Accessibility & Responsive PromptsCheatsheet
Make accessibility and responsiveness explicit requirements so AI builds inclusive, adaptive UI instead of div-soup you retrofit.
Make accessibility and responsiveness explicit requirements so AI builds inclusive, adaptive UI instead of div-soup you retrofit.
Prompt agents to work in a plan-act-verify loop with scope limits and a feedback signal so they self-correct instead of drifting.
Break a coding prompt into its six working parts, role, task, context, constraints, format, and examples, and learn what each one does.
Prompt API endpoints and backend logic with the contract spelled out: methods, schemas, validation, errors, and auth.
Compare the three kinds of AI coding assistant, chat, inline, and agent, and learn which to reach for and how prompting changes between them.
Give the model the signatures, types, data shapes, and errors it needs so its code fits your real project, not a generic one.
Use AI as a first-pass reviewer: prompt focused passes for bugs, security, and clarity, with ranked, actionable findings.
Set explicit rules, what to use, what to avoid, and what not to touch, so the model stays inside safe, correct bounds.
Encode your project's rules once in a context file (CLAUDE.md, AGENTS.md, .cursor/rules) so every prompt starts with them.
Understand the context window as a finite budget, what counts against it, and how to spend it on the code and facts that matter.
Prompt styling that uses your approach and tokens, describes layout in intent, and handles responsive and theming needs.
Prompt queries and migrations with the real schema, the engine, and safety rules so you avoid slow, wrong, or destructive SQL.
Turn a bug into a tight debugging prompt: the exact error, the code that threw, the input, and what you already tried.
Split a large request into ordered, independently verifiable steps so each prompt is small enough to get right.
Prompt the model to write docs grounded in the real code: accurate docstrings, READMEs, and commit messages for a stated audience.
Use AI to onboard into unfamiliar code: trace data flow, decode dense logic, and map a codebase at the right level of detail.
Use input/output examples to lock in a pattern the model should follow, and know when zero-shot is enough.
Point the model at the real files and symbols it needs so answers match your codebase instead of a generic guess.