Add eas-simulator skill by gwdp · Pull Request #88 · expo/skills

gwdp · 2026-06-24T06:28:48Z

Why

EAS provides cloud simulators. This skill makes it easy for agents to open in-development apps on them.

What

New skill at plugins/expo/skills/eas-simulator/ — SKILL.md and three reference files. Covers the session lifecycle, three ways to get an app onto the sim, driving it (press, screenshot, etc.), and cleanup.

Test plan

Ran all three modes on real sessions from Cursor on a Mac. Opus 4.8, Composer 2.5, and Codex 5.3 all picked up and followed the skill correctly.

Mode A — local release build

Built locally, uploaded to the cloud sim, app rendered.

Transcript

Mode B — EAS build (iOS)

EAS built it, VM downloaded the artifact (no credentials), app rendered.

Transcript

Mode B — EAS build (Android)

EAS built the APK, VM downloaded it, rendered on the remote Android emulator. No browser preview — Android is screenshot-only.

Transcript

Mode C — dev build + tunnel (live edit)

Edited a file locally, it hot-reloaded on the remote sim with no rebuild.

Transcript
Transcript Linux

argent — editor MCP link

Started an argent session (--type argent), ran argent init --yes to register the Argent MCP in Cursor, wired ARGENT_TOOLS_URL + ARGENT_AUTH_TOKEN as env vars in .cursor/mcp.json (higher precedence than argent link, works in sandboxed shells), and reloaded the editor. The remote sim was controllable from chat via Argent's MCP tools.

Transcript

Trigger accuracy — 6/6 (100%)

#	Prompt	Result
1	Run my Expo app on a cloud iOS simulator and screenshot the home screen	✅
2	I'm on Linux with no Mac available — use EAS to open my app on a remote simulator	✅
3	Start an EAS simulator session, install my app, and take a screenshot	✅
4	Use eas simulator to run my expo app on iOS and capture a screenshot of it	✅
5	I want to make live code changes and see them hot-reload on a cloud simulator without a Mac	✅
6	Open my app on a remote Android simulator via EAS and verify it renders correctly	✅

Still to do:

Check whether this belongs in public skills while the feature is experimental

davidmokos

Review comments based on Anthropic and OpenAI skill-creator guidance.

Kudo

would like to know further test plans:

if we ask agent to use argent, does it work well? (because the skill / references hardcoded agent-device in multiple places)
if we ask agent to run android workflow, does ti work well? (because the skill / references hardcoded ios in multiple places)

gwdp · 2026-06-26T08:22:13Z

would like to know further test plans:

if we ask agent to use argent, does it work well? (because the skill / references hardcoded agent-device in multiple places)

if we ask agent to run android workflow, does ti work well? (because the skill / references hardcoded ios in multiple places)

Thanks for the review @Kudo and @davidmokos 🙏 Addressed all the feedback — replies inline. Also added test plans for argent (editor MCP link) and Android, both worked quite well, although argent received a little refinement to improve experience. Let me know how you guys feel about it!

Kudo

i have a mixed feeling for the current work. but i don't want to block much. if you want to ship it first and iterate later. please just re-request review for me. (i use graphite dashboard. please don't feel hesitant about the "request changes" / "re-request review" workflow)

the major concern is

some step-by-step in markdowns could potentially use scripts in the skill to make it more deterministic. for example, the argent mcp setup.
i feel we are mixing "how-to build" concept in this skill. ideally we should keep this skill smaller and link to other skill. currently the differece between mode a/b/c are mostly how the app built. we could try to focus single stuff - "given an app/ipa/apk, use eas simulator" to run it. how to generate app/ipa/apk is not in the skill scope.
imo, mode b is the happy path for me. even though the skill said it's rarely used. if people can build ios app locally, they should mostly have local simulators available. using eas build or eas workflow to build the app, for people running on linux/windows machine to test ios app, is something we are targeting first. maybe we can simplify the mode matrix a little bit.

Kudo · 2026-06-26T13:24:00Z

+| `screenshot <path>` | Capture to a local PNG (downloaded from the daemon) |
+| `gesture <pan\|fling\|swipe\|pinch\|rotate\|transform>` / `swipe` / `scroll` / `longpress` / `type` / `back` / `home` | Standard interactions — `gesture` needs a kind subcommand |
+| `metro prepare (--public-base-url <url> \| --proxy-base-url <url>)` / `metro reload` | Wire a dev client to Metro / reload (Mode C). `--proxy-base-url` = optional bridge origin for remote Metro access — **not exercised by this skill's flow** (run-your-app.md connects via the public tunnel URL). |
+| `logs` / `record` / `network` / `perf` | Evidence capture |


nit: i feel that we should not doc agent-device in our skill. does agent-device have some doc that we can ask agents to fetch?

or even just run agent-device help?

agent device skills are installed when you install agent-device: https://github.com/callstackincubator/agent-device

(side note: did we test the full process including the agent-device install on windows?)

also, we should probably commit to a single library: argent or agent-device, instead of recommending both

nit: i feel that we should not doc agent-device in our skill. does agent-device have some doc that we can ask agents to fetch?

or even just run agent-device help?

Agreed that --help is better and decouples us from maintaining a verb list in the skill. Updated. I originally added the table after seeing models struggle with agent-device in dogfooding sessions. Will do a bit more testing before re-requesting review for this particular change.

agent device skills are installed when you install agent-device: https://github.com/callstackincubator/agent-device

(side note: did we test the full process including the agent-device install on windows?)

I checked transcripts and couldn't see agent-device skill. Digging further it was pretty clear that because we exec through npx, those are not loaded and we can't rely on it. (which is a nice isolation imo, let me know your thoughts)

Windows is not directly tested; assuming devs on Windows are using WSL (You guys probably have a better idea if this is a bad assumption). Will look to validate that in the coming days

also, we should probably commit to a single library: argent or agent-device, instead of recommending both

I'm a little hesitant on this one, imo, going fully blind on it means the agent has no reference when a user brings it up, and that tends to produce more loops and token spend before landing on something maybe works. Let me know if you guys feel strong about this.

davidmokos

Don't want to block this. I think we need to test it properly in the wild and make changes when we see the agents struggle. I'd encourage everyone in expo to dogfood this skill and the simulator service after we merge it

gwdp · 2026-06-27T07:20:46Z

i have a mixed feeling for the current work. but i don't want to block much. if you want to ship it first and iterate later. please just re-request review for me. (i use graphite dashboard. please don't feel hesitant about the "request changes" / "re-request review" workflow)

the major concern is

some step-by-step in markdowns could potentially use scripts in the skill to make it more deterministic. for example, the argent mcp setup.

I hesitate to give scripts and hard instructions because in my experience, models and user environments are different, and giving the minimum, to allow it to adapt is the part that makes the skill succeed in the most diversity. Happy to be wrong and discuss it further

i feel we are mixing "how-to build" concept in this skill. ideally we should keep this skill smaller and link to other skill. currently the differece between mode a/b/c are mostly how the app built. we could try to focus single stuff - "given an app/ipa/apk, use eas simulator" to run it. how to generate app/ipa/apk is not in the skill scope.

Fair, and I agree we opinionated more than ideal. The modes emerged from real dogfooding scenarios though; each one came from a "what if I want to do it this way" moment. I'd rather keep the minimum needed to not leave the model stranded than link out and risk it not finding what it needs in time.

imo, mode b is the happy path for me. even though the skill said it's rarely used. if people can build ios app locally, they should mostly have local simulators available. using eas build or eas workflow to build the app, for people running on linux/windows machine to test ios app, is something we are targeting first. maybe we can simplify the mode matrix a little bit.

The framing was mostly to avoid false-triggering on Mac users who just want a local sim. But the trend I'm seeing, even on Mac is the full agent loop: prompt, see, agent sees too. That all-in-IDE experience is where Mode C earns its place as default. For Linux/Windows targeting iOS, yeah Mode B is the right happy path there, agreed 💯

Thanks for the review once again @Kudo, replies above

@davidmokos dropped some more improvements, if you dont mind a second check, I do appreciate the time 🙇‍♂️

Kudo

thanks for answering the questions. you know what you want. the current work is based on your thinking. that's great and i don't want to block it. approving the pr to move forward.

leaving answers that we can follow up later

Windows using WSL

i think that's not correct. a lot windows user still use powershell / cmd without WSL.

The framing was mostly to avoid false-triggering on Mac users who just want a local sim. But the trend I'm seeing, even on Mac is the full agent loop: prompt, see, agent sees too. That all-in-IDE experience is where Mode C earns its place as default.

for mac users, if they want agent loop. what's the benefit to use eas simulator than local agent-device/argent?

also what does the all-in-IDE experience mean here? does eas simulator offer ui panel inside cursor so we can see simulator ui in the same IDE?

gwdp · 2026-06-27T07:58:31Z

Thank you for the quick review @Kudo !

i think that's not correct. a lot windows user still use powershell / cmd without WSL.

appreciate this input! dogfooding some there without WSL and will follow up on this, very interested in making this particular one flawless

for mac users, if they want agent loop. what's the benefit to use eas simulator than local agent-device/argent?

I see motivation around hardware, but more interesting, reproducing bugs on lower/unsupported iOS versions without having the simulator image installed locally 🥳 (I struggled with this multiple time in the past)

also what does the all-in-IDE experience mean here? does eas simulator offer ui panel inside cursor so we can see simulator ui in the same IDE?

cursor and others are currently offering a built-in browser which is leveraged by the skill -> opens from serve-sim provided tunnel (check video)

Kudo · 2026-06-27T18:50:18Z

thanks for sharing the insight. that makes sense to me.

I see motivation around hardware, but more interesting, reproducing bugs on lower/unsupported iOS versions without having the simulator image installed locally 🥳 (I struggled with this multiple time in the past)

maybe we can even add this "when to use" to the skill. that could be one selling point.

szdziedzic

Good job 👏 . I think this looks good overall so I'm approving it although I left some comments about argent. Let's release it so we can all test it more easily and see if we like it + iterate on the feedback. Would be great to test it in Cursor Cloud Agents too. I will play with it more once it lands. Awesome.

szdziedzic · 2026-07-01T11:39:47Z

+```bash
+# 1. Add a simulator build profile to eas.json (merges — won't overwrite existing profiles)
+node -e "
+const fs = require('fs');
+const p = 'eas.json';
+const c = fs.existsSync(p) ? JSON.parse(fs.readFileSync(p, 'utf8')) : {};
+c.build = c.build || {};
+c.build.sim = { ios: { simulator: true } };
+fs.writeFileSync(p, JSON.stringify(c, null, 2) + '\n');
+"


I think it won't work for some setups. It would be good if agent could prioritize getting existing sim profile first before creating new one?

I think it won't work for some setups

You're right, there are multiple setup variances, and from experience, the script could force the LLM to use it without much consideration. (reason why I'm not a big fan of script as instructions)

Updated to pure instructions without a script, allowing us to support a little more than the previous iteration.

…un-your-app fixes

…xed shells

…ld first

…ion if already present

…for sim profile

…e fixed NSPasteboard entry

gwdp changed the title ~~add eas-simulator skill~~ Add eas-simulator skill Jun 24, 2026

gwdp requested review from davidmokos and zvadaadam June 25, 2026 06:36

gwdp marked this pull request as ready for review June 25, 2026 06:37

gwdp force-pushed the gwdp/eas-simulator-skill branch from 95f2749 to b1e998a Compare June 25, 2026 06:41

davidmokos reviewed Jun 25, 2026

View reviewed changes

Comment thread plugins/expo/skills/eas-simulator/references/run-your-app.md Outdated

Comment thread plugins/expo/skills/eas-simulator/SKILL.md Outdated

Comment thread plugins/expo/skills/eas-simulator/references/run-your-app.md Outdated

Kudo reviewed Jun 25, 2026

View reviewed changes

Comment thread plugins/expo/skills/eas-simulator/SKILL.md Outdated

Comment thread plugins/expo/skills/eas-simulator/SKILL.md

Comment thread plugins/expo/skills/eas-simulator/SKILL.md

Comment thread plugins/expo/skills/eas-simulator/SKILL.md Outdated

gwdp force-pushed the gwdp/eas-simulator-skill branch from 3ad2e3b to c568085 Compare June 26, 2026 08:23

gwdp requested review from Kudo and davidmokos June 26, 2026 08:24

Kudo requested changes Jun 26, 2026

View reviewed changes

davidmokos approved these changes Jun 26, 2026

View reviewed changes

gwdp requested review from Kudo and davidmokos June 27, 2026 07:21

Kudo approved these changes Jun 27, 2026

View reviewed changes

szdziedzic reviewed Jun 29, 2026

View reviewed changes

Comment thread plugins/expo/skills/eas-simulator/references/controllers.md Outdated

Comment thread plugins/expo/skills/eas-simulator/references/controllers.md Outdated

Comment thread plugins/expo/skills/eas-simulator/references/controllers.md Outdated

gwdp requested a review from szdziedzic June 30, 2026 16:50

gwdp force-pushed the gwdp/eas-simulator-skill branch from 87b12d3 to 5096676 Compare June 30, 2026 16:52

szdziedzic approved these changes Jul 1, 2026

View reviewed changes

gwdp added 7 commits July 1, 2026 12:06

add eas-simulator skill

94c1f3e

eas-simulator: tighten description, allowed-tools, argent docs, and r…

9717466

…un-your-app fixes

fix simctl detection and README naming

89c5fb9

eas-simulator: trim agent-device verb table; point to --help

2e1ff9d

eas-simulator: mention Claude Code and Codex in argent MCP setup

f6fa728

eas-simulator: remove argent screenshot known issue (fixed upstream)

21145fe

eas-simulator: make argent link primary, env vars fallback for sandbo…

fd0453b

…xed shells

eas-simulator: clarify argent install limitation + check existing bui…

880a62b

…ld first

gwdp force-pushed the gwdp/eas-simulator-skill branch from 206a03b to 880a62b Compare July 1, 2026 19:08

gwdp added 3 commits July 1, 2026 12:28

[eas-simulator] preserve existing sim profile in eas.json, skip creat…

70181ad

…ion if already present

[eas-simulator] replace node script with agent-readable instructions …

89d3362

…for sim profile

[eas-simulator] screenshot needs open first; scoped build:list; remov…

91c2e11

…e fixed NSPasteboard entry

gwdp merged commit 1f99511 into main Jul 2, 2026
2 checks passed

gwdp deleted the gwdp/eas-simulator-skill branch July 2, 2026 04:59

Uh oh!

Conversation

gwdp commented Jun 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Why

What

Test plan

Uh oh!

davidmokos left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Kudo left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

gwdp commented Jun 26, 2026

Uh oh!

Kudo left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Kudo Jun 26, 2026

Choose a reason for hiding this comment

Uh oh!

davidmokos Jun 26, 2026

Choose a reason for hiding this comment

Uh oh!

davidmokos Jun 26, 2026

Choose a reason for hiding this comment

Uh oh!

gwdp Jun 27, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

davidmokos left a comment

Choose a reason for hiding this comment

Uh oh!

gwdp commented Jun 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Kudo left a comment

Choose a reason for hiding this comment

Uh oh!

gwdp commented Jun 27, 2026

Uh oh!

Kudo commented Jun 27, 2026

Uh oh!

Uh oh!

Uh oh!

Uh oh!

szdziedzic left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

szdziedzic Jul 1, 2026

Choose a reason for hiding this comment

Uh oh!

gwdp Jul 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

gwdp commented Jun 24, 2026 •

edited

Loading

gwdp commented Jun 27, 2026 •

edited

Loading

gwdp Jul 1, 2026 •

edited

Loading