperformanceVotes: 0GitHub stars: 9