Turn repeated AI commands into safe shell aliases, then promote a stable multi-step prompt into a small CLI with explicit inputs, visible configuration, and reproducible output.
John turns frequently used Claude flags into short shell aliases, then demonstrates a custom CLI that wraps Gemini prompts in a fast terminal questionnaire for generating design concepts.
A memorable command that runs a repeatable AI task with validated inputs, predictable output, and no hidden destructive flags or secrets.
Google AI assistant
Claude for coding tasks
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
List commands you use repeatedly and choose only stable, low-risk sequences for aliases. Put complex quoting or project logic in a script rather than a one-line alias.
Review these recent shell commands and identify repeatable, non-destructive candidates for aliases or functions. Exclude credentials, bypass-permission defaults, deletion, publishing, and environment-specific absolute paths. Explain the proposed expansion for each.
Choose a repeated AI task with consistent inputs and output, such as producing several design concepts from a website type, page, style, theme, and reference.
Build a small CLI around the installed AI tool or API. Keep model and prompt templates in versioned configuration, read credentials from the environment, and support help and dry-run output.
Prompt for only the variables that change the result. Validate required values, constrain enumerated choices, show defaults, and print the output destination before the API call.
Collect: website type, page, visual direction, viewport, theme, optional reference, number of variations, and output directory. Before running, print the chosen model, sanitized prompt summary, variation count, and destination. Require confirmation only when files would be overwritten.
Run the CLI against representative inputs, save outputs with stable filenames and metadata, and return useful errors for authentication, rate limits, invalid inputs, and partial generation.
Generate [count] distinct concepts for a [website type], [page], in a [visual direction] style for [viewport], using [theme] and [reference]. Save each output plus model, prompt version, and input metadata under [directory]. Do not overwrite existing files unless explicitly requested.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
Log your workouts effortlessly without ever opening a spreadsheet. This workflow uses the Claude mobile app to parse a simple voice note and automatically update your workout tracking spreadsheet in the background.
Create a custom email management interface within Claude to read, triage, and draft replies without opening the Gmail tab. This workflow helps you reclaim focus and compound your learnings by training your AI on every interaction.
Build a fully automated system in Claude to generate personalized, interactive HTML proposals and client onboarding materials, saving hours on administrative work and creating a high-touch experience.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.