browser-qa

Use when validating or debugging a workflow in the embedded browser and you need a reproducible, evidence-first loop.

Quality

81%

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

93%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.

An exemplary lean, highly actionable skill body that names specific tools and parameters, sequences the debugging workflow with decision branches, and stays well within token budget without needing external files.

Dimension	Reasoning	Score
Conciseness	The body is lean bullet-point guidance with no concept padding (no explaining what a browser or wait is); every line earns its place and assumes Claude's competence.	5 / 5
Actionability	Names exact tools and flags (browser_act with wait_for, browser_get_state detail=compact, narrow read-only browser_evaluate, browser_list_requests then browser_get_request), giving copy-paste-ready executable guidance for the common cases.	5 / 5
Workflow Clarity	The Repro Loop is a clear 5-step sequence with a failure-classification decision tree and a 'capture evidence only after stable and reproducible' checkpoint, but an explicit fix-and-revalidate retry statement is implied rather than stated.	4 / 5
Progressive Disclosure	A single under-50-line SKILL.md with no external references, organized into well-labeled sections (Goals, Repro Loop, Tool Discipline, Evidence Rules, Final Reporting), which meets the simple-skill exception for a top score.	5 / 5
	Total	19 / 20 Passed

Description

70%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 solid, mostly third-person description with an explicit trigger clause and a clear niche, but it leans on methodology phrasing rather than enumerating concrete capabilities, leaving specificity and completeness just short of the top anchors.

Suggestions

Lead with 1-2 concrete capabilities (e.g., 'Reproduces and diagnoses browser workflow failures') before the 'Use when' clause to sharpen the 'what'.

Add common trigger synonyms users say naturally, such as 'browser testing', 'repro', or 'regression checking'.

Reframe 'evidence-first loop' into a more user-natural phrase or drop it in favor of a concrete action.

Dimension	Reasoning	Score
Specificity	Names the domain ("embedded browser") and two concrete actions ("validating or debugging") plus a methodology ("reproducible, evidence-first loop"), but does not list several specific concrete actions as the 4/5 anchors require.	3 / 5
Completeness	The "Use when..." clause gives an explicit, specific trigger, and the "what" (a reproducible, evidence-first validation/debugging loop) is present but folded into the trigger rather than stated as a standalone capability list.	4 / 5
Trigger Term Quality	"validating", "debugging", "workflow", and "embedded browser" are natural terms a user would say; a few common synonyms (testing, repro, regression) are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The "embedded browser" niche is clearly distinct with minimal conflict risk against generic skills, though "reproducible, evidence-first loop" is slightly abstract and could overlap with general debugging skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: holaboss-ai/holaOS
Path: runtime/harnesses/src/embedded-skills/browser-qa/SKILL.md
Commit: 4684714

Reviewed: 12 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.