CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-automation

Use for complex Agent Zero browser automation, including multi-tab browsing, screenshots, forms, uploads, raw pointer/keyboard actions, host-vs-container browser mode, and visual verification workflows.

79

Quality

100%

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

100%

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

The body is a well-structured, token-efficient tool reference: concrete actions, one executable JSON example, clear sequenced workflows with explicit pre-action checkpoints, and clean sectioning with a single signaled sub-skill reference. It avoids concept re-explanation and stays appropriately concise.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what a browser or DOM is, and every section delivers actionable specifics; the only mild redundancy (the fragile-forms load hint repeated in the intro and Forms section) is reinforcement rather than padding, so it stays at the level-3 'every token earns its place' anchor.

3 / 3

Actionability

It names concrete tool actions and args ('open', 'content', 'click', 'type', 'select_option', 'set_checked', 'upload_file', 'quality', 'full_page', 'path') and includes a complete, copy-pasteable JSON example for the 'multi' action; per the code-vs-instruction scoring note, the tool-reference guidance is actionable even with a single full code block.

3 / 3

Workflow Clarity

The Core Workflow is a clear 6-step numbered sequence with explicit checkpoints ('call list first, match by title or currentUrl, then use set_active or navigate'; 'verify the file exists in the active browser environment'), and Screenshots is a 3-step sequence; the core workflow is non-destructive so the batch/destructive feedback-loop cap does not apply, fitting the level-3 anchor.

3 / 3

Progressive Disclosure

No bundle files exist, and the body is organized into well-signaled one-level-deep sections (Core Workflow, Modes, Screenshots, Forms, Pointer/Keyboard, Tabs, Multi) with a single clearly signaled external reference ('browser-form-workflows' via skills_tool:load), matching the 'clear overview with well-signaled one-level-deep references' anchor.

3 / 3

Total

12

/

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 concise yet comprehensive: it states a clear trigger ('Use for'), lists multiple concrete capabilities, and stays scoped to browser automation. It is distinguishable from neighboring research/search skills and unlikely to misfire.

DimensionReasoningScore

Specificity

The description enumerates seven concrete capability areas — 'multi-tab browsing, screenshots, forms, uploads, raw pointer/keyboard actions, host-vs-container browser mode, and visual verification workflows' — matching the 'lists multiple specific concrete actions' anchor rather than the domain-only level 2.

3 / 3

Completeness

An explicit 'Use for...' trigger clause answers 'when', and the enumerated actions answer 'what', satisfying the level-3 'both what AND when with explicit triggers' anchor; it is not capped at 2 because the trigger guidance is present.

3 / 3

Trigger Term Quality

It surfaces natural terms a user would say ('browser automation', 'multi-tab browsing', 'screenshots', 'forms', 'uploads', 'visual verification'); the more technical phrases ('raw pointer/keyboard', 'host-vs-container') augment rather than replace these, so coverage stays at the level-3 anchor.

3 / 3

Distinctiveness Conflict Risk

Scoping to 'Agent Zero browser automation' with browser-specific triggers carves a clear niche unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.

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
agent0ai/agent-zero
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.