Browser QA

Browser QA is a Quality skill for Claude Code, published by holaboss-ai in holaOS.

7.4K stars641 forkson holaboss-ai/holaOSAdded 2026/08/15+21% in starsRepository updated 2026/08/15

agentagent-harnessagent-osagenticaiai-agentai-agentsartificial-intelligenceclaude-codecodexelectronholabossholaosllmmcpmemorymodel-context-protocolruntimetypescriptworkspace

Install in seconds

Install Browser QA

Copy Browser QA into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/holaboss-ai/holaOS/tree/main/runtime/harnesses/src/embedded-skills/browser-qa ~/.claude/skills/browser-qa

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/holaboss-ai/holaOS.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: runtime/harnesses/src/embedded-skills/browser-qa/SKILL.md in holaboss-ai/holaOS
Installs to: ~/.claude/skills/browser-qa
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1354 skills

What Browser QA does

Browser QA reproduces and isolates failures in an embedded browser using an evidence-first loop, then reports whether the failure is locator, timing, session state, or product behavior. Use it for reproducible browser validation, regression checking, or debugging workflows.

Browser QA is cataloged under Quality on DirSkills. Browser QA comes from a repository tagged agent, agent-harness, agent-os, agentic and ai.

Documentation

README

Excerpt

Browser QA

Use this skill when the task is browser validation, repro, regression checking, or investigation in the workspace-embedded browser.

Goals

reproduce the issue with the fewest browser calls possible
separate product failure from wait or locator failure
capture only the evidence needed to explain the result

Repro Loop

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:
- wrong target
- stale target
- missing wait
- auth or session state
- true product behavior
Capture evidence only after the failure is stable and reproducible.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Browser QA

What else does holaboss-ai publish alongside Browser QA?
Browser QA is one of 25 skills that DirSkills catalogs from holaboss-ai/holaOS, the repository it ships in. Its siblings there include App Builder SDK, Audience Analyst and Browser Core Efficient. Each one is a separate skill with its own page in this directory, installs the same way Browser QA does, and is maintained by holaboss-ai in that same repository. The rest of the collection is listed on the holaboss-ai/holaOS page.
How does Browser QA compare to other Quality skills?
Browser QA ranks #240 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Browser QA against them. Open each page to compare what they document and how they install.