CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.

76

Quality

96%

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

92%

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

A highly actionable, lean command reference with a clear core workflow and an explicit ref-lifecycle feedback loop. Its main weakness is progressive disclosure: all detail lives inline in a single long file with no reference files to split out the command catalog.

Suggestions

Move the Essential Commands catalog into a references/COMMANDS.md (or similar) file, keeping SKILL.md as a concise overview that links to it, so the command reference is one level deep rather than inline.

Consolidate the repeated 'wait --load networkidle' and 'snapshot -i' pattern into the Core Workflow once, and have later pattern sections reference it instead of re-stating the full sequence each time.

De-duplicate the wait commands that appear in both Essential Commands and the Timeouts and Slow Pages section, pointing the latter back to the canonical reference to reduce inline repetition.

DimensionReasoningScore

Conciseness

The body is command-dense with minimal inline commentary and no explanations of concepts Claude already knows (e.g., no 'what a browser is' filler); comments are short and load-bearing, so most tokens earn their place.

3 / 3

Actionability

Every section provides fully executable, copy-paste-ready commands with real flags and refs (e.g., 'agent-browser fill @e2 "text"', 'agent-browser wait --load networkidle'), matching the anchor for concrete, specific, runnable guidance.

3 / 3

Workflow Clarity

The Core Workflow gives an explicit 4-step sequence and the Ref Lifecycle section is a clear feedback loop (re-snapshot after navigation/submission/DOM changes), providing the validation-style checkpoint the top anchor rewards; no destructive/batch gap applies.

3 / 3

Progressive Disclosure

The skill is well-sectioned but monolithic at ~195 lines with no bundle files: the Essential Commands block (~40 lines) and Timeout/Annotated sections repeat reference material inline that could be offloaded to a separate reference file, fitting the 'content that should be separate is inline' anchor rather than the one-level-deep reference ideal.

2 / 3

Total

11

/

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.

A strong, third-person description that clearly conveys both capability and triggering conditions with concrete, natural-language actions and a distinct browser-automation niche. It does not pad with fluff or over-claim.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data"), matching the anchor for listing several specific concrete actions rather than vague domain-only language.

3 / 3

Completeness

Explicitly states what ("Browser automation CLI for AI agents") and when with an explicit trigger clause ("Use when the user needs to interact with websites... Also triggers when a dev server starts"), satisfying the what-and-when anchor at the top level.

3 / 3

Trigger Term Quality

Uses natural terms a user would say ("fill forms", "click buttons", "take screenshots", "test web apps", "verify dev server output") plus the dev-server trigger, giving good coverage rather than jargon-only phrasing.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (browser automation via agent-browser) with distinct web/dev-server triggers that are unlikely to collide with other skills; not a generic 'helps with code and documents' style description.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
openai/plugins
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.