ce-test-browser

Run browser tests for pages affected by the current branch or PR.

Quality

82%

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

100%Weight 40%Scale 1-3

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

The content is concise, highly actionable, and structured as a clear validated workflow with well-signaled one-level-deep references, representing strong progressive disclosure and executable guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational with no padding about what browser tests or PRs are; it assumes Claude's competence and every section earns its place with concrete policy and commands.	3 / 3
Actionability	It provides fully executable commands (gh pr view, git diff, lsof checks, agent-browser invocations) and a concretely specified cross-harness visibility question, copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	A clear 10-step sequence includes explicit validation checkpoints (verify server before asking, confirm root before iterating) and an error feedback loop (document, fix, re-run) in step 9.	3 / 3
Progressive Disclosure	The SKILL.md is an overview with two well-signaled one-level-deep references (agent-browser-driver.md, pipeline-orchestration.md), both real files, each loaded only when its condition applies, with no nested reference chains.	3 / 3
	Total	12 / 12 Passed

Description

65%Weight 40%Scale 1-3

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 concise, concrete, and uses natural trigger terms, but it omits an explicit 'Use when' clause, leaving the trigger condition implied and capping both completeness and distinctiveness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to browser-test pages changed by the current branch or an open PR'.

Expand the action list to name the concrete behaviors (navigate affected routes, capture screenshots, verify key elements) to lift specificity toward 3.

Sharpen distinctiveness by contrasting with unit/API test skills, e.g. 'for end-to-end browser tests only, not unit or API tests'.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Run browser tests for pages affected by the current branch or PR'), but does not list multiple specific actions, matching the anchor for partial completeness rather than comprehensive.	2 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the 'when' is only implied by the branch/PR phrasing, which caps completeness at 2 per the judging guideline.	2 / 3
Trigger Term Quality	'browser tests', 'pages affected', 'current branch', and 'PR' are natural terms users would actually say, with good coverage of common phrasings rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The branch/PR scoping gives it a niche, but 'Run browser tests' could still overlap with generic test-runner skills since explicit distinguishing triggers are absent.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-test-browser/SKILL.md
Commit: a9f6d53

Reviewed: 7 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.