CtrlK
BlogDocsLog inGet started
Tessl Logo

browser

Web browser automation with AI-optimized snapshots for claude-flow agents

54

2.52x
Quality

43%

Does it follow best practices?

Impact

57%

2.52x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/browser/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

64%

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

This is a solid, actionable browser automation reference with excellent command coverage and concrete examples. Its main weaknesses are the lack of error handling/validation guidance (critical for browser automation where elements may not load or pages may change unexpectedly) and the monolithic structure that could benefit from splitting reference tables and integration details into separate files. Some sections like Hooks and Memory Integration add bulk without clear actionable value.

Suggestions

Add error handling guidance: what to do when elements aren't found, waits time out, or clicks don't trigger expected navigation — include a validate/retry pattern

Split the command reference tables and integration sections (MCP Tools, Memory, Hooks) into separate referenced files to improve progressive disclosure

Remove or significantly trim the Hooks and Memory Integration sections unless they directly support browser automation workflows — they feel tangential

DimensionReasoningScore

Conciseness

The skill is mostly efficient with good use of tables and code blocks, but includes some unnecessary sections (Hooks, Memory Integration) that feel like padding, and the tips section restates what's already obvious from the workflow. The intro line about '93% context reduction' is a nice touch but the overall document could be tighter.

2 / 3

Actionability

Commands are concrete, copy-paste ready, and cover the full range of operations. The examples section provides complete executable workflows for common scenarios (login, form submission, data extraction, multi-session). Selectors are shown with real syntax.

3 / 3

Workflow Clarity

The core workflow shows a clear 4-step sequence (navigate → snapshot → interact → re-snapshot), and examples follow this pattern. However, there are no validation checkpoints or error recovery steps — no guidance on what to do when a click fails, an element isn't found, or a wait times out, which is important for browser automation where pages are unpredictable.

2 / 3

Progressive Disclosure

The content is well-structured with clear sections and tables, but everything is in a single monolithic file. The command reference tables, examples, and integration sections could be split into separate files. No bundle files are provided, and no references to external files exist, so all content is inline.

2 / 3

Total

9

/

12

Passed

Description

22%

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 too terse and vague, relying on jargon ('AI-optimized snapshots', 'claude-flow agents') without explaining concrete capabilities or when the skill should be selected. It lacks a 'Use when...' clause and fails to list specific actions like navigating pages, clicking elements, filling forms, or extracting data from websites.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'automate browser', 'scrape website', 'navigate web page', 'fill web form', 'click button on page', 'open URL'.

Replace vague phrases like 'AI-optimized snapshots' with concrete actions such as 'navigate to URLs, click elements, fill forms, extract page content, take screenshots'.

Clarify what 'claude-flow agents' means or remove it in favor of user-facing language that describes the actual use cases.

DimensionReasoningScore

Specificity

The description says 'web browser automation' which is a broad domain reference, and 'AI-optimized snapshots' is vague jargon. No concrete actions like 'click buttons', 'fill forms', 'scrape data', or 'navigate pages' are listed.

1 / 3

Completeness

The 'what' is vaguely stated as 'web browser automation with AI-optimized snapshots' but lacks specifics. There is no 'when' clause or explicit trigger guidance at all, which per the rubric should cap completeness at 2, and the weak 'what' brings it to 1.

1 / 3

Trigger Term Quality

'Web browser automation' and 'snapshots' are somewhat relevant keywords, but common user terms like 'scrape', 'navigate', 'click', 'web page', 'URL', 'selenium', 'puppeteer', or 'browse' are missing. 'Claude-flow agents' is internal jargon unlikely to appear in user requests.

2 / 3

Distinctiveness Conflict Risk

'Web browser automation' narrows the domain somewhat compared to generic 'helps with code', but it could overlap with web scraping skills, testing automation skills, or other browser-related tools. The mention of 'claude-flow agents' adds some specificity but is jargon rather than a clear niche differentiator.

2 / 3

Total

6

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
ruvnet/ruvector
Reviewed

Table of Contents

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.