Agent skill

AI Client

Conventions for the opentrons-ai-client React/TypeScript frontend — project structure, API integration, state management (Jotai), feature flags, types, and testing.

Apache-2.0Auto-check passedBackend & APIs

Install AI Client

skills CLI

$ npx skills add Opentrons/opentrons --skill ai-client -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Opentrons/opentrons ai-client --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Opentrons/opentrons.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/ai-client .claude/skills/ai-client && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "ai-client" agent skill from https://github.com/Opentrons/opentrons/tree/edge/.cursor/skills/ai-client into .claude/skills/ai-client/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-client", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Opentrons/opentrons/tree/edge/.cursor/skills/ai-client

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Opentrons/opentrons --skill ai-client -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Opentrons/opentrons ai-client --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Opentrons/opentrons.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/ai-client .agents/skills/ai-client && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "ai-client" agent skill from https://github.com/Opentrons/opentrons/tree/edge/.cursor/skills/ai-client into .agents/skills/ai-client/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-client", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Opentrons/opentrons --skill ai-client -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Opentrons/opentrons ai-client --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Opentrons/opentrons.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/ai-client .cursor/skills/ai-client && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "ai-client" agent skill from https://github.com/Opentrons/opentrons/tree/edge/.cursor/skills/ai-client into .cursor/skills/ai-client/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-client", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Opentrons/opentrons.git --path .cursor/skills/ai-client

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Opentrons/opentrons --skill ai-client -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Opentrons/opentrons ai-client --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Opentrons/opentrons.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/ai-client .gemini/skills/ai-client && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "ai-client" agent skill from https://github.com/Opentrons/opentrons/tree/edge/.cursor/skills/ai-client into .gemini/skills/ai-client/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-client", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Opentrons/opentrons ai-client

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Opentrons/opentrons --skill ai-client -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Opentrons/opentrons.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/ai-client .github/skills/ai-client && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "ai-client" agent skill from https://github.com/Opentrons/opentrons/tree/edge/.cursor/skills/ai-client into .github/skills/ai-client/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-client", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Opentrons/opentrons --skill ai-client -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Opentrons/opentrons ai-client --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Opentrons/opentrons.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/ai-client .opencode/skills/ai-client && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "ai-client" agent skill from https://github.com/Opentrons/opentrons/tree/edge/.cursor/skills/ai-client into .opencode/skills/ai-client/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-client", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: ai-client
GitHub stars: 523
Token cost: ~1.6k tokens
SKILL.md length: 395 words
Files: 1
Skills in repo: 17
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Conventions for the opentrons-ai-client React/TypeScript frontend — project structure, API integration, state management (Jotai), feature flags, types, and testing.

Works in 4 steps: Calls getAccessToken() to get a fresh… → Calls buildRequestConfig() to assemble… → Calls callApi(config) from useApiCall → …
Working with files in opentrons-ai-client/
SKILL.md covers Overview, Project Structure, Types — Use camelCase Throughout and State Management (Jotai), plus 6 more sections
Calls make

What it does

AI Client is an agent skill from Opentrons/opentrons. Conventions for the opentrons-ai-client React/TypeScript frontend — project structure, API integration, state management (Jotai), feature flags, types, and testing. Use when working with files in opentrons-ai-client/ or discussing the AI client application.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering State management and Third-party API integration. It works with React and TypeScript. The repository describes itself as: Software for writing protocols and running them on the Opentrons Flex and Opentrons OT-2. The licence is Apache-2.0.

When your agent uses it

Working with files in opentrons-ai-client/
Discussing the AI client application

Example prompts

“Use the ai-client skill to convention for the opentrons-ai-client React/TypeScript frontend — project structure, API integration, state management…”
“/ai-client”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Calls getAccessToken() to get a fresh token before each request
Calls buildRequestConfig() to assemble the Axios config
Calls callApi(config) from useApiCall
On completion, updates chatDataAtom and chatHistoryAtom

What it can do on your machine

Read from SKILL.md and the folder at commit adb4970. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- make
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Client loads about 1.6k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 395 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~67
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Opentrons/opentrons at commit adb4970, republished under its Apache-2.0 licence (© Opentrons). 395 words, ~1,609 tokens.

Download SKILL.mdSave it as .claude/skills/ai-client/SKILL.md (or your agent's skills folder).

name: ai-client
description: Conventions for the opentrons-ai-client React/TypeScript frontend — project structure, API integration, state management (Jotai), feature flags, types, and testing. Use when working with files in opentrons-ai-client/ or discussing the AI client application.

AI Client Instructions

Overview

opentrons-ai-client is a React/TypeScript single-page application that generates and updates Opentrons protocols from natural language descriptions. It lives in the monorepo and is built with Vite.

Deployed environments: staging (staging.opentrons.ai) and prod (ai.opentrons.com).

Project Structure

opentrons-ai-client/
├── src/
│   ├── OpentronsAI.tsx           # Root component, Auth0 bootstrap, feature flag sync
│   ├── main.tsx                  # Auth0 provider, router, app entry
│   ├── analytics/                # Mixpanel event tracking
│   ├── assets/localization/en/   # i18next translation strings
│   ├── components/               # atoms/, molecules/, organisms/
│   ├── pages/                    # Chat, CreateProtocol, UpdateProtocol, Landing, Settings
│   ├── resources/
│   │   ├── atoms.ts              # Jotai atoms (app-wide state)
│   │   ├── constants.ts          # API base URLs and Auth0 config per environment
│   │   ├── types.ts              # Shared TypeScript types (ChatData, CreatePrompt, etc.)
│   │   ├── hooks/
│   │   │   ├── useInputPromptController.ts  # Main submit logic
│   │   │   ├── useGetAccessToken.ts         # Auth0 token fetching
│   │   │   ├── useApiCall.ts                # Axios wrapper (callApi, data, isLoading, error)
│   │   │   └── useAttachFiles.ts            # File attachment handling
│   │   └── utils/
│   │       ├── buildRequestConfig.ts        # Builds Axios config per endpoint type
│   │       ├── buildChatHistory.ts          # Formats chat history for the API
│   │       ├── createUserInput.ts           # Creates ChatData for user turns
│   │       ├── protocolUtils.ts             # Prompt builders for create/update
│   │       └── resolveErrorMessage.ts       # Maps API error_type to user-facing strings
│   └── feature-flags/            # Feature flag types and DEPRECATED_FLAGS cleanup
└── vite.config.mts

Types — Use camelCase Throughout

All types in src/resources/types.ts use camelCase field names. The API request/response bodies also use camelCase. Do not use snake_case for any new TypeScript types or API payload fields.

Key types:

Type	Purpose
`ChatData`	A single turn in the chat display (user or assistant)
`Chat`	A history entry sent to the server (`role`, `content`, `protocolContent`)
`CreatePrompt`	Atom shape for the create-protocol form state
`UpdatePrompt`	Atom shape for the update-protocol form state

State Management (Jotai)

Key atoms in src/resources/atoms.ts:

Atom	Purpose
`chatDataAtom`	All turns displayed in the chat UI
`chatHistoryAtom`	History sent to the server in API requests
`createProtocolChatAtom`	Create-protocol form values
`updateProtocolChatAtom`	Update-protocol form values
`featureFlagsAtom`	Feature flags (persisted to `localStorage`)
`feedbackModalAtom`	Whether the feedback modal is open

tokenAtom has been removed. Always use useGetAccessToken() to fetch a fresh token before making API calls.

API Integration

The client communicates with the server via a standard JSON HTTP API. Endpoint selection is handled in buildRequestConfig.ts.

Request type	Endpoint
Update protocol (no files)	`POST /api/chat/update-protocol`
Create protocol (no files)	`POST /api/chat/create-protocol`
Chat completion (no files)	`POST /api/chat/completion`
Chat completion (with files)	`POST /api/chat/completion-multipart`

The useInputPromptController hook is the single entry point for all submissions. It:

Calls getAccessToken() to get a fresh token before each request
Calls buildRequestConfig() to assemble the Axios config
Calls callApi(config) from useApiCall
On completion, updates chatDataAtom and chatHistoryAtom

Show full SKILL.md (129 more words)Show less

Authentication

Use useGetAccessToken() (not the removed tokenAtom) whenever a token is needed
getAccessToken() is async — always await it and wrap in try/catch
FeedbackModal and other components that POST independently also use useGetAccessToken()

Environment-Driven URLs

constants.ts exports endpoint constants for three environments (LOCAL_*, STAGING_*, PROD_*). buildRequestConfig.ts uses _NODE_ENV_ (a Vite define) via pickEndpoint() to select the right URL.

Feature Flags

Feature flags live in featureFlagsAtom and are persisted to localStorage. Flags listed in DEPRECATED_FLAGS (src/feature-flags/types.ts) are automatically cleaned up on startup.

User-facing flags are toggled on the Settings page. The enablePrereleaseMode flag is toggled via window.enablePrereleaseMode() in the browser console.

useEffect Exhaustive-Deps Convention

New code wraps useEffect callbacks in the multi-line form and adds a FIXME comment for any suppressed exhaustive-deps lint rule:

useEffect(
  () => {
    // ...
  },
  // FIXME(YYYY-MM-DD): Supply all missing dependencies, if it's safe. If it's unsafe, explain why.
  // eslint-disable-next-line react-hooks/exhaustive-deps
  [dep1, dep2]
)

Dev Commands

Run from the monorepo root:

bash

make -C opentrons-ai-client dev     # Start Vite dev server
make test-js-opentrons-ai-client    # Run unit tests
make format-js                      # Prettier auto-fix
make lint-js                        # ESLint + Prettier check
make lint-css                       # Stylelint check
make check-js                       # TypeScript type check

Files

Just SKILL.md in .cursor/skills/ai-client of Opentrons/opentrons.

Open the folder on GitHubat commit adb4970

Compare with similar skills

AI Client next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AI Client compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
AI Client this skillOpentrons/opentrons	523	—	~1.6k	Automated safety check: Pass	Apache-2.0	today
Frontend Typescript Rulesshinpr/ai-coding-project-boilerplate	233	—	~1.7k	Automated safety check: Pass	MIT	5 days ago
React Flow Node TSmicrosoft/skills	3.1k	6 repos	~502	Automated safety check: Pass	MIT	today
React Generate Skilljiushiwon/wg-skills	114	—	~2.8k	Automated safety check: Pass	Apache-2.0	2 days ago
Typescript Rulesshinpr/claude-code-workflows	693	—	~1.8k	Automated safety check: Pass	MIT	8 days ago
React Code Reviewgiuseppe-trisciuoglio/developer-kit	356	—	~2.6k	Automated safety check: Notes	MIT	29 days ago

Similar skills

Frontend Typescript Rules
shinpr/ai-coding-project-boilerplate
Applies React/TypeScript type safety, component design, and state management rules.
233 GitHub stars~1.7k tokensUpdated 5 days ago
Frontend & DesignAuto-check passed
React Flow Node TS
microsoft/skills
Official
Create React Flow node components with TypeScript types, handles, and Zustand integration.
3.1k GitHub starsUsed in 6 repos~502 tokens
Frontend & DesignAuto-check passed
React Generate Skill
jiushiwon/wg-skills
This skill should be used when the user wants to create a standardized React 18 + TypeScript + Vite + Zustand project from scratch.
114 GitHub stars~2.8k tokensUpdated 2 days ago
Frontend & DesignAuto-check passed
Typescript Rules
shinpr/claude-code-workflows
React/TypeScript frontend development rules including type safety, component design, state management, and error handling.
693 GitHub stars~1.8k tokensUpdated 8 days ago
Frontend & DesignAuto-check passed
React Code Review
giuseppe-trisciuoglio/developer-kit
Provides comprehensive code review capability for React applications, validates component architecture, hooks usage, React 19 patterns, state management, performance optimization, accessibility…
356 GitHub stars~2.6k tokensUpdated 29 days ago
Frontend & DesignAuto-check: notes
Dify Component Writing Guide
langgenius/dify
Use when implementing or refactoring React/TypeScript components and the task requires decisions about component ownership, feature boundaries, state, data…
158k GitHub stars~626 tokensUpdated today
Frontend & DesignAuto-check passed

Questions about AI Client

What does AI Client do?

Conventions for the opentrons-ai-client React/TypeScript frontend — project structure, API integration, state management (Jotai), feature flags, types, and testing. AI Client is an agent skill from Opentrons/opentrons. Conventions for the opentrons-ai-client React/TypeScript frontend — project structure, API integration, state management (Jotai), feature flags, types, and testing.

When should I use AI Client?

AI Client fits situations like: working with files in opentrons-ai-client/; discussing the AI client application.

How do I install AI Client in Claude Code?

Run `npx skills add Opentrons/opentrons --skill ai-client -a claude-code`. Or copy the skill folder (.cursor/skills/ai-client in Opentrons/opentrons) into .claude/skills/ai-client in your project. Claude Code loads it when a task matches its description.

How do I install AI Client in Codex?

Run `npx skills add Opentrons/opentrons --skill ai-client -a codex`. Or copy the skill folder (.cursor/skills/ai-client in Opentrons/opentrons) into .agents/skills/ai-client in your project. Codex loads it when a task matches its description.

Can I use AI Client in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Opentrons/opentrons --skill ai-client -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-client, .gemini/skills/ai-client, .github/skills/ai-client and .opencode/skills/ai-client in your project.

What does AI Client need to run?

Going by SKILL.md and its folder, AI Client needs the command-line tools its instructions call (make).

Does AI Client access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI Client safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does AI Client use?

AI Client is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Client use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to AI Client?

Skills that share tags, products or a category with AI Client: Frontend Typescript Rules (shinpr/ai-coding-project-boilerplate, 233 stars), React Flow Node TS (microsoft/skills, 3.1k stars), React Generate Skill (jiushiwon/wg-skills, 114 stars) and Typescript Rules (shinpr/claude-code-workflows, 693 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Client?

Opentrons (a GitHub organization) maintains it in Opentrons/opentrons, which has 523 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.

Source: Opentrons/opentrons on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install AI Client

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

AI Client Instructions

Overview

Project Structure

Types — Use camelCase Throughout

State Management (Jotai)

API Integration

Authentication

Environment-Driven URLs

Feature Flags

useEffect Exhaustive-Deps Convention

Dev Commands

Files

Compare with similar skills

Similar skills

More from Opentrons/opentrons

Related

Questions about AI Client