dogfood

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.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable body that walks through a concrete mobile-QA workflow with executable commands and a clear reference table. Its main gap is a referenced template file missing from the bundle, plus minor duplication and a lack of explicit validation in the wrap-up step.

Suggestions

Ship the missing templates/dogfood-report-template.md bundle file referenced in the Initialize cp command and Templates table, or remove the reference so navigation is not broken.

Add an explicit validation checkpoint in Wrap-Up — e.g., verify every screenshot/video referenced in report.md exists on disk before running 'agent-device close' — to turn it into a validate→fix→retry loop.

Trim the duplicated snapshot/screenshot commands in the 'Useful commands per screen' block since they restate commands already shown in Orient and Explore.

Dimension	Reasoning	Score
Conciseness	The body is largely lean — tables, tight bullets, and direct commands with no padding about concepts Claude already knows — but the per-screen 'Useful commands' block repeats snapshot/screenshot commands already shown in Orient/Explore, which could be trimmed.	4 / 5
Actionability	Fully executable copy-paste-ready agent-device commands throughout (launch, login fill, screenshot, record start/stop, close) with placeholders defined in the Setup table, covering the common cases.	5 / 5
Workflow Clarity	A clear six-step numbered workflow with implicit checkpoints ('diff snapshot -i' after transitions, 'Re-snapshot after any mutation'), but there is no explicit validate→fix→retry feedback loop in Wrap-Up (e.g., confirming all referenced screenshots exist before closing the session).	4 / 5
Progressive Disclosure	Good one-level-deep structure with References and Templates tables signaling when to read each file, but templates/dogfood-report-template.md is referenced in both the cp command and Templates table yet is absent from the bundle, undermining navigation.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that crisply states capabilities, supplies a rich set of natural trigger phrases, and cleanly separates what-it-does from when-to-use-it. It is distinct from other skills and free of vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'explore and test a mobile app', 'find bugs, UX issues, and other problems', and 'Produces a structured report with reproducible evidence: screenshots, optional repro videos, and detailed steps' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (systematically explore/test a mobile app to find bugs/UX issues and produce an evidenced report) and 'when' ('Use when asked to...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases users would actually say — 'dogfood', 'QA', 'exploratory test', 'find issues', 'bug hunt', 'test this app' — including synonyms and a mobile qualifier.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (mobile app dogfooding/QA via agent-device on iOS/Android) with distinct triggers, making overlap with other skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: callstackincubator/agent-skills
Path: plugins/vendored/.agents/skills/dogfood/SKILL.md
Commit: 61e6e7d

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.