voyager

Authoring E2E tests for web (Playwright/Cypress/WebdriverIO) and native mobile (Appium/Detox/Maestro/XCUITest/Espresso). Covers Page Object design, auth flows, parallel execution, visual regression, a11y, CI, and remote device-farm (BrowserStack/Sauce Labs/AWS/Firebase). Use when authoring E2E suites. Not for unit (Radar), load/chaos (Siege), ad-hoc browser (Vector), or native impl (Native).

Aller à l'installation

Dépôt: simota/agent-skills
Dernière activité de la source: 7 août 2026 à 13:16
Langue détectée de SKILL.md: anglais
Étoiles: 71
Forks: 14

Options d'installation

Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.

npx skills add https://github.com/simota/agent-skills --skill voyager

La commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.

Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.

Vérifiez les fichiers source

Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.

Explorateur de fichiers

24 fichiers

SKILL.md

Instructions source · Aperçu en lecture seule

Retour à la recherche Retour à l’installation

chain

Auditing skill/plugin/MCP supply chains. Treats SKILL.md, bundled scripts, MCP server defs, hooks, and `.claude/` config as third-party software. Generates sha256 manifests, scans for Unicode Tag injection, detects curl-pipe + credential-exfil patterns, enforces third-party intake checklist, and pins MCP tool descriptions against rug-pulls. Use when auditing skill/MCP supply chain. Not for app SAST (Sentinel), CI/CD (Gear/Pipe), hook design (Latch), SKILL.md format (Gauge), or runtime exploit (Probe).

2026-08-10

latch

Proposing, configuring, debugging, and maintaining Claude Code hooks (PreToolUse/PostToolUse/Stop and other lifecycle events). Use when workflow automation, quality gates, or security enforcement via hooks is needed.

2026-08-10

nexus

Orchestrating specialist AI agent teams as a meta-coordinator. Decomposes requests into minimum viable chains, spawns each as an independent session in AUTORUN modes, and drives to final output. Use when a task spans multiple specialist domains, requires parallel agent execution, or needs hub-and-spoke routing across the skill ecosystem.

2026-08-10

Tout voir dans ce dépôt

Voyager

Browser-based E2E specialist for critical user journeys, cross-browser validation, and CI-ready test suites.

Trigger Guidance

Use Voyager for browser-level journey verification, auth/session coverage, visual regression, accessibility checks, cloud-browser runs, or CI-integrated E2E automation.

Native mobile E2E: Use Voyager when the artifact is a shipping .ipa / .apk / .aab (or RN bundle) and reusable test automation is needed — Detox (RN grey-box), Maestro (cross-platform YAML + Studio + MaestroGPT), Appium 3.x (widest matrix), XCUITest (iOS deep), or Espresso + Compose UI Test (Android). Read reference/mobile-testing.md first; version detail in reference/2026-best-practices.md.

Remote device-farm orchestration: Use Voyager when ≥3 device combos are required, the PR-blocking smoke must run on a real device, or remote WebDriver/Appium endpoints are involved. Route to BrowserStack App Automate, Sauce Labs Real Device Cloud, AWS Device Farm, Firebase Test Lab, or LambdaTest HyperExecute. Tier: local sim/emu → 1 farm for PR smoke → real-device lab for release gate. Read reference/cloud-testing.md.

Adaptive / foldable E2E: For foldables (Z Fold, Pixel Fold), multitasking tablets, or window-size-aware layouts, exercise Compose WindowSizeClass breakpoints and iPadOS Stage Manager / Split View postures. Add at least one fold/unfold transition to the release-gate tier.

Privacy-aware E2E: For Apple Privacy Manifest enforcement (required-reason APIs, tracking-domain declarations), verify that test scaffolding carries its own and does not break the host app's manifest aggregation. Enforcement timeline in .

Voyager

Browser-based E2E specialist for critical user journeys, cross-browser validation, and CI-ready test suites.

Trigger Guidance

Use Voyager for browser-level journey verification, auth/session coverage, visual regression, accessibility checks, cloud-browser runs, or CI-integrated E2E automation.

Keywords

Recipe

playwright, e2e, browser test, journey test

playwright

cypress, cy.

playwright (Cypress branch — read cypress-guide.md)

visual regression, screenshot, pixel diff

visual

accessibility, a11y, axe, WCAG

a11y

auth flow, login test, session

auth

CI, pipeline, sharding, parallel

playwright (CI scope — read ci-reporting.md)

flaky, flake, retry, instability

playwright (flake diagnosis — read debug-monitoring.md)

mobile emulation, mobile viewport, responsive E2E, PWA mobile

playwright (mobile emulation — read mobile-testing.md)

native mobile E2E, appium, detox, maestro, xcuitest, espresso, .ipa, .apk, .aab

mobile

device farm, browserstack app automate, app percy, sauce labs real device, aws device farm, firebase test lab, lambdatest, hyperexecute, testmu ai, real device, parallel session, cloud session, remote webdriver, appium server, appium 3, webdriver bidi

mobile (device-farm tier — read cloud-testing.md + mobile-testing.md)

foldable, galaxy z fold, pixel fold, window size class, compact medium expanded, stage manager, split view, multi-window, posture

mobile (adaptive/foldable — read mobile-testing.md)

privacy manifest, PrivacyInfo.xcprivacy, required reason api, tracking domain, privacy sandbox, data access auditing

mobile (privacy-aware — read mobile-testing.md)

applitools, app percy, testrigor, mabl, native visual ai, self-healing mobile, vision ai, maestro ai

visual / mobile (native visual AI — read ai-powered-e2e-testing.md + mobile-testing.md)

container, testcontainers, docker test

playwright (container — read container-testing.md)

web component, shadow DOM, lit, stencil

component (read web-component-testing.md)

AI test, MCP, self-healing, codegen, playwright cli

playwright (AI lifecycle — read ai-powered-e2e-testing.md)

screencast, video receipt, visual proof, recording

playwright (screencast — read ai-powered-e2e-testing.md)

API test, request context, backend verify

api

complex multi-agent task

Hand off to Nexus per _common/BOUNDARIES.md

unclear request

Default playwright; clarify via framework-selection.md

File

Read this when

playwright-patterns.md

Playwright is the default or current framework

framework-selection.md

You must choose or justify the framework

cypress-guide.md

The project already uses Cypress

visual-a11y-testing.md

Visual regression, keyboard flows, or WCAG checks matter

selector-accessibility-first.md

You need selector rules, ARIA snapshots, or fallback criteria

ci-reporting.md

You are wiring CI, sharding, artifacts, or reporters

performance-testing.md

Core Web Vitals, Lighthouse CI, or browser performance budgets are in scope

complex-scenarios.md

The flow includes multi-tab, iframe, file, WebSocket, offline, or Shadow DOM behavior

environment-management.md

You need Docker, preview envs, auth setup, mail capture, or local-only E2E workflow

ephemeral-env-test-data.md

You need test isolation, factories, preview environments, or network interception strategy

debug-monitoring.md

You are diagnosing flake, console issues, traces, HARs, or retries

edge-cases-i18n.md

Timezone, locale, cookie, storage, offline, or network-condition cases matter

cloud-testing.md

BrowserStack / Sauce Labs / LambdaTest / AWS Device Farm / Firebase Test Lab sessions — matrices, App Automate config, tunnels, parallel-session caps, cost-tier strategy, credentials

mobile-testing.md

Artifact is a shipping .ipa/.apk/.aab or RN bundle — framework selection, mobile POM, accessibility-id locators, two-axis flake taxonomy, device-farm tier matrix, WebdriverIO+Appium config, real-device capabilities, mobile-emulation alternatives, rotation/push/airplane patterns. Start here for native mobile E2E.

2026-best-practices.md

You need full source citations for Playwright Test Agents, CLI-vs-MCP, axe-core ceiling, Datadog flake loop, mobile AI, Cypress AI, visual-regression tiers, synthetic convergence, Screenplay, Appium 3 BiDi, Playwright version notes, mobile/device-farm version notes, Privacy Manifest timeline, or flake/budget thresholds

e2e-anti-patterns.md

You need suite architecture, anti-pattern checks, or flaky-prevention thresholds

ai-powered-e2e-testing.md

AI-assisted planning, generation, healing, or cost/risk tradeoffs are in scope

container-testing.md

Container-based test environments, Testcontainers, or Docker-integrated E2E are required

web-component-testing.md

Shadow DOM, Lit, Stencil, or Web Component testing is required

api-e2e-testing.md

User-journey E2E through an API-only interface (Playwright APIRequestContext chains, mock-vs-real backend toggle, contract-test follow-up)

component-testing.md

Component tests in a real browser (Playwright Component Testing, Cypress Component Testing, Storybook Interactions)

recipe-verify-gates.md

You need the full rationale and VERIFY checklist for a Recipe beyond the one-line summary under ## Subcommand Dispatch

OPUS_5_AUTHORING.md

You are sizing the test plan, calibrating effort to risk-tier, or front-loading critical journey scope at PLAN. Critical for Voyager: P3, P6.

PROOF_CARRYING.md

You are invoked from nexus acceptance Phase 2 (UI flows + visual regression as Layer 2 oracles) and Phase 3 (adversarial UI users — impatient / mobile / screen-reader / broken-connection / payment-failure personas). Adversarial-finding outputs must include non-trivial exploration logs; empty findings are rejected as semantically empty.

reference/autorun-schema.md

You are emitting the AUTORUN _STEP_COMPLETE block — Voyager-specific Output/Next schema.

_common/CODE_QUALITY.md

You are about to write or modify code — the 7-axis quality bar (SLD/SEC/RDB/MNT/TST/PRF/SCL), its sourced anti-patterns, and the CODE_QUALITY_GATE emitted before done.

Phase	Focus	Required checks
PLAN	Choose framework, scope, and environment; explore intent (Planner)	Critical journeys, risk tags (`@critical`/`@smoke`/`@regression`), test-data strategy, environment plan, visual-regression tier (pixel / perceptual / Visual AI)
AUTOMATE	Implement reusable tests (Generator)	Page Objects (or Screenplay for complex narrative journeys), fixtures/helpers, stable selectors, deterministic assertions
STABILIZE	Remove flake and false confidence (Healer)	Wait strategy, auth reuse, data isolation, retry evidence; axe-core + IGT — never sign off "a11y covered" from automation alone (57% ceiling); quarantine tests flaking > 10% over 30 days
SCALE	Operationalize in CI/CD	Sharding, artifacts, reports, browser/device matrix, failure diagnostics
DELIVER	Route results and escalate	Coverage/bug reports to downstream (Radar / Judge / Guardian); escalate synthetic-monitoring deployment to Beacon and CI infra changes to Gear

Direction	Handoff	Purpose
Radar → Voyager	`RADAR_TO_VOYAGER`	Test escalation when unit/integration is insufficient
Artisan → Voyager	`ARTISAN_TO_VOYAGER`	E2E test request based on component specification
Builder → Voyager	`BUILDER_TO_VOYAGER`	E2E test request for new features
Attest → Voyager	`ATTEST_TO_VOYAGER`	E2E verification based on acceptance criteria
Director → Voyager	`DIRECTOR_TO_VOYAGER`	E2E scenarios for demo flows
Flow → Voyager	`FLOW_TO_VOYAGER`	UX test requests for animation-related behavior
Native → Voyager	`NATIVE_TO_VOYAGER`	Mobile E2E test handoff for shipped iOS/Android apps (build artifact path, accessibility-id taxonomy, supported OS matrix, store-tier release-gate criteria)
Voyager → Radar	`VOYAGER_TO_RADAR`	Coverage reports and test pyramid delegation
Voyager → Scout	`VOYAGER_TO_SCOUT`	Flaky test root cause investigation request
Voyager → Gear	`VOYAGER_TO_GEAR`	CI pipeline configuration request
Voyager → Judge	`VOYAGER_TO_JUDGE`	Test quality metrics
Voyager → Builder	`VOYAGER_TO_BUILDER`	Bug reports discovered during E2E runs
Voyager → Vector	`VOYAGER_TO_NAVIGATOR`	Browser task execution delegation
Voyager → Bolt	`VOYAGER_TO_BOLT`	Performance regression fix request
Voyager → Siege	`VOYAGER_TO_SIEGE`	Load testing delegation
Oracle → Voyager	`ORACLE_TO_VOYAGER`	AI-powered testing strategy and MCP agent guidance
Voyager → Oracle	`VOYAGER_TO_ORACLE`	AI test agent evaluation and cost/risk tradeoff assessment

Agent	Voyager owns	They own
Radar	E2E browser-level journey tests	Unit, integration, and edge case tests
Vector	Reusable E2E test automation	Ad-hoc browser task execution
Siege	E2E functional validation	Load, chaos, and resilience testing
Director	E2E test scenarios for journeys	Demo video recording and production
Attest	E2E test implementation	Specification-level acceptance criteria
Native	Native mobile E2E test harness around the shipped app (Detox/Maestro/Appium/XCUITest/Espresso, accessibility-id locators, device-farm orchestration)	Production native app implementation (SwiftUI/Compose, store compliance, navigation/data layer)
Forge	E2E for shipping `.ipa`/`.apk`/`.aab` (production-bound)	Throwaway mobile PoC (Expo/RN/Flutter, native capabilities stubbed, ≤4h time-box)

Recipe	Subcommand	Default?	When to Use	Read First
Playwright Suite	`playwright`	✓	Playwright E2E test suite creation	`reference/playwright-patterns.md`
Page Object	`page-object`		Page Object Model design and implementation	`reference/playwright-patterns.md`
Auth Flow	`auth`		Authentication flow E2E tests	`reference/complex-scenarios.md`
Accessibility	`a11y`		Accessibility automated testing	`reference/visual-a11y-testing.md`
Visual Regression	`visual`		Visual regression testing	`reference/visual-a11y-testing.md`
API E2E	`api`		User-journey E2E through an API-only interface (no UI): HTTP call → backend state → downstream API validation chain	`reference/api-e2e-testing.md`
Mobile E2E	`mobile`		E2E testing for shipped mobile apps (Detox / Maestro / Appium / device farm)	`reference/mobile-testing.md`
Component Test	`component`		Component tests executed in a real browser (Playwright CT / Cypress CT / Storybook Interactions)	`reference/component-testing.md`

voyager

Options d'installation

Vérifiez les fichiers source

Voyager

Trigger Guidance

Voyager

Trigger Guidance

Core Contract

Boundaries

Always

Ask First

Never

Workflow

Collaboration

Overlap Boundaries

Recipes

Subcommand Dispatch

Signal Keywords → Recipe

Handoff Thresholds

Output Requirements

Reference Map

Operational

AUTORUN Support

Nexus Hub Mode

name	voyager
description	Authoring E2E tests for web (Playwright/Cypress/WebdriverIO) and native mobile (Appium/Detox/Maestro/XCUITest/Espresso). Covers Page Object design, auth flows, parallel execution, visual regression, a11y, CI, and remote device-farm (BrowserStack/Sauce Labs/AWS/Firebase). Use when authoring E2E suites. Not for unit (Radar), load/chaos (Siege), ad-hoc browser (Vector), or native impl (Native).

voyager

Informations de source

Options d'installation

Vérifiez les fichiers source

Plus depuis ce dépôt

Plus depuis ce dépôt

Voyager

Trigger Guidance

Voyager

Trigger Guidance

Core Contract

Boundaries

Always

Ask First

Never

Workflow

Collaboration

Overlap Boundaries

Recipes

Subcommand Dispatch

Signal Keywords → Recipe

Handoff Thresholds

Output Requirements

Reference Map

Operational

AUTORUN Support

Nexus Hub Mode