メニュー
Author local Maestro iOS-Simulator E2E flows for the Kata Code mobile app using the reusable TS orchestrator and Kata-specific flows. Use when adding or updating flows under mobile-e2e/.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
| name | mobile-e2e-test-author |
| description | Author local Maestro iOS-Simulator E2E flows for the Kata Code mobile app using the reusable TS orchestrator and Kata-specific flows. Use when adding or updating flows under mobile-e2e/. |
Local-only Maestro suite for the Kata Code mobile app on the iOS Simulator. The TS orchestrator owns server lifecycle, isolation, prereq gates, and artifacts; Maestro YAML owns on-device interaction. Real services only — no mocks.
Verified green on-device (iPhone 17 Pro): @smoke, @pairing, @agent. Open:
@auth (the native NativeClerk.presentAuth modal is not yet driven by Maestro).
Full verified locators and the run inventory live in the
Maestro Studio authoring guide
and the E2E test catalog.
Durable learnings to reuse, not relearn:
clearState: false on launchApp keeps the saved Metro URL so the dev client
loads past the Expo Dev Launcher; pair extendedWaitUntil for Metro bundling and
real provider round-trips.connection-status on ConnectionStatusDot, asserted as
connection-status-ready for the pairing ready-state.maestro/shared/ (e.g. open-add-environment.yaml), composed
via runFlow. shared/ is excluded from flow discovery (SUBFLOW_DIRS in
cli/flows.ts) so subflows are never run standalone.flows/agent.ts derives
them (providerMenuLabel: openai→Codex, anthropic→Claude; modelMenuLabel:
gpt-5.4-mini→GPT-5.4-Mini) mirroring the server's toDisplayName. Keep in sync.Read mobile-e2e/README.md and the design spec
(docs/specs/2026-06-24-mobile-e2e-testing-foundation-design.md).
Read Mobile E2E authoring (Maestro Studio) for the canonical Studio workflow.
Inspect existing flows under mobile-e2e/maestro/ and the TS building blocks in
mobile-e2e/src/harness/ and mobile-e2e/src/flows/.
Explore the live app with Maestro Studio first, then codify locators — do not guess selectors from product code alone. Full workflow: Mobile E2E authoring (Maestro Studio).
vp run e2e:mobile:studio # boots the sim, verifies the dev client, opens Studio
| Layer | Role |
|---|---|
src/harness/ (TS) | Generic: simulator control, server stack (serve + token + project add), isolated run, Maestro runner, artifacts, prereq gates |
src/flows/ (TS) | Kata-specific: pairing inputs, Clerk Connect gate, agent expected-text + normalization |
maestro/**/*.yaml | On-device UI — the only layer that references screen elements |
src/cli/run.ts | Orchestrates a run: gate → isolate → sim → server → Maestro → manifest → cleanup |
The TS layer injects dynamic values (one-time token, expected agent text, model)
into flows as -e KEY=VALUE (${KEY} in YAML). Keep dynamic plumbing in TS; keep
flows declarative.
src/harness/ and Kata UI/product
language in src/flows/ + maestro/.mobile-e2e/.auth/,
mobile-e2e/test-results/, mobile-e2e/artifacts/, local .env.local).@smoke, @pairing,
@auth, @agent). New surfaces get new tags; register them in src/config/tags.ts.accessibilityLabel
in product code only when no durable locator exists and it is a deliberate test
contract (e.g. a ConnectionStatusDot ready state).vp run e2e:mobile:build).@smoke and @pairing need no credentials (bearer loopback path).@auth needs CLERK_PUBLISHABLE_KEY, CLERK_SECRET_KEY, KATACODE_E2E_GOOGLE_EMAIL.
Mobile sign-in is a native auth modal (NativeClerk.presentAuth); Maestro may
not be able to drive it. Its green runtime pass is a maintainer responsibility.@agent needs KATACODE_E2E_AGENT_PROVIDER, KATACODE_E2E_AGENT_MODEL, and the
matching provider key. Select the model explicitly; the composer default is not
reliable for deterministic replies. Green runtime pass is a maintainer responsibility.vp run e2e:mobile --list # list flows + tags
vp run e2e:mobile --include-tags @smoke # smoke launch
vp run e2e:mobile --include-tags @pairing # bearer pairing
vp run e2e:mobile:studio # explore / author locators
vp test run mobile-e2e/src # harness + flow unit tests
vp check mobile-e2e # format + lint
Suggested rollout order: @smoke → @pairing → @auth → @agent, one at a time in
Studio, giving the maintainer the exact verify command after each passes.
Assess and selectively port changes from the upstream T3 Code fork (pingdotgg/t3code) into Kata Code. Use whenever the user wants to review what upstream has done, assess the diff, decide what to bring in, triage upstream commits, plan a vendor-pull, run an upstream scan, or figure out which upstream changes are worth porting. Covers scanning upstream since the last baseline, grouping commits by effort and risk, recommending Port/Skip/Watch per change, and re-implementing chosen changes as fork-original commits with Kata branding applied from the start.
Use this skill for multi-step, spec-driven, or acceptance-gated implementation work that should move through Plan, Build, and Verify phases.
Author local Playwright Electron E2E tests for Kata Code using the reusable harness and Kata-specific flows. Use when adding or updating tests under e2e/.
Use when preparing, packaging, tagging, or publishing Skiller Desktop releases, including GitHub release CI, macOS code signing, notarization, release secrets, and desktop version bumps.
Compact the current conversation into a handoff document for another agent to pick up.
Validate Kata Code nightly releases on macOS with the @Computer plugin. Start and update the nightly app, use its New Project flow to create a timestamp-suffixed nightly UAT project under `/Volumes/EVO/dev`, then execute explicit acceptance criteria for a Codex GPT-5.4-Mini chat, Browser and Files panels, and git commit flow; capture criterion-level screenshots and write an evidence-linked report in the created project. Use when validating or documenting the Kata Code nightly release flow.