CtrlK
BlogDocsLog inGet started
Tessl Logo

browser

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 efficient and highly actionable with concrete, executable commands and verification practices, though the workflow could be consolidated into an explicit ordered sequence. Its main defect is that both referenced detail files (EXAMPLES.md, REFERENCE.md) are missing from the bundle.

Suggestions

Create the referenced EXAMPLES.md and REFERENCE.md files (or remove the dangling links), so the clearly signaled references resolve to real content.

Consolidate Best Practices into a single numbered workflow (navigate → act → verify via screenshot → close) with an explicit validate-and-retry loop referencing the Troubleshooting guidance.

Trim the 'No user prompting' bullet and reconsider the Mode Comparison table, since environment selection is automatic and the table adds informational rather than instructional value.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with only minor trimmable redundancy — the 'No user prompting' bullet restates the automatic selection, and the Mode Comparison table is informational given selection is automatic.

4 / 5

Actionability

The command block and Quick Example are copy-paste ready and cover the common cases, and setup provides executable 'npm install' / 'npm link' steps; only the ['{}'] schema placeholder notation is slightly opaque.

5 / 5

Workflow Clarity

A usable sequence exists ('Always navigate first', 'View screenshots after each command to verify', 'Close browser when done') with recovery guidance in Troubleshooting, but the workflow is distributed across sections rather than presented as one explicit ordered loop with validate-and-retry checkpoints.

4 / 5

Progressive Disclosure

The overview is well-organized with clearly signaled one-level-deep references to EXAMPLES.md and REFERENCE.md, but neither file exists in the bundle, so the navigation points to dead ends and the structure is undermined.

3 / 5

Total

16

/

20

Passed

Description

92%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: third person, concise, with a concrete 'what' and an explicit, trigger-rich 'Use when' clause covering natural user phrasing. The only improvement would be adding common synonyms such as 'web scraping'.

DimensionReasoningScore

Specificity

Names the mechanism ('via CLI commands') and six concrete actions — 'navigate web pages', 'extract data', 'take screenshots', 'fill forms', 'click buttons' — giving comprehensive coverage of the browser-automation action space rather than minor gaps.

5 / 5

Completeness

Explicitly answers both 'what' ('Automate web browser interactions using natural language via CLI commands') and 'when' ('Use when the user asks to browse websites, navigate web pages, ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like 'browse websites', 'take screenshots', 'fill forms', and 'click buttons' are present, but common synonyms such as 'web scraping' or 'scrape data' are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

Browser automation is a clear niche and its triggers ('navigate web pages', 'click buttons', 'take screenshots') are unlikely to fire for other skills; only negligible overlap via 'extract data from websites'.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
UnicomAI/wanwu
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.