dev-browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

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

The canonical home for this skill is dev-browser in SawyerHood/dev-browser

Quality

Content

72%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 body is concise and well-organized with executable install/config commands, but it stops short of demonstrating the skill's central purpose — the actual browser-automation workflow is deferred to `--help`, leaving the primary task under-specified. Progressive disclosure is fine for a skill this small with no bundle files.

Suggestions

Add one minimal executable example showing the core automation task (e.g., a sample `dev-browser` script or command that navigates and extracts/screenshot), so the primary workflow is copy-paste-ready rather than deferred to `--help`.

Provide a short numbered usage workflow (launch/connect -> run script -> read result) so the main multi-step flow is sequenced explicitly in the body.

Clarify how sandboxed JavaScript scripts are authored and passed to the CLI, since the body mentions the mechanism but never shows it.

Dimension	Reasoning	Score
Conciseness	The body is lean — an install block, a "Run `dev-browser --help`" pointer, and one dense idle-timeout paragraph ("--idle-timeout 5m closes each launched browser after inactivity while preserving its profile and login state") — with no padding explaining concepts Claude already knows. It is not score 2 because nothing reads as unnecessary or tighten-able.	3 / 3
Actionability	Concrete commands exist ("npm install -g dev-browser", "dev-browser install", "--idle-timeout 5m", "--idle-timeout 0"), but the core browser-automation workflow is deferred to "Run `dev-browser --help` to learn more" with no example script or command for actually controlling a browser. This matches score 2 (some concrete guidance but missing key details), falling short of score 3's copy-paste-ready bar for the primary task.	2 / 3
Workflow Clarity	Install steps are clear, but the main task — controlling browsers with sandboxed JavaScript scripts — is not sequenced or demonstrated; usage is pushed to `--help`. This fits score 2 (sequence present but the primary workflow is implicit/deferred) rather than score 1 (install steps are present) or score 3 (the main workflow is not laid out).	2 / 3
Progressive Disclosure	The skill is under 50 lines with no bundle files in references/, scripts/, or assets/, and the body is organized into clear Installation and Usage sections. Per the simple-skills scoring note, well-organized sections alone earn score 3 here. It is not score 2 because there is no inline content that should be split off and no nested referencing.	3 / 3
	Total	10 / 12 Passed

Description

100%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 specific, complete, and distinctive: it names concrete browser-automation actions, provides an explicit Use-when clause plus natural trigger phrases, and occupies a clear niche unlikely to conflict with other skills. It is a strong, well-constructed description.

Dimension	Reasoning	Score
Specificity	"navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows" lists multiple specific concrete actions, matching the score-3 anchor. It exceeds score 2 because the action list is comprehensive rather than naming only some actions.	3 / 3
Completeness	It states what ("Browser automation with persistent page state") and when ("Use when users ask to navigate websites...") with explicit trigger phrases, matching the score-3 anchor that requires both what AND when. It is not score 2 because the "when" is explicit, not merely implied.	3 / 3
Trigger Term Quality	Trigger phrases "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into" give good coverage of natural terms a user would say. It is not score 2 because common variations are not missing — the list is broad.	3 / 3
Distinctiveness Conflict Risk	Browser automation with persistent page state is a clear niche, and triggers like "go to [url]", "take a screenshot", and "scrape" are unlikely to fire for unrelated skills. It is not score 2 because it is more distinct than a generic "Works with document files" example.	3 / 3
	Total	12 / 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: numman-ali/n-skills
Path: skills/automation/dev-browser/skills/dev-browser/SKILL.md
Commit: b1c6173

Reviewed: 8 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.