dev-browser

Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/dev-browser/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable commands and a clearly sequenced, validated Chrome-setup workflow, and it never over-explains basics. Its main weaknesses are repeated guidance across the "Plate Defaults" and "Rules" sections and a monolithic single-file layout that could split the verbose profile-clone procedure into a reference.

Suggestions

De-duplicate the overlapping guidance between "Plate Defaults" and "Rules" (profile cloning, macOS `open -na`, 9222 reuse) into a single authoritative section to tighten token use.

Move the long Google Chrome profile-clone script block into a referenced script or reference file and keep SKILL.md as a concise overview with a one-level-deep pointer, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no concept over-explanation, but it restates the same guidance multiple times (profile cloning, macOS `open -na`, 9222 reuse appear in both "Plate Defaults" and "Rules"), so it is mostly efficient but could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready bash and python snippets with specific flags and exact paths (e.g. the rsync clone and `open -na "Google Chrome" --args ...` launch), matching the score-3 anchor.	3 / 3
Workflow Clarity	The "Google Chrome Path" gives a numbered 1–5 sequence with explicit validation checkpoints (`curl /json/version` health check, `lsof` for a wrong 9222 owner) and an error-recovery fallback (connecting via the exact websocket URL), satisfying the feedback-loop requirement.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the content is well-sectioned, but the single ~134-line file is above the under-50-line simple-skill threshold and keeps everything inline with no offloaded detail, so it is organized yet somewhat monolithic.	2 / 3
	Total	10 / 12 Passed

Description

75%

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, third-person, and clearly answers both what the skill does and when to use it, with an explicit fallback trigger that distinguishes it from the primary Browser Use skill. It is slightly light on concrete action variety and natural keyword coverage, which keeps specificity and trigger-term quality at the middle level.

Suggestions

Add one or two more concrete actions to the description (e.g. "drives a persistent debug Chrome over CDP, reuses a signed-in profile") to raise specificity.

Include more natural user phrasings such as "automate the browser", "debug Chrome", or "CDP" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete capability ("browser automation with persistent Chrome state") but lists only one broad action rather than multiple specific ones, matching the score-2 anchor of naming a domain and some actions without being comprehensive.	2 / 3
Completeness	It states what it does ("Fallback browser automation with persistent Chrome state") and gives an explicit trigger ("Use only when Browser Use is unavailable or blocked"), clearly answering both what and when.	3 / 3
Trigger Term Quality	Includes some natural terms ("browser automation", "Chrome state", "Browser Use", "unavailable or blocked") but lacks common variations a user might say (e.g. "browser", "automate the browser", "debug Chrome"), so coverage is partial rather than strong.	2 / 3
Distinctiveness Conflict Risk	The fallback niche is sharply defined by the explicit condition (only when Browser Use is unavailable/blocked), making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

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

Reviewed: about 13 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.