All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,957
- 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 browserBrowse code review & quality skills
Showing 11,305–11,328 of 15,957 skills
- Coca Contrastive Captioners Are Image Text Foundation Models Arxiv 2205 01917v2Use this skill when you want to combine contrastive and captioning objectives on the same image-text data for a unified vision-language foundation model. Avoid it when you only need one objective (contrastive or captioning) and not both.Votes: 0GitHub stars: 9
- Chameleon Mixed Modal Early Fusion Foundation Models Arxiv 2405 09818v1Use this skill when you want to train a mixed-modal model using early fusion of image and text tokens for both understanding and generation. Avoid it when you only need understanding (not generation) or cannot tokenize images.Votes: 0GitHub stars: 9
- Cambrian 1 A Fully Open Vision Centric Exploration Of Multimodal Llms Arxiv 2406 16860v1Use this skill when you want a data-centric approach to VLM design that systematically evaluates vision encoders, connectors, and instruction data. Avoid it when you want a simple plug-and-play VLM without extensive ablation studies.Votes: 0GitHub stars: 9
- Scienceqa Learn To Explain Multimodal Reasoning Via Thought Chains For Science Question Answering Arxiv 2209 09513v2Use this skill when you need a multimodal science QA dataset with detailed explanations and chain-of-thought reasoning for training VLMs. Avoid it when you do not need science reasoning or chain-of-thought data.Votes: 0GitHub stars: 9
- Referring Expression Comprehension A Survey Of Methods And Datasets Arxiv 2007 09554v2Use this skill when you need an overview of referring expression datasets (RefCOCO, RefCOCO+, RefCOCOg) for VLM grounding training. Avoid it when you already know the referring expression dataset landscape.Votes: 0GitHub stars: 9
- Openimages V7 Extended Dataset With Bounding Boxes And Visual Relationships Crossref Openimages 2020Use this skill when you need a massive multi-label detection dataset with 9M images, 600 categories, and visual relationship annotations. Avoid it when COCO or Objects365 provide sufficient detection coverage.Votes: 0GitHub stars: 9
- Flamingo A Visual Language Model For Few Shot Learning Arxiv 2204 14198v2Use this skill when you need to collect and train on interleaved image-text web data for few-shot visual learning. Avoid it when you only have paired image-caption data without interleaved document structure.Votes: 0GitHub stars: 9
- Vibe Flow独立开发者 Web/SaaS 项目专属 Vibe Coding 全流程。Invoke when starting a new web product project to run a complete 14-skill pipeline from idea to launch, with controlled feedback loops.Votes: 0GitHub stars: 8
- SuperpowersComprehensive skill framework from obra/superpowers for AI-assisted development workflows, covering planning, implementation, debugging, code review, and moreVotes: 0GitHub stars: 8
- Golang Best PracticesMUST be used for Go tasks. Covers Go 1.21+, standard library, Go modules, concurrency, performance optimization, testing, and WebAssembly (GOOS=js, GOARCH=wasm). Load for any .go files work.Votes: 0GitHub stars: 8
- Skill Quality ReviewerThis skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report". Evaluates local skills across description quality, content organization, writing style, and structural integrity.Votes: 0GitHub stars: 2
- Command DevelopmentThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.Votes: 0GitHub stars: 2
- Code Review ExcellenceMaster effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.Votes: 0GitHub stars: 2
- Architecture DesignUse ONLY when creating NEW registrable components in ML projects that require Factory/Registry patterns. ✅ USE when: - Creating a new Dataset class (needs @register_dataset) - Creating a new Model class (needs @register_model) - Creating a new module directory with __init__.py factory - Initializing a new ML project structure from scratch - Adding new component types (Augmentation, CollateFunction, Metrics) ❌ DO NOT USE when: - Modifying existing functions or methods - Fixing bugs in existi...Votes: 0GitHub stars: 2
- Zoom OutCodebase orientation skill: navigate unfamiliar code by ascending abstraction layers to map modules, callers, and domain vocabulary. Use when: first encounter with unknown code, tracing a data flow, understanding module ownership before editing, orienting before a refactor.Votes: 0GitHub stars: 2
- Write SkillMeta-skill for creating high-quality SKILL.md files. Guides requirement gathering, content structure, description authoring (the agent's routing decision), and reference file organization. Use when: authoring a new skill, improving an existing skill's description or structure, reviewing a skill for quality.Votes: 0GitHub stars: 2
- Workflow Review DeepOrchestrate a multi-agent workflow to perform a deep-dive security, correctness, and architecture review.Votes: 0GitHub stars: 2
- To PrdConverts conversation context into a structured Product Requirements Document (PRD) and publishes it to the project issue tracker. Do NOT interview the user — synthesize what is already known. Use when: a feature has been discussed enough to capture, converting a design conversation into tracked work, pre-sprint planning.Votes: 0GitHub stars: 2
- Science Museum EducatorExpert Science Museum Educator with 15+ years in informal science learning, exhibit interpretation, and public engagement. Specializes in inquiry-based teaching, hands-on program design, and visitor-centered experiences. Use when: science-education, museum-programs, exhibit-guides, STEM-outreach.Votes: 0GitHub stars: 2
- Religious OfficerProfessional religious officer specializing in spiritual guidance, religious ceremony leadership, community ministry, and interfaith dialogue. Use when providing spiritual counsel, organizing religious events, or serving diverse faith communities. Use when: spiritual-care, religious-services, community-ministry, chaplaincy, pastoral-care.Votes: 0GitHub stars: 2
- PerfumerExpert-level Perfumer skill with deep knowledge of fragrance composition, olfactory families, scent pyramid construction, and fragrance chemistryVotes: 0GitHub stars: 2
- Mechanical EngineerLicensed Professional Mechanical Engineer (PE) specializing in HVAC, plumbing, fire protection, and building automation systems. Expert in load calculations, energy modeling, and ASHRAE standards. 10+ years designing commercial, healthcare, and industrial MEP systems. Use when: mechanical engineering, HVAC design, plumbing, fire protection, energy modeling, building systems.Votes: 0GitHub stars: 2
- Escape Room DesignerMaster escape room designer specializing in puzzle mechanics, narrative integration, thematic world-building, and player experience optimizationVotes: 0GitHub stars: 2
- End To End Autonomous ResearcherExpert-level End-to-End Autonomous Driving Researcher specializing in UniAD/VAD/DriveLM architectures, BEV perception, transformer-based world models, and rigorous closed-loop evaluation on nuScenes and Waymo Open Dataset benchmarks. Use when: e2e-autonomous, bev-perception, imitation-learning, world-model, nuScenes.Votes: 0GitHub stars: 2