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.

68

Quality

83%

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

82%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.

A tight, well-structured workflow guide that offloads fragile-form detail to a referenced skill and gives concrete tool actions. Adding explicit validation/retry loops for batch and destructive operations would lift workflow clarity.

Suggestions

Add an explicit validate-then-retry checkpoint for the multi action (e.g., re-check content after a mutating batch) since it is a batch operation that currently lacks a feedback loop.

Specify how to verify a screenshot actually captured the expected state before reasoning from it, turning the Screenshots And Vision sequence into a checked loop.

Add a short post-action verification step (re-run content on the target tab) for fragile form submissions to close the validation gap the form-workflow handoff relies on.

DimensionReasoningScore

Conciseness

Lean, reference-dense prose with no padding; it assumes Claude's competence and explains only the non-obvious tool-specific behaviors.

5 / 5

Actionability

Concrete action names, typed refs, and an executable multi-action JSON example cover the common cases, though some sections stay descriptive about when to use actions rather than how to call them.

4 / 5

Workflow Clarity

The Core Workflow is a clear numbered sequence with implicit verification (match by title/currentUrl before reusing a tab); destructive/batch guidance like the multi-action mutation caveat is present but explicit validate-then-retry loops are not.

4 / 5

Progressive Disclosure

Well-organized sections with one clearly signaled one-level-deep reference to the browser-form-workflows skill; the form detail is appropriately offloaded, though no bundle files exist to deepen it.

4 / 5

Total

17

/

20

Passed

Description

83%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, specific description that clearly states capabilities and trigger conditions with a generous trigger list. Minor overlap risk and a few missing synonyms keep it just below perfect.

DimensionReasoningScore

Specificity

Lists several concrete actions (multi-tab browsing, screenshots, forms, uploads, raw pointer/keyboard actions, visual verification) with only minor coverage gaps around navigation/search.

4 / 5

Completeness

Explicitly answers both what (complex Agent Zero browser automation with the listed capabilities) and when (the 'Use for' clause plus a rich triggers list).

5 / 5

Trigger Term Quality

Strong natural terms like 'browser automation', 'open website', 'browser screenshot', and 'host browser' map to user phrasing, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

Scoped to Agent Zero browser automation with host-vs-container mode distinction, but some triggers like 'open URL' could overlap with general web skills.

4 / 5

Total

17

/

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

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.