browser-qa

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

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./runtime/harnesses/src/embedded-skills/browser-qa/SKILL.md

Quality

Content

100%

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

The body is an exemplary lean, actionable instruction skill: it names specific browser tools and parameters, sequences the repro loop with a failure-classification feedback loop and stability gate, and stays tightly organized within a single well-structured file.

Dimension	Reasoning	Score
Conciseness	The body is a tight set of bullet points with no conceptual padding (it never explains what a browser or wait is); every line is actionable guidance and earns its tokens, matching the 'lean and efficient' anchor.	3 / 3
Actionability	Each bullet names a concrete tool and parameter (e.g., `browser_act` with `wait_for`, `browser_get_state detail=compact`, `browser_evaluate`, `browser_storage_get`), giving specific executable guidance appropriate to an instruction skill rather than vague direction.	3 / 3
Workflow Clarity	The 'Repro Loop' is a clear 5-step sequence with an explicit failure-classification feedback loop in step 4 and a 'stable and reproducible' gate before evidence capture in step 5, providing the sequence plus checkpoints the top anchor calls for.	3 / 3
Progressive Disclosure	At under 50 lines and single-purpose with no external references needed, the well-organized sections (Goals, Repro Loop, Tool Discipline, Evidence Rules, Final Reporting) satisfy the 'under 50 lines, well-organized sections' exception for a top score.	3 / 3
	Total	12 / 12 Passed

Description

57%

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

The description is distinct and trigger-focused with a clear 'Use when' clause, but it is light on enumerated concrete actions and leans on internal jargon ('evidence-first loop') rather than natural user phrasing. It answers 'when' more strongly than 'what'.

Suggestions

Lead with a concrete 'what' clause listing specific actions (e.g., 'Reproduce browser failures, classify them as locator/timing/session/product, and capture minimal evidence.'), then keep the 'Use when' trigger.

Replace or supplement 'reproducible, evidence-first loop' with natural user terms like 'regression checking', 'browser validation', or 'reproducing a bug'.

Add a couple of trigger variations (e.g., 'Use when validating, debugging, or regression-checking a workflow in the embedded browser') to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('embedded browser') and actions ('validating or debugging a workflow'), but does not enumerate multiple concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action list of a 3.	2 / 3
Completeness	The explicit 'Use when' clause answers 'when' clearly, but the 'what does this do' is only implied through the object of the when-clause rather than stated as a distinct capability, landing at the 'has what, but when is missing or only implied' boundary — here it is the inverse, with what being the weak side.	2 / 3
Trigger Term Quality	'validating' and 'debugging' are natural terms, but 'reproducible, evidence-first loop' is jargon a user would not say and common variations like 'regression' or 'testing' are absent, so coverage is partial rather than full.	2 / 3
Distinctiveness Conflict Risk	The 'embedded browser' framing carves a clear niche with distinct triggers unlikely to conflict with non-browser skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 12 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: 74c7b6f

Reviewed: 6 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.