CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

74

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable, well-structured reference with executable examples, clear workflows, and verification steps. Its main weakness is length — several sections could be moved into reference files to tighten the overview.

Suggestions

Move the Security section and Engine Selection / Native Mode sections into dedicated reference files to shorten the SKILL.md overview and improve progressive disclosure.

Trim explanatory framing sentences like the 'Why this matters' block under eval — Claude can infer shell-quoting risk from the rules-of-thumb list.

Consider moving the experimental Native Mode section to a reference file and keeping only a one-line pointer, since it is explicitly not recommended for production use.

DimensionReasoningScore

Conciseness

The body is almost entirely executable commands and concrete patterns with minimal conceptual padding, but a few framing sentences (e.g. the 'Why this matters' block, inline Security section) add length that could be trimmed without losing clarity.

4 / 5

Actionability

Fully executable, copy-paste-ready command examples throughout, covering common cases (form submission, auth vault, state persistence, eval heredoc) with specific flags and expected output.

5 / 5

Workflow Clarity

Core workflow is explicitly sequenced (Navigate → Snapshot → Interact → Re-snapshot) with verification checkpoints (re-snapshot, diff snapshot) and explicit cleanup guidance for batch/parallel session operations.

5 / 5

Progressive Disclosure

Clear 'Deep-Dive Documentation' table signals one-level-deep references to real files, but several sizable sections (Security, eval, engine selection, templates) are inlined rather than split into references.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description that is specific, comprehensive, and explicit about both capabilities and triggers. It names concrete actions and quotes natural user phrasings, leaving little ambiguity about when to invoke the skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' ('Browser automation CLI for AI agents... interact with websites, including...') and 'when' ('Use when the user needs...', 'Triggers include...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Quotes exact natural user phrases users would say ('open a website', 'fill out a form', 'click a button', 'take a screenshot', 'scrape data from a page', 'test this web app', 'login to a site'), with comprehensive coverage of common phrasings.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche — a browser automation CLI for AI agents — with distinct, specific triggers and minimal realistic overlap with other skills.

5 / 5

Total

20

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (542 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 3 missing

Warning

Total

13

/

16

Passed

Repository
ZHangZHengEric/Sage
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.