CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-browser

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".

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.

The body is a well-organized, fully executable command reference with a clear core workflow and concrete examples. It is slightly redundant in places and lacks explicit verification checkpoints, but otherwise strong.

Suggestions

Add explicit verification steps after interactions (e.g. re-snapshot and assert the expected element appeared) to close the workflow validation gap.

Trim redundancy where commands are restated across the Core Workflow and Key Commands sections.

Consider moving the full command catalog or the "vs Playwright MCP" comparison into a reference file to tighten SKILL.md, now that the body is fairly long for a single file.

DimensionReasoningScore

Conciseness

Mostly lean command reference with terse inline comments and minimal over-explanation; some redundancy (commands restated across sections, "vs Playwright MCP" prose repeats the table) keeps it just short of fully efficient.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout with concrete worked examples (login flow, search/extract, form filling) covering the common cases.

5 / 5

Workflow Clarity

The core workflow is clearly sequenced (Navigate → Snapshot → Interact → Re-snapshot); minor validation gaps (no explicit verify-after checkpoints) keep it below 5, and operations are not destructive/batch so the cap does not apply.

4 / 5

Progressive Disclosure

No bundle files exist; the body is a single self-contained reference with well-organized section headers and good navigation, though it is somewhat long for one file.

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.

The description is concrete and well-structured, answering both what the skill does and when to use it with explicit trigger phrases. It is distinct from Playwright MCP and appropriately concise.

DimensionReasoningScore

Specificity

Lists several concrete actions ("fill forms, take screenshots, or scrape data") plus specifics like "Bash commands" and "ref-based element selection"; minor coverage gaps (e.g. click, extract text) keep it below 5.

4 / 5

Completeness

Clearly states both what ("Browser automation ... fill forms, take screenshots, or scrape data") and when ("Use when you need to...", "Triggers on...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Explicit natural triggers ("browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation") are phrases users would actually say, with good synonym coverage but a few variations missing.

4 / 5

Distinctiveness Conflict Risk

Distinguishes itself explicitly ("Alternative to Playwright MCP") and targets a specific Bash-based browser-automation niche; minor overlap risk with general web-browsing skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
marchatton/agent-skills
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.