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.

90

2.62x
Quality

87%

Does it follow best practices?

Impact

92%

2.62x

Average score across 6 eval scenarios

SecuritybySnyk

Critical

Do not install without reviewing

The canonical home for this skill is agent-browser in vercel-labs/agent-browser

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable and well-structured with a clear core workflow and good reference navigation. Its main weakness is length: several topics are fully inlined despite having dedicated reference files, slightly bloating the token budget.

Suggestions

Trim or summarize the inlined Authentication, Session Persistence, and Security sections into brief overviews that defer to references/authentication.md and references/session-management.md, since those reference files already exist.

Condense the Timeouts and eval-quoting sections to their essential rules-of-thumb; the detailed prose can move to references/commands.md.

Verify the referenced templates/ scripts exist or remove the Ready-to-Use Templates table, since the templates/ directory is not present in the bundle.

DimensionReasoningScore

Conciseness

The body is mostly lean command examples and agent-browser-specific gotchas, but at ~530 lines several sections (auth, security, timeouts, eval quoting) are explained at length and could be tightened or moved to references.

3 / 5

Actionability

Nearly every section is copy-paste-ready executable commands covering the common cases — navigation, snapshot, interaction, auth, extraction, diffing — with concrete flags and examples.

5 / 5

Workflow Clarity

The core workflow (Navigate → Snapshot → Interact → Re-snapshot) is clearly sequenced with explicit re-snapshot checkpoints and a diff-verification step, though a few destructive/batch paths could state validation more emphatically.

4 / 5

Progressive Disclosure

A Deep-Dive Documentation table links to 7 real reference files (all verified present), but topics that have dedicated reference files (auth, session-management) are also fully inlined in the body, leaving minor organization overlap.

4 / 5

Total

16

/

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.

The description is exemplary: it concisely states the skill's purpose, enumerates concrete capabilities, and supplies explicit, natural trigger phrases. Third-person voice is maintained and there is no vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task" — giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both what ("Browser automation CLI for AI agents" plus the action list) and when ("Use when the user needs..." and "Triggers include...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides comprehensive natural trigger phrases users would actually say — "open a website", "fill out a form", "scrape data from a page", "test this web app", "login to a site" — including synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (programmatic browser interaction) with distinct, unambiguous triggers, making conflict with unrelated skills minimal.

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 (540 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
Intelligent-Internet/ii-agent
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.