“Code generation”

Hardware-aware code generation for TuyaOpen embedded projects.

Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent…

Also use for agentic data engineering pipelines, code generation agents, agent-powered CLI tools, MCP server development, or any system where an AI model…

Use when implementing, optimizing, or reviewing performance-critical C#/.NET scalar or SIMD hot paths whose throughput depends on RyuJIT code generation

Remove AI-generated code slop and clean up code style.

Remove AI-generated code slop from the branch's diff and clean up code style.

Generate TypeScript/JavaScript code that reads/decodes AND writes/encodes ClickHouse RowBinary streams for the ClickHouse HTTP server.

Review generated code against the approved LLD to verify structural conformance.

Use after writing or modifying non-trivial application code, before final verification, to find and fix common AI-generated code problems.

Generate documentation for code — use when asked to document a module, generate API docs, create a README for code, or write reference documentation.

Security review at three points in the workflow — threat model the design before implementation, SAST scan the generated code before architect code review…

SIMULATE animation end-to-end BEFORE generating code — trace every user interaction, state change, and frame to predict behavior and catch edge cases.

Remove AI-generated code slop from the current diff.

Delegate boilerplate code generation to a cheaper worker model.

Generate complete, runnable Volcengine SDK code and provide SDK configuration guidance.

Generates Angular code and provides architectural guidance.

Build and debug Nimony compile-time plugins for code generation and DSL rewrites.

Quality gates, test automation, and feedback loops for AI-generated code.

Use when you must generate predictable code that follows the patterns of an existing file (tests, config, type stubs, boilerplate).

Corrects the wrong defaults a model has when standing up self-hosted SonarQube Server as a continuous gate on AI-generated code, verified against…

Diagnoses failures *specific to SPViz*, regarding its DSLs, code generation, generated project models, generated language servers, and generated visualization…

Clean up generated code changes — strip slop (dead code, one-use abstractions, redundant guards, comment noise, unnecessary effects), fix what the change…

Use when cleaning AI-generated code from a branch diff before commit.

Use Webflow MCP server + AI Assistant — AI agents design pages, manage CMS, run SEO/AEO audits, and generate code.