Dogfood Exploratory QA
vercel-labs/agent-browser
Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue.
Validates or debugs a workflow in the embedded browser with a reproducible, evidence-first loop that separates product failures from wait or locator problems.
Install Browser QA Repro Loop
$ npx skills add holaboss-ai/holaOS --skill browser-qa -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install holaboss-ai/holaOS browser-qa --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/holaboss-ai/holaOS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/harnesses/src/embedded-skills/browser-qa .claude/skills/browser-qa && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "browser-qa" agent skill from https://github.com/holaboss-ai/holaOS/tree/main/runtime/harnesses/src/embedded-skills/browser-qa into .claude/skills/browser-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-qa", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/holaboss-ai/holaOS/tree/main/runtime/harnesses/src/embedded-skills/browser-qaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add holaboss-ai/holaOS --skill browser-qa -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install holaboss-ai/holaOS browser-qa --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holaboss-ai/holaOS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/runtime/harnesses/src/embedded-skills/browser-qa .agents/skills/browser-qa && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "browser-qa" agent skill from https://github.com/holaboss-ai/holaOS/tree/main/runtime/harnesses/src/embedded-skills/browser-qa into .agents/skills/browser-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-qa", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add holaboss-ai/holaOS --skill browser-qa -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install holaboss-ai/holaOS browser-qa --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holaboss-ai/holaOS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/runtime/harnesses/src/embedded-skills/browser-qa .cursor/skills/browser-qa && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "browser-qa" agent skill from https://github.com/holaboss-ai/holaOS/tree/main/runtime/harnesses/src/embedded-skills/browser-qa into .cursor/skills/browser-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-qa", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/holaboss-ai/holaOS.git --path runtime/harnesses/src/embedded-skills/browser-qa--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add holaboss-ai/holaOS --skill browser-qa -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install holaboss-ai/holaOS browser-qa --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holaboss-ai/holaOS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/runtime/harnesses/src/embedded-skills/browser-qa .gemini/skills/browser-qa && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "browser-qa" agent skill from https://github.com/holaboss-ai/holaOS/tree/main/runtime/harnesses/src/embedded-skills/browser-qa into .gemini/skills/browser-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-qa", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install holaboss-ai/holaOS browser-qaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add holaboss-ai/holaOS --skill browser-qa -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/holaboss-ai/holaOS.git skills-src && mkdir -p .github/skills && cp -r skills-src/runtime/harnesses/src/embedded-skills/browser-qa .github/skills/browser-qa && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "browser-qa" agent skill from https://github.com/holaboss-ai/holaOS/tree/main/runtime/harnesses/src/embedded-skills/browser-qa into .github/skills/browser-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-qa", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add holaboss-ai/holaOS --skill browser-qa -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install holaboss-ai/holaOS browser-qa --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holaboss-ai/holaOS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/runtime/harnesses/src/embedded-skills/browser-qa .opencode/skills/browser-qa && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "browser-qa" agent skill from https://github.com/holaboss-ai/holaOS/tree/main/runtime/harnesses/src/embedded-skills/browser-qa into .opencode/skills/browser-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "browser-qa", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
browser-qa- GitHub stars
- 11k
- Token cost
- ~712 tokens
- SKILL.md length
- 363 words
- Files
- 1
- Skills in repo
- 30
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Validates or debugs a workflow in the embedded browser with a reproducible, evidence-first loop that separates product failures from wait or locator problems.
- Works in 5 steps: State the exact starting page, tab, and… → Use the cheapest path that can reproduce… → After each page-changing step, use… → …
- Reproducing a browser bug with as few tool calls as possible
- SKILL.md covers Goals, Repro Loop, Tool Discipline and Evidence Rules, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The agent states the exact starting page, tab and account state, takes the cheapest path that reproduces the behavior, and uses explicit waits after each page-changing step. When a step fails it sorts the cause into wrong target, stale target, missing wait, auth or session state, or true product behavior, and it captures evidence only once the failure is stable.
Tool guidance favors `browser_act` with `wait_for`, `browser_find` for known targets and compact `browser_get_state` for orientation, with console, error and request tools used only after the cheaper paths fail. Storage and cookie reads can check auth state, and the setters are for controlled repair only. Screenshots are for visual ambiguity, page text is read only when content matters, and the final report keeps the exact failing target, wait, URL and observed result. The excerpt ends in the final reporting section.
When your agent uses it
- Reproducing a browser bug with as few tool calls as possible
- Telling a real product failure from a bad locator or missing wait
- Checking a regression in the embedded browser and reporting the evidence
Example prompts
- “Reproduce the checkout button failing on the cart page and tell me whether it is a real bug or a timing problem.”
- “Find out why the login flow loops back to the sign-in screen and capture only the evidence that matters.”
- “Verify that the CSV export download completes in the embedded browser.”
Requirements
- The workspace's embedded browser tools, such as `browser_act` and `browser_find`
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- State the exact starting page, tab, and account state you are testing.
- Use the cheapest path that can reproduce the behavior.
- After each page-changing step, use explicit waits rather than repeated broad state reads.
- If a step fails, determine whether it is
- Capture evidence only after the failure is stable and reproducible.
What it can do on your machine
Read from SKILL.md and the folder at commit 4684714. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Browser QA Repro Loop loads about 712 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 363 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 363 words (~712 tokens).
“Use this skill when the task is browser validation, repro, regression checking, or investigation in the workspace-embedded browser.”
- name
- browser-qa
Files
Just SKILL.md in runtime/harnesses/src/embedded-skills/browser-qa of holaboss-ai/holaOS.
Open the folder on GitHubat commit 4684714
Compare with similar skills
Browser QA Repro Loop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Browser QA Repro Loop this skillholaboss-ai/holaOS | 11k | — | ~712 | Automated safety check: Pass | Custom licence | |
| Dogfood Exploratory QAvercel-labs/agent-browser | 44k | 8 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Hands On Testktnyt/cclsp | 675 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Diff-Driven Smoke TestsSkyvern-AI/skyvern | 23k | — | ~5.2k | Automated safety check: Pass | AGPL-3.0 | |
| Dogfoodredf0x1/camofox-browser | 411 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Diff-Driven QASkyvern-AI/skyvern | 23k | — | ~4.7k | Automated safety check: Warn | AGPL-3.0 |
Similar skills
- Official
Hands On Test
ktnyt/cclsp
Performs manual hands-on testing of a web application using playwright-cli.
Diff-Driven Smoke Tests
Skyvern-AI/skyvern
Reads your git diff, writes a handful of happy-path browser smoke tests, runs them with Skyvern or Chrome DevTools MCP and posts screenshot evidence to the PR.
Dogfood
redf0x1/camofox-browser
QA testing workflow for CamoFox Browser — systematic testing with console capture, error detection, and Playwright tracing.
Diff-Driven QA
Skyvern-AI/skyvern
Reads your git diff, decides whether the change needs browser QA, API checks or repo tests, runs that validation and reports pass or fail with evidence.
Interactive Testing
Porabuild/Poracode
Run repeatable integration and smoke testing against the real Poracode Electron app through Chrome DevTools Protocol.
More from holaboss-ai/holaOS
All 30 skills in this repoInterface Design for Dashboards and Apps
holaboss-ai/holaOS
Pushes an agent past generic defaults when designing dashboards, admin panels, SaaS apps and tools, with attention to structure, type, navigation and how data is shown.
Customize an Installed Capability
holaboss-ai/holaOS
Edits an already-installed workspace capability's manifest to add an MCP server, a skill, an integration or agent guidance, then reinstalls it so the change takes effect on the next run.
Dashboard Builder for holaOS
holaboss-ai/holaOS
Builds the visual layer of a holaOS dashboard app with TanStack Start and @holaboss/ui, starting from a bundled reference instead of a blank page.
Capability Creator
holaboss-ai/holaOS
Bundles one or more existing skills and the integrations they need into a single named, installable capability.
Efficient Embedded Browser Loop
holaboss-ai/holaOS
Guidelines for driving a workspace's embedded browser with the fewest tool calls, smallest state reads and no needless screenshots or waits.
holaOS MCP Configurator
holaboss-ai/holaOS
Adds, removes or updates MCP servers in a holaOS workspace by editing workspace.yaml in the mcp_registry format, with rules for headers, local servers and tool allowlists.
Related
Categories
Questions about Browser QA Repro Loop
What does Browser QA Repro Loop do?
Validates or debugs a workflow in the embedded browser with a reproducible, evidence-first loop that separates product failures from wait or locator problems. The agent states the exact starting page, tab and account state, takes the cheapest path that reproduces the behavior, and uses explicit waits after each page-changing step. When a step fails it sorts the cause into wrong target, stale target, missing wait, auth or session state, or true product behavior, and it captures evidence only once the failure is stable.
When should I use Browser QA Repro Loop?
Browser QA Repro Loop fits situations like: reproducing a browser bug with as few tool calls as possible; telling a real product failure from a bad locator or missing wait; checking a regression in the embedded browser and reporting the evidence.
How do I install Browser QA Repro Loop in Claude Code?
Run `npx skills add holaboss-ai/holaOS --skill browser-qa -a claude-code`. Or copy the skill folder (runtime/harnesses/src/embedded-skills/browser-qa in holaboss-ai/holaOS) into .claude/skills/browser-qa in your project. Claude Code loads it when a task matches its description.
How do I install Browser QA Repro Loop in Codex?
Run `npx skills add holaboss-ai/holaOS --skill browser-qa -a codex`. Or copy the skill folder (runtime/harnesses/src/embedded-skills/browser-qa in holaboss-ai/holaOS) into .agents/skills/browser-qa in your project. Codex loads it when a task matches its description.
Can I use Browser QA Repro Loop in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add holaboss-ai/holaOS --skill browser-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/browser-qa, .gemini/skills/browser-qa, .github/skills/browser-qa and .opencode/skills/browser-qa in your project.
What does Browser QA Repro Loop need to run?
SKILL.md names no scripts, command-line tools or credentials: Browser QA Repro Loop is instructions for the agent only. Our summary lists: The workspace's embedded browser tools, such as `browser_act` and `browser_find`.
Does Browser QA Repro Loop access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Browser QA Repro Loop safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Browser QA Repro Loop use?
Browser QA Repro Loop has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Browser QA Repro Loop use?
About 712 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Browser QA Repro Loop?
Skills that share tags, products or a category with Browser QA Repro Loop: Dogfood Exploratory QA (vercel-labs/agent-browser, 44k stars), Hands On Test (ktnyt/cclsp, 675 stars), Diff-Driven Smoke Tests (Skyvern-AI/skyvern, 23k stars) and Dogfood (redf0x1/camofox-browser, 411 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Browser QA Repro Loop?
holaboss-ai (a GitHub organization) maintains it in holaboss-ai/holaOS, which has 11,451 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on August 21, 2026.
Source: holaboss-ai/holaOS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.