CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

browser-use

Operate and verify webpages in the OpenSquilla Desktop sidebar using the conversation-owned browser MCP tools. Use for interactive browsing, forms, page navigation, and visual checks.

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

78%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 lean, well-structured instruction-only skill body: every bullet adds non-obvious operational constraints for the sidebar browser, with strong validation and error-recovery guidance woven throughout. Its main gaps are the absence of a top-level ordered workflow and minor repetition between overlapping safety rules.

DimensionReasoningScore

Conciseness

The body is dense with operational constraints Claude would not otherwise know (e.g., 'argument_validation with outcome=not_started means that request did not execute') and contains no padding or explanations of known concepts. It falls short of 5 due to minor repetition around ref validity ('never invent them or carry them across pages' vs. 'Navigation, reload, tab changes, and page updates can invalidate element refs') and a few sentences that could be tightened.

4 / 5

Actionability

Concrete condition-to-action guidance is tied to specific tool concepts — 'browser_open', 'browser_navigate', 'targetRef', 'argument_validation', 'availableUploads' — such as 'Supply an HTTP(S) URL to open a website' and 'Upload only a user attachment identified by an availableUploads file ID'. As an instruction-only skill about tools whose schemas are discovered live, omitting literal call examples is justified; it is not a 5 because no example invocations or worked scenarios are given.

4 / 5

Workflow Clarity

The content is topic-organized rather than a numbered sequence, but embeds explicit validation checkpoints and error-recovery loops ('Check each action's execution state and the resulting observation before relying on it', 'inspect the page before repeating a state-changing action', 'If a scroll reports no change, inspect the affected region... before deciding whether another scroll is useful'). It misses a 5 because no overall ordered workflow (e.g., open → inspect → act → verify) is laid out.

4 / 5

Progressive Disclosure

A single well-organized file with clear sections ('Page state', 'Visual and text evidence', 'Files, dialogs, and tabs', 'Authority') and no bundle files; nothing here clearly belongs in separate files and there are no buried or nested references, so the structure is easy to navigate. This fits the simple-skill case where well-organized sections in one appropriately sized file merit top marks.

5 / 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.

A strong description: third-person, concise, with a clear 'what' and an explicit 'Use for' clause covering natural trigger phrases. Coverage of capabilities and natural trigger synonyms (e.g., screenshot, click, open a website) could be slightly broader to reach top marks.

DimensionReasoningScore

Specificity

Names the domain ('Operate and verify webpages in the OpenSquilla Desktop sidebar using the conversation-owned browser MCP tools') and lists several concrete actions — 'interactive browsing, forms, page navigation, and visual checks' — with minor gaps in coverage (e.g., tab management, downloads, dialogs are not mentioned). It is not a 5 because coverage is not comprehensive, and not a 3 because it goes beyond 1-2 actions.

4 / 5

Completeness

It clearly answers 'what' ('Operate and verify webpages in the OpenSquilla Desktop sidebar using the conversation-owned browser MCP tools') and explicitly answers 'when' with a 'Use for' clause listing concrete trigger phrases ('interactive browsing, forms, page navigation, and visual checks'). This matches the anchor for explicit what-and-when with concrete triggers.

5 / 5

Trigger Term Quality

'interactive browsing, forms, page navigation, and visual checks' are phrases users would naturally say, giving good keyword coverage. It falls short of 5 because common natural terms like 'screenshot', 'click', 'scroll', or 'open a website' are missing, but exceeds 3 since several relevant synonyms are present.

4 / 5

Distinctiveness Conflict Risk

The 'OpenSquilla Desktop sidebar' and 'conversation-owned browser MCP tools' scoping creates a clear niche with minimal conflict risk, but generic terms like 'forms' and 'page navigation' leave minor overlap risk with other browser or web-interaction skills. It is mostly distinct rather than fully distinct.

4 / 5

Total

17

/

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.

Validation — 13 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

TokenRhythm/opensquilla

Path

src/opensquilla/skills/bundled/browser-use/SKILL.md

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.