agent-browser-issue

Open a concise GitHub follow-up for reusable browser-use limitations. Use when browser automation is blocked by a likely tool-side issue that is worth fixing separately, especially for clicks, dropdowns, file inputs, focus traps, or other repeatable agent/browser failures.

Quality

95%

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%

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

A concise, well-structured instruction skill that tells Claude exactly what to collect, how to format the GitHub issue (label + template), and what to do afterward. No bundle files are needed and the content is appropriately scoped.

Dimension	Reasoning	Score
Conciseness	The body is lean: minimal bullet lists ("Capture only the minimum"), a tight issue-body template, and no explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	It gives concrete, copy-paste-ready guidance: the exact label `agent:browser`, the fields to collect, and a structured body template with named sections, which is actionable for an instruction-only skill.	3 / 3
Workflow Clarity	The Collect → Issue → After sections form a clear, ordered sequence, and the After section provides handoff guidance; for this simple non-destructive task no validation checkpoint is needed.	3 / 3
Progressive Disclosure	It is a short, single-purpose skill with no need for external bundle files, and its well-organized sections (Collect, Issue, After) keep everything one level deep with clear navigation.	3 / 3
	Total	12 / 12 Passed

Description

90%

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 tight, third-person description with an explicit Use-when trigger and a clearly bounded niche. Its only weakness is that it describes a single action rather than multiple concrete capabilities, capping specificity at 2.

Suggestions

Broaden the capability statement from one action to a few concrete verbs (e.g., "Open, title, and label a GitHub follow-up issue") to lift specificity toward 3.

Dimension	Reasoning	Score
Specificity	It names one concrete action ("Open a concise GitHub follow-up") and the failure domains (clicks, dropdowns, file inputs, focus traps), but does not list multiple distinct actions as the level-3 anchor requires.	2 / 3
Completeness	It states what it does ("Open a concise GitHub follow-up for reusable browser-use limitations") and an explicit "Use when browser automation is blocked..." trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	"browser automation is blocked", "clicks", "dropdowns", "file inputs", "focus traps", and "agent/browser failures" are natural terms a user would say when hitting this situation, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow (reusable tool-side browser/agent bugs) and explicitly excludes auth gates, human gates, and product bugs, making conflict with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/agent-browser-issue/SKILL.md
Commit: 45116fd

Reviewed: about 14 hours 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.