Mode d’emploi
- Copiez la commande et examinez le paquet avant de l’installer dans votre environnement agent.
- Consultez le document original pour les outils, identifiants et environnements requis.
- Décrivez les entrées et le livrable souhaité ; comparez la sortie aux sources.
npx skills add https://github.com/software-mansion/argent --skill argent-test-ui-flowAvant de commencer
- L’installation n’inclut ni abonnement au modèle, ni quota API, ni accès aux fichiers.
- Étoiles et installations reflètent l’activité, pas un test indépendant de qualité ou de sécurité.
Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.
Before testing
Resolve the device first: call list-devices, use the platform the user named or else prefer a device that is already running, and don't pick a cabled phone without explicit intent. Setup: argent-ios-simulator-setup / argent-android-emulator-setup. The interaction tool names are identical on iOS and Android.
Physical iPhone (kind: "device"): read argent-ios-device-interact first. launch-app before anything; describe fails while the app is backgrounded.
1. Workflow
For implementation tasks that modify visible UI, this workflow also serves as a visual acceptance path.
- Baseline screenshot: call
screenshotto see the current UI state. For visual regression comparison or UI change verification, capture the baseline atscale: 1.0withincludeImageInContext: falseand keep the returnedpathbefore editing whenever feasible. - Find target: get element coordinates from a discovery tool before tapping:
- App screens (React Native included), in-app modals and system dialogs:
describe. Fall back toscreenshotonly if an overlay is not exposed reliably. When the app raises its own permission dialog, answer it here; that's the real flow under test. To take a prompt out of the flow, useargent-settings-permissionsduring setup.
- Interact: perform the action (
gesture-tap,gesture-swipe,keyboard,button, ...); you receive a screenshot and element tree automatically (an identical earlier tree is named by itsTree id, not repeated). - Verify: check the returned screenshot. If it shows a loading/transitional state, block with
await-ui-element(expected elementvisible, or a spinnerhidden) rather than a guessed delay (its result carries the new screenshot and element tree), but only with a selector you can trust (text/identifier/role) that the screen is known to have or that you saw in a priordescribe; a guessed one just times out. Otherwise use a short fixed wait. Pick evidence by what's being asserted:
- Visual (layout, spacing, color, typography, image/icon rendering, clipping, overflow, text rendering): prefer
screenshot-diffagainst the step 1 baseline: it surfaces pixel-visible changes the auto-screenshot might miss. Fall back to inspecting the auto-screenshot only when a stable baseline isn't available. - Structural (navigation state, element existence, accessibility labels/values, selection, hierarchy, route): verify with
describeordebugger-component-tree. - Runtime / log / network (console errors, API calls, persistence, timing): verify with
view-network-logs,debugger-log-registry,debugger-evaluate, or targeted tests. Anot_connectedresult from the debugger tools is not evidence about the app: follow itsguidance, then re-verify. - Mixed: collect evidence for each relevant class.
- Report the combined verdict: expected behavior, observed behavior, evidence used, and any blocker for requested visual diffing.
- Repeat for each step in the flow.
2. Example: login flow
1. describe → login screen
2. gesture-tap email field (frame centre from the tree)
3. keyboard { text: "user@example.com" }
4. gesture-tap password field (from the returned tree)
5. run-sequence: keyboard { text: "{{secret:APP_PASSWORD}}" }, gesture-tap Login button
6. await-ui-element → home screen appearedCredentials: never type plaintext credentials; use a{{secret:<NAME>}}placeholder (keyboard'stextparameter lists where it is read from and what to do when a name is missing). Never invent credentials or echo secret values into reports or saved files.
3. Recovery Pattern
- Screen mid-transition or loading: wait with
await-ui-elementas in step 4, then re-check. Fall back to a fixed wait +screenshotonly when no element reliably marks the transition. Don't poll with repeated screenshots. - Tap misses the target: re-run
describeand retry once with new coordinates. If it fails twice, stop and report that the element was not found. - Permission dialog or modal visible: re-run
describefirst. Stay in screenshot-driven navigation only while the overlay is not exposed reliably: tap one visible button at a time, verify with the returned screenshot, and switch back todescribeas soon as it is dismissed. - A saved e2e test fails during
e2e-executereplay (as opposed to the live steps above): followargent-create-e2e's Diagnose a replay failure: classify the failure, inspect the actual screen, repair the smallest justified unit, then replay the full e2e test.
Record for replay: if a tested flow is likely to be repeated, use the argent-create-e2e skill to record it as a .yaml test, so it can be replayed later with a single e2e-execute call.
Related Skills
| Skill | When to use |
|---|---|
argent-device-interact | Tool usage for tapping, swiping, typing (iOS + Android) |
argent-screenshot-diff | Visual regression and before/after screenshot comparison |
argent-ios-simulator-setup | Booting and connecting an iOS simulator |
argent-android-emulator-setup | Booting and connecting an Android emulator |
argent-react-native-app-workflow | Starting the app, Metro, build issues |
argent-metro-debugger | Console logs, JS evaluation, component inspection |
argent-create-e2e | Record a test sequence as a replayable e2e test |