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

86%

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

86%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.

A tight, well-structured instruction-only skill that gives Claude a concrete issue template and clear sequencing with a useful exclusion gate. The only soft spot is a lack of an explicit post-creation verification step, which keeps workflow clarity just below perfect.

Suggestions

Add a brief post-issue verification step in the 'After' section (e.g. 'Confirm the issue URL is reachable and paste it into the task caveat/handoff') to close the workflow's feedback loop.

Optionally include one short filled-in example of the issue body template so the fill-in placeholders have a concrete reference shape.

Consider stating how to obtain/confirm the correct GitHub repository for filing the agent:browser issue, since the skill assumes the target repo is already known.

Dimension	Reasoning	Score
Conciseness	Lean ~50-line body of terse bullets and a copy-paste issue template that assumes Claude's competence and explains no concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Provides a concrete, fill-in issue body template (URL/Action/Block/Expected/Actual/Repro) and a specific label (agent:browser); not a 5 because the template uses placeholders that require adaptation rather than being literally copy-paste-ready, and not a 3 because guidance is concrete rather than pseudocode.	4 / 5
Workflow Clarity	Clear Collect -> Issue -> After sequence with an explicit front gating check (exclusions list) filtering when to act; not a 5 because there is no explicit completion-verification or feedback loop (e.g. confirm the issue opened), though the destructive/batch cap does not apply to issue creation.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed and well-organized into clear sections (Collect, Issue, After); per the simple-skill exception this scores 5 on well-organized sections alone.	5 / 5
	Total	18 / 20 Passed

Description

87%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 strong description that clearly defines both what the skill does and when to use it, with concrete trigger scenarios and low conflict risk. Slightly shy of perfect only on specificity and trigger-term breadth, where a few more action verbs and synonyms could push it higher.

Dimension	Reasoning	Score
Specificity	Names the concrete action ('Open a concise GitHub follow-up') and enumerates several specific failure scenarios (clicks, dropdowns, file inputs, focus traps); not a 5 because the core action is a single operation with minor coverage gaps rather than a comprehensive multi-action list.	4 / 5
Completeness	Explicitly states both the what ('Open a concise GitHub follow-up for reusable browser-use limitations') and the when with concrete trigger phrases ('Use when browser automation is blocked by a likely tool-side issue... especially for clicks, dropdowns, file inputs, focus traps').	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('browser automation is blocked', 'clicks', 'dropdowns', 'agent/browser failures'); not a 5 because it lacks broader synonyms and file-extension-style terms, and not a 3 because keyword coverage is clearly good rather than partial.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (reusable browser/tooling bugs) with distinct triggers (tool-side issue, agent/browser failures) and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 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: 9ec2c8e

Reviewed: ~11 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.