Agent skill

Steve

by mikker in mikker/steve

Use the steve CLI to automate macOS apps via Accessibility APIs.

No licenceAuto-check passedTesting & QA

Install Steve

skills CLI
$ npx skills add mikker/steve --skill steve -a claude-code

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

GitHub CLI
$ gh skill install mikker/steve steve --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/mikker/steve.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/steve .claude/skills/steve && 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/

Facts

Skill name
steve
GitHub stars
170
Token cost
~421 tokens
SKILL.md length
137 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Use the steve CLI to automate macOS apps via Accessibility APIs.

  • Works in 2 steps: Assume the CLI is installed and… → Ensure Accessibility permissions are…
  • You need to drive Mac UI (apps
  • SKILL.md covers Overview, Quick Start, Core Tasks and Reliability Tips
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Steve is an agent skill from mikker/steve. Use the steve CLI to automate macOS apps via Accessibility APIs. Use when you need to drive Mac UI (apps, windows, menus, elements), run UI smoke tests, or script interactions using steve commands and JSON output.

Its SKILL.md is about 420 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 Testing & QA, covering Desktop control and QA and bug reports. It works with macOS. The repository describes itself as: CLI for driving Mac applications via the Accessibility API.

When your agent uses it

  • You need to drive Mac UI (apps
  • Run UI smoke tests
  • Script interactions using steve commands and JSON output

Example prompts

  • “/steve”

Workflow steps

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

  1. Assume the CLI is installed and available on PATH. If not, download it from the GitHub releases page…
  2. Ensure Accessibility permissions are granted for the terminal running steve.

What it can do on your machine

Read from SKILL.md and the folder at commit 9b03d3f. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    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

Steve loads about 421 tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 137 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~421

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 137 words (~421 tokens).

“Use the steve CLI to automate macOS applications through the Accessibility API. Prefer steve when you need deterministic, scriptable UI control with JSON responses.”

— opening of SKILL.md by mikker
name
steve

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/steve of mikker/steve.

Open the folder on GitHubat commit 9b03d3f

Compare with similar skills

Steve 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.

Steve compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Steve this skillmikker/steve170—~421Automated safety check: PassNone
Parallels macOS VM Labsteipete/agent-scripts7.3k—~1.8kAutomated safety check: PassMIT
Evidence-Driven Testingmichaelshimeles/skills1.3k1 repos~3.9kAutomated safety check: PassNone
Electron App Screenshotkeybase/client9.3k—~476Automated safety check: PassBSD-3-Clause
Warp UI Testing with Computer Usewarpdotdev/warp65k1 repos~1kAutomated safety check: PassAGPL-3.0
Bot Channel Acceptance Testinglobehub/lobehub83k—~1kAutomated safety check: PassCustom licence

Similar skills

  • Parallels macOS VM Lab

    steipete/agent-scripts

    Uses a clean Parallels macOS VM to test GUI automation, TCC permission prompts and screenshot tools like Peekaboo, verifying results from outside the guest.

    7.3k GitHub stars~1.8k tokensUpdated 4 days ago
    Testing & QAAuto-check passed
  • Evidence-Driven Testing

    michaelshimeles/skills

    Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.

    1.3k GitHub starsUsed in 1 repo~3.9k tokens
    Testing & QAAuto-check passed
  • Takes a screenshot of a running Electron desktop app through playwright-cli over remote debugging, shrinks it and shows it so you can check the UI visually.

    9.3k GitHub stars~476 tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Guides visual testing of Warp UI changes by launching the app with an API key and driving it through the computer use tool, with optional mocked state.

    65k GitHub starsUsed in 1 repo~1k tokens
    Testing & QAAuto-check passed
  • Extends a project's acceptance process to real chat bot channels: Discord, Slack, Telegram, WeChat, Lark, QQ, and iMessage on macOS.

    83k GitHub stars~1k tokensUpdated today
    Testing & QAAuto-check passed
  • Verifies a Warp client change by pushing it to a branch and spawning a cloud agent with computer use that follows the test-warp-ui skill, only when you ask for it.

    65k GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check passed

Works with

Questions about Steve

What does Steve do?

Use the steve CLI to automate macOS apps via Accessibility APIs. Steve is an agent skill from mikker/steve. Use the steve CLI to automate macOS apps via Accessibility APIs.

When should I use Steve?

Steve fits situations like: you need to drive Mac UI (apps; run UI smoke tests; script interactions using steve commands and JSON output.

How do I install Steve in Claude Code?

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

How do I install Steve in Codex?

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

Can I use Steve 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 mikker/steve --skill steve -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/steve, .gemini/skills/steve, .github/skills/steve and .opencode/skills/steve in your project.

What does Steve need to run?

SKILL.md names no scripts, command-line tools or credentials: Steve is instructions for the agent only.

Does Steve 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 Steve 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 Steve use?

No licence was found for Steve or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Steve use?

About 421 tokens (SKILL.md is roughly 1.7k 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 Steve?

Skills that share tags, products or a category with Steve: Parallels macOS VM Lab (steipete/agent-scripts, 7.3k stars), Evidence-Driven Testing (michaelshimeles/skills, 1.3k stars), Electron App Screenshot (keybase/client, 9.3k stars) and Warp UI Testing with Computer Use (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Steve?

mikker (a GitHub user) maintains it in mikker/steve, which has 170 GitHub stars. The repository was last updated on March 27, 2026.

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