Skills software-mansion argent Argent

argent-lens

Use it when:
You want design alternatives for a screen or component and to pick between them yourself, on the running app.
It does:
Plans distinct variants per element, then builds each, screenshots it on the device, proposes it in Lens and reverts it.
You get:
Your pick for each element applied in code, your comments acted on, and a report of what was applied or skipped.
Rules:
At least two variants per element, each a real, distinct screenshot of the running app, never a mockup.
Needs:
The Argent MCP server with its argent-lens feature flag, off by default and turned on with argent enable argent-lens, and the app running on a simulator or emulator.

Skill 12 of 12 in the Argent bundle, after argent-native-profiler.

Needs Argent's argent-lens feature flag, which is off by default: run argent enable argent-lens once.

TL;DR

Part of Software Mansion's Argent toolkit, which lets the agent control simulators, emulators and devices. Lens is Argent's window for choosing between designs: it shows each element as a card beside the live device stream, and you pick a variant per element, pin comments and press Complete. The agent first writes down which elements it will redesign and the distinct variants for each, such as filled, outlined or pill for a search field, and reads each element's exact identifier from the screen so the card points at the right one. Then, one variant at a time, it changes the code, reloads or rebuilds the app, navigates to the element, takes a screenshot, proposes it and reverts it, so captures never mix. Byte-identical screenshots mean a variant isn't on screen yet; if it can't produce visibly different captures, it stops and tells you. One blocking call waits for your decision, then it implements the chosen variants and treats every comment as a change request, including those on skipped variants.

Summarizes the skill at b965c94.

npx skills add https://github.com/software-mansion/argent --skill argent-lens
Total Downloads
25,900 on skills.sh, Nov 9, 2026
Repo stars
3,175 software-mansion/argent
First seen
Jun 17, 2026 on skills.sh
Weekly Downloads
1.8K
+27% over the 8 weeks to Nov 9
Weekly values
Week toInstalls
Sep 211,379
Sep 281,514
Oct 51,527
Oct 121,579
Oct 191,632
Oct 261,684
Nov 21,614
Nov 91,758
Category

Taste for interfaces that don't look generated: direction, motion and accessibility.

Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.

Type

A multi-step process the agent follows: interview, debug, run a TDD loop, review.

Effect

Its own steps create or change files, git state or local tools.

Needs

Needs an MCP server connected.

Publisher

A verified publisher on skills.sh, or the company or maintainer behind the product the skill operates.

Topics
Stack

SKILL.md

From software-mansion/argent at b965c94. Checked daily, last changed Nov 6, 2026.

Frontmatter
name: argent-lens
description: Propose multiple visual design variants for on-screen elements and let the human pick in the Argent Lens window. Use when the user asks for design alternatives / options / A-B choices for a screen or component, or any time you have produced more than one candidate look for an element and want a human decision before committing.

Prerequisite: feature flag. This workflow is gated behind the argent-lens flag (off by default). Run argent enable argent-lens once before using it. If propose_variant comes back not-found, the flag is off; enable it and retry.

1. Overview

You implement several candidate designs, capture each one running on the device, and stage them with propose_variant (non-blocking, once per variant). The Argent Lens window opens on its own and shows each element as a card beside the live device stream; the human picks per element, may pin comments, and presses Complete. await_user_selection is the single blocking call that returns their decision. Both tools' descriptions cover their parameters and return shapes.

Resolve a simulator/emulator first (argent-ios-simulator-setup / argent-android-emulator-setup) and, for React Native, argent-react-native-app-workflow to run the app and reload the bundle.

2. Workflow

Step 0: Plan the variants

Decide, before touching code, exactly which elements you are redesigning and the distinct variants for each. Write them down (e.g. "Search field: Filled / Outlined / Pill", "Primary CTA: Solid / Gradient"). Each variant must be a single, self-contained change you can apply, screenshot, and revert independently. Vague or overlapping variants produce useless proposals.

Step 1: Get a precise matcher

For each element, run describe on its screen and read its exact identifier / label / role. Prefer match: { by: "identifier", … } (stable testID), then an exact label; the default text match is fine only when the element's visible text is unique. A wrong match makes the card point at the wrong element or float unanchored.

Step 2: For each variant: build → navigate → screenshot → propose → revert
  1. Build the variant in code.
  2. Apply it on the device. Reload the RN bundle (debugger-reload-metro) or rebuild as needed so the running app shows this variant.
  3. Navigate to it (argent-device-interact): a screenshot is only meaningful if the element is on screen.
  4. Screenshot. Call screenshot and pass the returned path straight through as variant.previewImage. NEVER hand-crop, resize, re-encode, or copy the screenshot to another folder: that double-crops against the preview window's own cropping and writes the image where the server won't serve it ("No preview"). If you suspect the variant didn't apply (no visible change vs. the previous capture), compare with the previous path (shasum -a 256): byte-identical captures mean the variant is not on screen yet. Fix that; never propose anyway.
  5. Propose with element, match, udid (the device you captured on) and previewImage, plus a summary and code/filePath when useful. The tool auto-captures the crop frame by describing the device at propose time, so propose right after the screenshot, while the variant is still on screen. Pass variant.frame only to override that, e.g. when the element can't stay on screen at propose time.
  6. Revert the change before building the next variant.
Step 3: Await the human's decision

After every variant for every element is staged, call await_user_selection once. A pending result is normal: the proposals stay live, call it again. In an argent lens session that tool is hidden: end your turn instead, and the user's choice arrives as a message.

Step 4: Apply the outcome

Implement the chosen variant for every selected element, treat every annotation and the global comment as a change request, and report what you applied and what was skipped. If the human commented but skipped a variant, the comment still matters; act on it.

3. Rules

  • One variant = one real, distinct screenshot. Every previewImage must show that variant actually running on the device, captured after it was applied: no mockups, no un-built ideas, never the same path (or byte-identical captures) for two variants. If you can't produce visibly different captures (the app is read-only, accessibility is broken so you can't navigate, the bundle won't hot-reload), STOP and tell the user instead of staging duplicates.
  • At least two variants per element. If you only have one look for an element, produce a real alternative or don't propose that element at all; a lone variant isn't a choice.
  • One variant on screen at a time. Apply → screenshot → propose → revert, so screenshots never bleed together.
  • Re-proposing starts a fresh round. Calling propose_variant after a round was consumed begins the next round and clears the previous round's elements; stage a full set each round.