CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-browser

Browser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating pages, filling forms, clicking buttons, taking screenshots, extracting page data, reading selected Open Design browser-tab context, testing web apps, dogfooding Open Design previews, QA, bug hunts, or reviewing app quality. Prefer local Open Design preview URLs unless the user explicitly asks for external browsing.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is highly actionable with a clear validated workflow, but it leans verbose through repeated CDP startup blocks and lacks progressive disclosure since no bundle/reference files split the detail.

Suggestions

De-duplicate the CDP startup + connect sequence: define it once and reference it from the smoke path instead of repeating it verbatim.

Move the specialized upstream guides list into a references file so the SKILL.md body stays an overview rather than inline listing every guide path.

Tighten the repeated warnings about not using Open Design's daemon CLI into a single consolidated safety note.

DimensionReasoningScore

Conciseness

The body is accurate and mostly efficient but repeats the CDP startup sequence almost verbatim in two sections and includes some redundancy around not running Open Design's daemon CLI, which could be tightened.

2 / 3

Actionability

Provides fully executable copy-paste bash sequences for CLI verification, CDP attach, connect, open, snapshot, and screenshot, with concrete expected outputs and ports.

3 / 3

Workflow Clarity

A clear numbered Workflow sequence with validation checkpoints (command -v, curl CDP probe loop, expected smoke success criteria) and feedback for error recovery when CDP is unavailable.

3 / 3

Progressive Disclosure

No bundle files are present (references/scripts/assets absent), so there are no one-level-deep references to verify; the body is a single monolithic document that could be split rather than kept inline.

2 / 3

Total

10

/

12

Passed

Description

100%

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, action-oriented, and explicitly pairs what the skill does with when to use it. Trigger terms map naturally to user phrasing and the Open Design niche is distinctive.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'navigating pages, filling forms, clicking buttons, taking screenshots, extracting page data', matching the top anchor for specific concrete actions.

3 / 3

Completeness

Explicitly answers what it does (browser automation CLI actions) and when to use it ('Use when the user needs to inspect, test, or automate browser behavior'), with explicit trigger guidance.

3 / 3

Trigger Term Quality

Natural user phrases like 'take a screenshot', 'scrape page', 'QA', 'bug hunt', and 'extract logo/colors' give good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

Clear niche around browser automation for Open Design preview validation with distinct triggers (extract logo, OG metadata, a11y), unlikely to conflict with non-browser skills.

3 / 3

Total

12

/

12

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.