agentleFS
d-o-hubd-o-hub/github-template-ai-agents/.agents/skills/dogfood/SKILL.md

dogfood

Skill2 starsChanged 13 days agoMITView on GitHub

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence. Not for test-runner, accessibility-auditor.

81 other projects use a version of this, 19 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use dep-refs, feature-boundary-planner and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • betacatslingSkill

    dep-refs

    Use when needs to inspect TypeScript export references in the z-code workspace, list exports from a file, verify whether an export is unused before deletion, investigate who imports a symbol during refactors, or combine pnpm knip unused-export results with pnpm dep:refs symbol-level reference tracing.

    Also in 5 projects that use this

  • betacatslingSkill

    feature-boundary-planner

    Map a ZCode behavior change to current UI surfaces, state owners, protocol commands, persistence, and validation. Use for impact analysis, product-boundary planning, or an implementation handoff grounded in the checked-out source.

    Also in 5 projects that use this

  • lir-navcooSkill

    yuanbao

    Yuanbao (元宝) groups: @mention users, query info/members.

    Also in 18 projects that use this

  • Cartograf666Skill

    architecture-governance

    Bootstrap, document, enforce, and review a project's architecture through layer responsibilities, dependency direction, architecture manifests, legacy baselines, Change Envelopes, cross-layer approval policy, and deterministic architecture checks. Use when starting a project, auditing an existing codebase, planning cross-layer work, preventing architecture erosion, reviewing structural changes, or deciding whether implementation may expand into another layer.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 7 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 13 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 81 edited versions we read keep these.

  • 13

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Only the Target URL is required.

    line 21
  2. Distinctive:

    If the user says something like "dogfood vercel.com", start immediately with defaults.

    line 31
  3. Very specific:

    Always use agent-browser directly -- never npx agent-browser.

    line 33
  4. Distinctive:

    Start a named session:

    line 52
  5. Distinctive:

    If the app requires login:

    line 61
  6. Distinctive:

    After successful login, save state for potential reuse:

    line 74
  7. Distinctive:

    Start from the main navigation.

    line 94
  8. Distinctive:

    Check edge cases: empty states, error handling, boundary inputs.

    line 96
  9. Distinctive:

    Check the browser console for errors periodically.

    line 98
  10. Distinctive:

    Use your judgment on how deep to go.

    line 109
  11. Distinctive:

    Every issue must be reproducible.

    line 113
  12. Very specific:

    Start a repro video: agent-browser --session {SESSION} record start {OUTPUT_DIR}/videos/issue-{NNN}-repro.webm

    line 116
  13. Distinctive:

    Stop video and write numbered repro steps in report

    line 119
  14. Distinctive:

    Repro is everything: Every issue needs proof matched to its type.

    line 134
  15. Distinctive:

    Never read the target app's source code: All findings must come from browser observation.

    line 138

“Common” is measured: kept by at least 6 in 10 of the 81 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dogfood

Systematically explore a web application, find issues, and produce a report with full reproduction evidence for every finding.

When to Use

  • User asks to dogfood, QA, or exploratory test a web application
  • Need to find bugs, UX issues, or other problems in a web app
  • Even if they just say "test this app" or "find issues in this site"

Setup

Only the Target URL is required. Everything else has sensible defaults -- use them unless the user explicitly provides an override.

ParameterDefaultExample override
Target URL(required)vercel.com, http://localhost:3000
Session nameSlugified domain (e.g., vercel.com -> vercel-com)--session my-session
Output directory./dogfood-output/Output directory: /tmp/qa
ScopeFull appFocus on the billing page
AuthenticationNoneSign in to user@example.com

If the user says something like "dogfood vercel.com", start immediately with defaults. Do not ask clarifying questions unless authentication is mentioned but credentials are missing.

Always use agent-browser directly -- never npx agent-browser. The direct binary uses the fast Rust client. npx routes through Node.js and is significantly slower.

Workflow

1. Initialize      Set up session, output dirs, report file
2. Authenticate    Sign in if needed, save state
3. Orient          Navigate to starting point, take initial snapshot
4. Explore         Systematically visit pages and test features
5. Document        Screenshot + record each issue as found
6. Wrap up         Update summary counts, close session

1. Initialize

mkdir -p {OUTPUT_DIR}/screenshots {OUTPUT_DIR}/videos

Start a named session:

agent-browser --session {SESSION} open {TARGET_URL}
agent-browser --session {SESSION} wait --load networkidle

2. Authenticate

If the app requires login:

agent-browser --session {SESSION} snapshot -i
# Identify login form refs, fill credentials
agent-browser --session {SESSION} fill @e1 "{EMAIL}"
agent-browser --session {SESSION} fill @e2 "{PASSWORD}"
agent-browser --session {SESSION} click @e3
agent-browser --session {SESSION} wait --load networkidle

For OTP/email codes: ask the user, wait for their response, then enter the code.

After successful login, save state for potential reuse:

agent-browser --session {SESSION} state save {OUTPUT_DIR}/auth-state.json

3. Orient

Take an initial annotated screenshot and snapshot to understand the app structure:

agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/initial.png
agent-browser --session {SESSION} snapshot -i

Identify the main navigation elements and map out the sections to visit.

4. Explore

Strategy -- work through the app systematically:

  • Start from the main navigation. Visit each top-level section.
  • Within each section, test interactive elements: click buttons, fill forms, open dropdowns/modals.
  • Check edge cases: empty states, error handling, boundary inputs.
  • Try realistic end-to-end workflows (create, edit, delete flows).
  • Check the browser console for errors periodically.

At each page:

agent-browser --session {SESSION} snapshot -i
agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/{page-name}.png
agent-browser --session {SESSION} errors
agent-browser --session {SESSION} console

Use your judgment on how deep to go. Spend more time on core features and less on peripheral pages.

5. Document Issues (Repro-First)

Every issue must be reproducible. When you find something wrong, stop exploring and document it immediately.

For interactive issues (functional, UX, console errors on action):

  1. Start a repro video: agent-browser --session {SESSION} record start {OUTPUT_DIR}/videos/issue-{NNN}-repro.webm
  2. Walk through steps at human pace with screenshots between actions
  3. Capture the broken state with annotated screenshot
  4. Stop video and write numbered repro steps in report

For static issues (typos, clipped text, visual glitches on load):

  • Single annotated screenshot is sufficient. No video needed.

6. Wrap Up

Aim to find 5-10 well-documented issues, then wrap up. Depth of evidence matters more than total count.

  1. Re-read the report and update summary severity counts
  2. Close the session: agent-browser --session {SESSION} close
  3. Tell the user the report is ready with summary

Guidance

  • Repro is everything. Every issue needs proof matched to its type.
  • Verify before collecting evidence. Retry at least once to confirm reproducibility.
  • Use the right snapshot: snapshot -i for interactive elements, snapshot for reading content.
  • Never delete output files mid-session. Work forward, not backward.
  • Never read the target app's source code. All findings must come from browser observation.
  • Check the console. Many issues are invisible in the UI but show as JS errors.

See Also

  • test-runner — Execute tests and diagnose failures
  • testing-strategy — Choose testing approaches
  • accessibility-auditor — Accessibility-specific testing

Rationalizations

RationalizationReality
"Manual testing is too slow compared to automated tests"Automated tests verify logic; dogfooding catches usability and UX issues that scripts miss.
"I already know the app works, I built it"Builders have the curse of knowledge; systematic exploration reveals what users actually encounter.
"A few screenshots are enough for a report"Reproduction evidence must be complete and reproducible to be actionable.

Red Flags

  • Dogfood session skipped due to time pressure
  • Issues reported without reproduction steps or evidence
  • Only testing happy paths without edge cases or error states

References

  • references/issue-taxonomy.md - What to look for, severity levels, exploration checklist
  • templates/dogfood-report-template.md - Copy into output directory as the report file

Voice & Context

  • Default: professional + blog
  • Reference: voice-profiles skill for definitions and auto-detection.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.