All skills
callstackincubator avatar

/dogfood

@23643af official

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.

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

This session only. Nothing lands on disk.

templatesdogfood-report-template.md

≈435 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Dogfood Report: {APP_NAME}

Field Value
Date {DATE}
Platform {PLATFORM}
Target App {TARGET_APP}
Session {SESSION_NAME}
Scope {SCOPE}

Summary

Severity Count
Critical 0
High 0
Medium 0
Low 0
Total 0

Issues

<!-- Copy this block for each issue found. Interactive issues need video + step screenshots. Static issues can be screenshot-only (Repro Video = N/A). -->

ISSUE-001: {Short title}

Field Value
Severity critical / high / medium / low
Category visual / functional / ux / content / performance / diagnostics / permissions / accessibility
Screen / Route {screen where issue was found}
Repro Video {path to video, or N/A for static issues}

Description

{What is wrong, what was expected, and what actually happened.}

Repro Steps

  1. Open {screen/entry point} Step 1

  2. {Action} Step 2

  3. {Action} Step 3

  4. Observe: {broken behavior} Result


Source: SKILL.md on GitHub

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

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
What it can do
Runs commands
All 2 allowed tools
Bash(agent-device:*)Bash(npx agent-device:*)
  • Testing
  • mobile
  • ios
  • android
  • qa
  • bug-hunting
  • agent-device
  • exploratory-testing

README badge

README badge for callstackincubator/agent-skills/dogfood

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.

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.