openclaw-skills-registry

Weekly Focus Engineering analysis using ActivityWatch data. Use when analyzing app usage patterns, detecting context switching problems, identifying "death loops" (repetitive app switching), calculating focus scores, or creating weekly productivity reviews.

WCAG 2.2 AA conformance auditor. Systematically verifies success criteria through automated, interactive, and manual testing methods.

Implement features from spec documents (context/doc required)

PR review for bugs, security & quality (requires PR URL)

Brutally honest roasts of your code with fixes

Accessibility improvement planning support. Generates organizational maturity assessment, phased roadmap, KPI design, and stakeholder persuasion materials.

WCAG audit planning support based on WAIC test guidelines. Helps determine audit scope, page selection method, and generates audit plan documents.

Accessibility review orchestrator. Analyzes web pages, code implementations, and design mockups from WCAG and WAI-ARIA APG perspectives. Automatically delegates to specialized sub-agents based on review target.

现代 C++ 专家，提供最佳实践代码实现、性能优化建议和深度技术解析。用户请求 C++ 开发、排错或优化时调用。

GitHub 使用专家，提供 Git 工作流、仓库管理、协作开发和 CI/CD 最佳实践指导。用户遇到 Git/GitHub 使用与排障时调用。

Python 编程专家，提供 Pythonic 代码实现、性能优化和最佳实践指导。用户请求 Python 开发、调试或规范建议时调用。

Three.js 交互：Raycaster、鼠标/触摸输入、对象拾取、高亮与控制器集成。用户需要点击/拖拽/选择等交互时调用。

Three.js 几何体：内置几何、BufferGeometry、自定义属性、Instancing。用户需要创建/优化网格几何时调用。

Three.js 加载器：GLTF/GLB、纹理加载、异步与缓存、常见坑（色彩空间/坐标系/资源路径）。用户需要加载模型或资源时调用。

Three.js 动画：AnimationMixer、关键帧、骨骼/蒙皮、morph targets 与混合。用户需要播放或混合模型动画时调用。

Three.js 后处理：EffectComposer、常见 Pass（Bloom/DOF 等）、屏幕特效与自定义 Pass。用户需要屏幕后处理链路时调用。

Three.js 基础能力：场景/相机/渲染器、坐标系、Object3D 层级与变换。用户需要搭建 3D 场景或理解基础概念时调用。

Three.js 材质：PBR（Standard/Physical）、基础材质、透明度、贴图与渲染状态。用户需要选择/调试材质效果时调用。

Three.js 灯光：灯光类型、阴影、环境光照与常用调试辅助。用户需要布光或处理阴影问题时调用。

Three.js 着色器：GLSL 基础、ShaderMaterial、uniforms、常用坐标空间与自定义效果。用户需要自定义视觉效果时调用。

Three.js 纹理：TextureLoader、UV、wrap/repeat、色彩空间、环境贴图与渲染目标。用户需要加载/调试贴图时调用。

当用户需要设计 LLM 评测方案、构建测试集、进行模型质量保障时使用此技能。触发关键词：LLM 测试、模型评测、提示词工程、回归测试、红队测试、幻觉检测、RAG 测试、Agent 测试、A/B 测试、LLM-as-a-Judge。适用于模型开发和应用落地的质量保障场景。

当用户需要设计深度学习模型、进行训练调优、解读论文或解决工程实践问题时使用此技能。触发关键词：深度学习、神经网络、模型训练、过拟合、梯度消失、PyTorch、TensorFlow、预训练模型、微调、模型部署、推理优化、CV(计算机视觉)、NLP(自然语言处理)、强化学习。适用于深度学习建模、训练、调试和部署的全流程场景。

当用户需要解决算法竞赛题目时使用此技能。适用于 LeetCode、Codeforces、AtCoder 等平台的题目求解、算法优化、复杂度分析。触发关键词：算法题、刷题、竞赛、时间复杂度、数据结构实现、TLE(超时)、MLE(内存超限)。

当用户需要系统架构设计、技术选型或架构评审时使用此技能。触发关键词：系统设计、架构方案、技术选型、微服务、分布式系统、高可用、扩展性、CAP定理、架构权衡、重构方案。适用于需要高层设计决策的场景，不适用于具体代码实现。

Use this skill when user needs to solve competitive programming problems. Applicable to LeetCode, Codeforces, AtCoder and similar platforms. Triggers include: algorithm problem, coding challenge, time complexity analysis, data structure implementation, TLE (Time Limit Exceeded), MLE (Memory Limit Exceeded).

Use this skill when user needs to design deep learning models, perform training optimization, interpret papers, or solve engineering practice issues. Trigger keywords: deep learning, neural networks, model training, overfitting, gradient vanishing, PyTorch, TensorFlow, pretrained models, fine-tuning, model deployment, inference optimization, CV (Computer Vision), NLP (Natural Language Processing), reinforcement learning. Applicable to full-cycle scenarios of deep learning modeling, training, debugging, and deployment.

Git/GitHub expert for workflows, repo management, PRs, and Actions CI/CD. Invoke for Git troubleshooting, collaboration, or automation setup.

Use this skill when user needs to design LLM evaluation strategies, build test datasets, or ensure model quality. Trigger keywords: LLM testing, model evaluation, prompt engineering, regression testing, red teaming, hallucination detection, RAG testing, Agent testing, A/B testing, LLM-as-a-Judge. Applicable to quality assurance in model development and application deployment.

Use this skill when user needs system architecture design, technology stack selection, or architecture review. Trigger keywords: system design, architecture proposal, tech stack, microservices, distributed systems, high availability, scalability, CAP theorem, architecture tradeoffs, refactoring plan. Applicable to high-level design decisions, not specific code implementation.