Hire an AI terminal interface integration designer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A fit check that says if SwiftTerm and your setup match
• A picture in words of how the view, the connection and the keys connect
• Integration steps in order
• Input and display choices, such as fonts, colors, selection and copy
• Notes on speed, memory and connection states
• An accessibility list and a test list

How it does the job well

• Use a SwiftTerm class or method name only if you can read its source or docs, or the user pasted it. Otherwise describe it by role and write "confirm in docs".
• Do not ask for passwords, private keys or server addresses. A fake host name is enough for planning.
• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You are adding an SSH or console screen to an iOS, macOS or visionOS app and have not picked a library setup yet.

• Fit check. Whether SwiftTerm and your platforms and connection match, and why.
• How the pieces connect. How the terminal view, your session code and the connection library pass text and keys.
• Integration steps. Build steps in order, with SwiftTerm method names marked for you to confirm in its docs.
• Input and display. Choices for keys, paste, selection, copy, fonts, colors and cursor.
• Speed and memory. Risks from fast output and long sessions, each with a plan.
• Connection states. What the screen shows when the link starts, fails, drops and returns.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Kent Beck would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Check the fit. It checks that you use SwiftTerm on an Apple platform and need the client side only.
• Place the view. It plans how the terminal view sits in your SwiftUI or UIKit screens and how it starts and stops.
• Bridge the stream. It plans how text from your SSH connection reaches the screen and how keystrokes and paste go back.
• Plan input and look. It covers special keys, selection, copy, fonts, colors and cursor style.
• Plan for speed and drops. It plans background reading, buffer size, scrolling, and what the screen shows when the link fails.
• Plan the checks. It covers accessibility and a test list for characters, long output and reconnects.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id terminal-integration-specialist only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/terminal-integration-specialist/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The platforms the app runs on, such as iOS, macOS or visionOS
• How the app is built, such as SwiftUI or UIKit
• What feeds the terminal, such as an SSH library and its name
• What the terminal must do, such as run commands, show logs or let users type
• Your current code or the symptom you see (optional)

Helpful context (optional)

• The SwiftTerm version and the SSH library you use.
• A short screen recording or description of the bug, if you have one.

Tools and access

• Claude, ChatGPT or Gemini: Any of them can plan from your code. One that can browse can check SwiftTerm's current docs.

Functions and deliverables

• Terminal interface integration designer: Plan a terminal view inside your iPhone, Mac or Vision Pro app with SwiftTerm, including SSH hookup, keyboard input, smooth text and a test list.
  • A fit check that says if SwiftTerm and your setup match
  • A picture in words of how the view, the connection and the keys connect
  • Integration steps in order
  • Input and display choices, such as fonts, colors, selection and copy
  • Notes on speed, memory and connection states
  • An accessibility list and a test list
  Source: Michael Sitarzewski and Agency Agents contributors.
• Interface styling and motion designer: Share a page brief, brand and project setup. Get interface code with considered type, spacing, depth and motion, plus checks to run.
  • Working page code
  • Type and colour choices
  • Motion and hover details
  • Ranked design fixes for a review
  Source: sickn33.
• Minimal editorial interface designer: Design a restrained, document-style interface. Get warm neutral colors, clear type, crisp borders and implementation code suited to the screen.
  • A design direction with fonts, colours, spacing and border rules
  • Code for your screen in the style
  • A ranked list of fixes, if you gave it a screen to review
  • A check that none of the banned elements slipped in
  • A short list of checks to run yourself, such as contrast and keyboard use
  Source: sickn33.
• Image and text matcher: Match pictures to words. Search a photo set by description, sort images into your own labels, or check what a picture shows, with no training.
  • Similarity scores for image and text pairs
  • Images sorted into your labels
  • Search results for a text query
  • Code you can run on your own files
  Source: Orchestra Research.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.
• Kent Beck: Plan a software change using Kent Beck’s recorded approach. List the cases, take small steps and keep code tidying separate from new behaviour.
  • Your problem worked on the way Kent Beck would: their questions, their method, their push-back
  • The answer or the work, in Kent Beck's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You are adding an SSH or console screen to an iOS, macOS or visionOS app and have not picked a library setup yet.
• Your terminal view shows wrong characters, lags when text pours in, or breaks on rotation or resize.
• You need keyboard shortcuts, paste, selection and copy to feel normal on a touch screen.
• You want to know what the screen should do when the connection drops, before you write the code.

Limits to check before starting

• You use a terminal library other than SwiftTerm. The plan will not fit.
• You are building a terminal on Android, Windows or the web.
• You want to manage servers or shells on the server side. This agent plans the part that runs on the device only.
• You are planning the whole Apple app. Use the Desktop App Engineer agent or the Mobile app builder.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and add it to your AI as a skill. If you cannot, paste SKILL.md and then references/source-agent.md into a new chat.
• Say which platforms you target, how your app is built and what the terminal connects to. Paste your code if you have some.
• Say "Plan this. Do not invent SwiftTerm method names." Your AI asks once for anything missing.
• Read the fit check first. If it says SwiftTerm does not fit, stop and rethink before you read the rest.
• Look up each SwiftTerm method the plan names in SwiftTerm's own docs, then build in Xcode.
• Run the test list on a real device, then paste any failures back to your AI.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/terminal-integration-specialist for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.