Coding standards, frameworks, refactoring, and code review (16.8K skills)
Diagnose problems in OMC or Claude Code sessions using logs, execution traces, saved state, and focused reproduction. Receive a clear account of the failure, a supported cause hypothesis, and the smallest next corrective action.
Review incoming GitHub issues and pull requests, verify claims, and organize evidence alongside existing decisions. Prepare unresolved choices with recommendations and consequences for maintainers, then carry out actions covered by verified authorization without merging changes.
Sets up shared project rules and a glossary so people and AI agents work from the same context. It preserves existing documents, introduces additional records when needed, and provides a check mode to audit inconsistencies.
Set up, refresh, or repair oh-my-claudecode after a plugin, npm, or local development installation. Configure project or global instructions, status display, and team defaults, with quick updates for existing setups and support for resuming interrupted configuration.
Updates an Ant Design Pro project by comparing it with the latest official template. It merges dependency and configuration changes while preserving custom pages and business logic, then checks for deprecated APIs and build errors.
Helps build and maintain Ant Design interfaces by checking component options, examples, and theme settings. It also supports debugging, version migrations, and project scans to identify deprecated code and configuration issues.
Use the CopilotKit CLI to check app connections, credentials, and agent responses before investigating code. It also guides project creation, integration into existing apps, hosted project selection, typed agent identifier generation, and thread history imports.
Creates a new domain-specific skin for reskinnable-demo, combining branding, layouts, pages, data, tools, and an agent. Structures live sales demonstrations around visible AI interactions, including generated interfaces, shared state, confirmations, and memory features.
Develop and debug CopilotKit Inspector interfaces in a dedicated local workbench. It guides baseline screenshots, visual checks after each change, and additional narrow-screen or theme checks when layout or contrast is involved.
Set up an agent that replies in Slack or Microsoft Teams using CopilotKit's guided CLI workflow. It covers project preparation, agent creation, channel configuration, a persistent host process, and verification with a real message.
Guides development of MCP servers that let AI access external actions and data using mcp-use. Covers project setup, tools, reusable prompts, interactive React interfaces, authentication, validation, and deployment through task-specific reference guides.
Helps integrate CopilotKit into an app by consulting current documentation and source code. Covers chat interfaces, agent connections, shared state, and troubleshooting, with guidance on checking configuration and avoiding incompatible API versions.
Implement and customize managed CopilotKit Channels so agents can reply in Slack or Microsoft Teams. It covers channel handlers, persistent runtime connections, Teams setup, and checks for silent failures such as missing permissions or incompatible package versions.
Connect a local CopilotKit agent to Slack through a managed Intelligence Channel. The skill guides dedicated Slack app creation, credential setup, runtime configuration, and checks that a human mention receives an actual reply.
Build MCP servers, which expose tools and data to AI agents, with mcp-use. The material covers server functions, reusable prompts, and interactive React widgets, but this skill is deprecated and points to mcp-app-builder as its replacement.
Guides development of ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK, covering server tools, React interfaces, and shared state. This skill is deprecated and directs users to mcp-app-builder.
Add or verify model support in SGLang's Rust processor so chat requests produce the same prompt text and token IDs as Python. Use reference-generated test cases to find differences in tools, reasoning settings, conversation history, and errors.
Add a CUDA/C++ GPU operation to sgl-kernel using AOT, meaning compilation before use. Follow the implementation through PyTorch registration, Python API exposure, SGLang integration, correctness tests, and benchmarks that account for cache reuse.
Guide changes to SGLang runtime configuration and shared process state. Identify where resolved settings, runtime flags, resources, and per-forward state belong, and use the documented access patterns and checks when developing or testing.
Investigate CUDA crashes in SGLang using logs and inputs saved before execution. Inspect tensor shapes, data types, and numerical anomalies, with guidance for separate process logs and additional CUDA debugging tools.
Apply consistent names to SGLang speculative decoding code, which verifies draft tokens to generate text. Distinguish tokens with or without the bonus token, counts, counters, and arrays when adding identifiers, renaming code, or reviewing changes.
Add, rename, or review SGLang environment variables using consistent definitions, types, names, and access methods. The skill also guides migration from old names and temporary test overrides that restore the original values afterward.
Guide changes and reviews for SGLang’s Scheduler, TokenizerManager, and ModelRunner classes. Keep initialization in small, replaceable helpers and separate computation from coordination so large classes retain clear responsibilities and explicit dependencies.
Add a diffusion model or Diffusers generation pipeline to SGLang. Examine reference code, choose a suitable pipeline structure, reuse existing components, and implement model settings and processing stages, with guidance for later multi-GPU support.