skilld
All skills
callstackincubator avatar

/dogfood

@23643af official
by Callstack Incubatorcallstackincubator/agent-skills1.7k stars
118

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", or "test this app" on mobile. Produces a structured report with reproducible evidence: screenshots, optional repro videos, and detailed steps for every issue.

Ask your Agent

Use this Skill: https://skilld.dev/gh/callstackincubator/agent-skills/dogfood

This session only. Nothing lands on disk.

referencesissue-taxonomy.md

≈726 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Issue Taxonomy (Mobile)

Reference for categorizing issues found during mobile dogfooding.

Severity Levels

Severity Definition
critical Blocks a core workflow, causes data loss, or crashes/freeze loops the app
high Major feature broken or unusable, no practical workaround
medium Feature works with notable friction or partial failure; workaround exists
low Minor cosmetic or polish issue

Categories

Visual / UI

  • Layout broken, clipped, overlapped, or unreadable text
  • Safe-area/notch overlap issues
  • Incorrect dark/light appearance rendering
  • Missing assets/icons
  • Animation glitches or flicker

Functional

  • Buttons/controls do nothing or trigger wrong action
  • Flows fail (create/edit/delete/submit)
  • Navigation dead-ends or wrong destination
  • State loss after background/foreground transitions
  • Deep link opens wrong screen or fails

UX

  • Confusing hierarchy or navigation labels
  • Missing loading/progress feedback
  • Unclear error handling or no recovery affordance
  • Excessive steps for common tasks
  • Inconsistent behavior between similar screens

Content

  • Typos, incorrect copy, placeholder text
  • Wrong labels/help text
  • Truncated text with no affordance
  • Inconsistent terminology across screens

Performance

  • Slow startup or route transitions
  • Input lag or gesture jank
  • Scroll hitches/frame drops
  • Notable battery/thermal symptoms during basic usage

Diagnostics / Logs

  • Native crashes or repeated fatal exceptions
  • Repeated warnings correlated with broken behavior
  • Unhandled runtime errors visible during repro

Permissions / Platform

  • Permission prompt flow broken or loops forever
  • Denied permissions not handled gracefully
  • Platform-specific regressions (iOS-only or Android-only)
  • Background/foreground lifecycle regressions

Accessibility

  • Missing labels or incorrect accessibility names
  • Focus order/navigation issues for assistive tech
  • Low contrast or unreadable text scaling
  • Touch targets too small for reliable interaction

Exploration Checklist

  1. Visual scan: capture screenshot; verify layout/safe areas/text/icon rendering.
  2. Interactions: press controls, open menus/modals, validate expected response.
  3. Forms/input: test valid/invalid/empty/boundary input.
  4. Navigation: traverse all top-level sections and return paths.
  5. App states: loading/empty/error/offline/permission-denied/background-resume.
  6. Logs/diagnostics: inspect app logs when behavior is suspicious.
  7. Platform parity: verify critical flows on each requested platform.
  8. Accessibility basics: labels, touch target sizes, readability/contrast.

Source: SKILL.md on GitHub

Third-party checks

1 warning16d3 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill is a utility for automated mobile application testing (dogfooding). It uses the 'agent-device' tool to interact with iOS and Android devices, capture screenshots/videos, and generate structured reports. It handles user-provided credentials to facilitate app authentication during testing.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 1 issue

Provenance

Signed by skilld at 23643af. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Activeupdated 6 months ago

Capability

What it can do
Runs commands
All 2 allowed tools
Bash(agent-device:*)Bash(npx agent-device:*)

Topics

  • Testing
  • mobile
  • ios
  • android
  • qa
  • bug-hunting
  • agent-device
  • exploratory-testing

README badge

README badge for callstackincubator/agent-skills/dogfood

What it does

Systematically explores a mobile app on iOS or Android using agent-device, documents bugs and UX issues with screenshots and optional videos, and produces a structured report with reproducible steps for each finding. Use this skill when asked to QA, dogfood, or exploratory test a mobile app.

Generated from the current SKILL.md.

Frequently asked

What platforms does this skill support?
iOS and Android. The skill infers platform from user context or asks if ambiguous.
Do I need to provide credentials to test a protected app?
Only if required by the app. Authentication is optional; pass credentials as a parameter if login is needed.
What does the skill output?
A structured report with screenshots, optional repro videos, and step-by-step instructions for each issue found. Issues are categorized by severity and stored in a timestamped output directory.
Does this skill require agent-device to be installed?
Yes. The skill uses the agent-device binary or npx agent-device to control and inspect the mobile app.
How many issues should I expect to find?
The skill targets 5-10 well-evidenced issues per session, prioritizing repro quality over issue count.

Generated from the current SKILL.md. These answers refresh after source changes.