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.

76

Quality

95%

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

90%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 concise, action-oriented, and well-structured with executable CLI examples and a useful mode-comparison table. The main gaps are the absence of an explicit validate->retry feedback loop in the main workflow and references to bundle files (EXAMPLES.md, REFERENCE.md, setup.json) that are not present.

Suggestions

Add an explicit numbered workflow with a validation checkpoint, e.g. '1. browser navigate <url> 2. browser screenshot to verify the page loaded 3. if wrong page, re-navigate 4. browser act/extract 5. browser close', to establish a clear feedback loop.

Provide the referenced bundle files (EXAMPLES.md, REFERENCE.md, setup.json) in the skill directory, or remove the references if the inline content is intended to be self-contained, so no links are dangling.

In Troubleshooting, pair each failure with a concrete recovery command (e.g. 'Action fails: run browser observe "<query>" then retry with the discovered element'), turning hints into a retry loop.

DimensionReasoningScore

Conciseness

The ~68-line body is lean and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; each section (Setup, Commands, Quick Example, mode table, Best Practices, Troubleshooting) earns its tokens.

5 / 5

Actionability

It provides concrete, copy-paste-ready CLI commands ('browser navigate <url>', 'browser act "<action>"', etc.) plus a complete Quick Example covering the common navigate/act/extract/close flow.

5 / 5

Workflow Clarity

A clear loose sequence exists via Best Practices ('Always navigate first', 'View screenshots...to verify', 'Close browser when done') with one verification checkpoint and Troubleshooting hints, but there is no explicit numbered workflow or structured validate->fix->retry feedback loop.

4 / 5

Progressive Disclosure

The SKILL.md is a well-organized overview with clearly-signaled one-level references to [EXAMPLES.md](EXAMPLES.md) and [REFERENCE.md](REFERENCE.md), but those referenced files and the referenced setup.json do not actually exist in the bundle, leaving the links dangling.

4 / 5

Total

18

/

20

Passed

Description

100%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, well-constructed description that concisely states the capability and provides explicit, comprehensive trigger guidance in natural user language. It clearly distinguishes the skill's niche with minimal conflict risk.

DimensionReasoningScore

Specificity

Names the domain ('Automate web browser interactions using natural language via CLI commands') and lists multiple concrete actions (navigate, extract, screenshot, fill forms, click buttons, browse) with comprehensive coverage, matching the anchor for listing multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers both 'what' (automate browser interactions via CLI commands) and 'when' (an explicit 'Use when the user asks to...' clause with concrete trigger phrases).

5 / 5

Trigger Term Quality

'browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications' provides comprehensive coverage of the natural phrases a user would actually say, including synonyms.

5 / 5

Distinctiveness Conflict Risk

The browser-automation niche is clearly defined with distinct triggers (browser/website actions via CLI) and minimal overlap risk with other skills.

5 / 5

Total

20

/

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.