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.

93

4.88x
Quality

96%

Does it follow best practices?

Impact

88%

4.88x

Average score across 3 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

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 well-structured, actionable, and token-efficient CLI reference with a clear workflow and explicit checkpoint guidance. Its only weakness is that the deep-dive references and templates it points to are not present in the bundle.

Suggestions

Provide the referenced bundle files (references/commands.md, references/snapshot-refs.md, references/session-management.md, references/authentication.md, references/video-recording.md, references/proxy-support.md) and the templates/*.sh scripts, or remove the broken links.

Consider moving the inline Essential Commands catalog into references/commands.md so SKILL.md stays a lean overview pointing one level deep.

DimensionReasoningScore

Conciseness

Command-dense and lean with no over-explanation of browser or CLI concepts; every line earns its place. It leans toward reference-heaviness but avoids the verbosity that defines level 2.

3 / 3

Actionability

Fully executable copy-paste-ready commands shown end-to-end with real @e1 refs in a concrete fill/click flow; not level 2 because guidance is complete rather than pseudocode.

3 / 3

Workflow Clarity

The Core Workflow is a clearly sequenced 4-step pattern with an explicit re-snapshot checkpoint ("MUST re-snapshot") and a Ref Lifecycle section describing when refs invalidate, giving a feedback loop.

3 / 3

Progressive Disclosure

Two well-organized tables signal one-level-deep references/templates, but none of the referenced files (references/*.md, templates/*.sh) actually exist in the bundle, so the references are dangling; not level 1 because structure and signaling are present.

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, specific description with explicit capabilities and natural trigger phrases covering both what and when. It is concise, distinctive, and uses third person.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps") matching the top anchor; not level 2 because it is comprehensive rather than partial.

3 / 3

Completeness

Explicitly answers what (browser automation CLI capabilities) and when ("Use when the user needs to interact with websites... Triggers include..."); not level 2 because the when is explicit, not implied.

3 / 3

Trigger Term Quality

Natural user phrasings like "open a website", "fill out a form", "take a screenshot", "scrape data from a page", "login to a site" cover what users would actually say.

3 / 3

Distinctiveness Conflict Risk

A clear browser-automation niche with distinct triggers unlikely to overlap with file or code skills.

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

relative_links

Relative link issues: 9 missing

Warning

referenced_paths_exist

Referenced path issues: 12 missing

Warning

Total

14

/

16

Passed

Repository
shanraisshan/claude-code-best-practice
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.