Name: browserhub
Rating: 51.2 (1 reviews)
Author: membranedev

browserhub

Browserhub integration. Manage data, records, and automate workflows. Use when the user wants to interact with Browserhub data.

Quality

56%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/browserhub/SKILL.md

Quality

Content

76%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.

The body is highly actionable with concrete, copy-paste Membrane commands and a useful action table, and is well-organized into logical sections. Its main gap is the absence of validation/verification steps for batch scraper-run operations, which the rubric caps at workflow clarity 3.

Suggestions

Add a verification loop for scraper runs: after 'Create Run', poll 'Get Run' until status is terminal before reporting results to the user.

Add a guard before batch/credit-consuming actions (e.g. check 'Get Account Status' for remaining credits before 'Create Run') so destructive or costly runs are not launched blindly.

Trim the introductory paragraph about what Browserhub is and who uses it; assume Claude's competence and lead with the workflow.

Dimension	Reasoning	Score
Conciseness	The body is largely commands and tables with minimal conceptual padding, though the opening paragraph ("Browserhub is a tool that allows users to run and manage browsers in the cloud...") and a few prose asides like "so you will know how to run it" could be trimmed. This matches 'efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean anchor.	4 / 5
Actionability	It provides copy-paste-ready, executable commands throughout — install, login, search, connect, action list/run, and proxy requests — plus a popular-actions table with concrete action keys and a flag reference table. This matches 'fully executable; copy-paste ready code or commands; specific examples cover the common cases.'	5 / 5
Workflow Clarity	There is a clear install → login → connect → discover → run sequence, but running scraper runs (Create Run, Get Run) and account credit consumption are batch operations with no validation/verification checkpoints or feedback loops (e.g. poll run status, confirm credits). Per the rubric cap, batch operations without validation cap workflow clarity at 3.	3 / 5
Progressive Disclosure	The content is organized into clear sections (Overview, Install, Setup, Connect, Actions, Best practices) with no bundle files present, so all guidance is appropriately inline. It matches 'good structure; most content appropriately placed; minor organization gaps' — well-organized but the popular-actions table and proxy flag list are dense blocks that sit slightly above a purely lean overview.	4 / 5
	Total	16 / 20 Passed

Description

37%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.

The description correctly names the product and includes a Use-when clause, but the capabilities are stated generically and the trigger terms miss the natural vocabulary (scrapers, runs, browser testing) users would actually say. It is functional but vague and would benefit from concrete actions.

Suggestions

Replace generic verbs with concrete Browserhub actions, e.g. 'Create and monitor scraper runs, list and inspect scrapers, and check account status and credits.'

Add natural trigger terms users would say: 'Use when the user wants to run scrapers, manage scraper runs, scrape web pages, or check Browserhub account status/credits.'

Tighten the 'when' clause to reference specific Browserhub concepts (scrapers, runs, credits) rather than 'interact with Browserhub data'.

Dimension	Reasoning	Score
Specificity	The description names the domain (Browserhub) but lists only generic actions — "Manage data, records, and automate workflows" — with no concrete capabilities like creating scraper runs or listing scrapers. It sits at the anchor that 'names the domain but actions are minimal or generic' rather than the anchor above, which requires several specific concrete actions.	2 / 5
Completeness	It states a 'what' ("Manage data, records, and automate workflows") and a 'when' ("Use when the user wants to interact with Browserhub data"), but the 'what' is vague and the 'when' is generic, so it does not reach the anchor requiring a clearer 'what' and more explicit 'when'.	3 / 5
Trigger Term Quality	The only natural keyword is the product name "Browserhub"; the phrase "interact with Browserhub data" is generic and omits the terms users would actually say — scrapers, scraper runs, browser automation, cross-browser testing, web scraping. This matches 'one or two generic keywords; missing the natural phrases users say.'	2 / 5
Distinctiveness Conflict Risk	The product name "Browserhub" gives it a recognizable niche, but the surrounding language ("manage data, records, automate workflows") is generic and could overlap with many data/automation skills, so it does not clearly reach the 'mostly distinct' anchor.	3 / 5
	Total	10 / 20 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: membranedev/application-skills
Path: skills/browserhub/SKILL.md
Commit: f484c82

Reviewed: 4 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.