CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 highly actionable, well-organized command reference with clear workflows and validation checkpoints, and it correctly defers detail to real reference files. Its weaknesses are redundancy across the Quick start/Core workflow/Commands sections and three broken template links.

Suggestions

Deduplicate the open/snapshot/click/fill/close commands that appear in both Quick start and Core workflow — keep them in the Commands reference and let the intro point there, to tighten token use (conciseness).

The templates/ directory does not exist, so the three 'Ready-to-use templates' links are broken — either ship the template scripts or remove that section so no referenced path dangles (progressive_disclosure).

Collapse the recording prose paragraph into a one-line note alongside the record commands to reduce explanatory padding (conciseness).

DimensionReasoningScore

Conciseness

The body is a terse command catalog with no concept explanations Claude already knows, but the Quick start, Core workflow, and Commands sections repeat the same open/snapshot/click/fill/close commands, and the recording section adds prose — efficient overall yet could be tightened, so the mostly-efficient anchor fits better than the every-token-earns-its-place score 3.

2 / 3

Actionability

Every entry is a concrete, executable command with real syntax and inline comments, plus complete worked examples (form submission, auth-with-state) that are copy-paste ready, matching the fully-executable anchor rather than the pseudocode score 2.

3 / 3

Workflow Clarity

The Core workflow gives a clear 4-step sequence and examples include explicit validation checkpoints (`wait --load networkidle`, `wait --url "**/dashboard"`, re-snapshot `# Check result`) plus the "Re-snapshot after navigation or significant DOM changes" rule, satisfying the explicit-validation anchor; not score 2 because checkpoints are present, not merely implicit.

3 / 3

Progressive Disclosure

The Deep-dive documentation table signals five one-level-deep references (all real files in references/) with descriptions — strong structure — but the three "Ready-to-use templates" links point to a templates/ directory that does not exist, so navigation is not fully reliable and the some-structure anchor fits better than the clean score 3.

2 / 3

Total

10

/

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.

The description is concise, uses correct third-person voice, names concrete actions, and pairs a clear capability statement with an explicit Use-when trigger clause. It hits the top anchor on every dimension with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "web testing, form filling, screenshots, and data extraction" plus "navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information" — matching the multi-action anchor rather than the single-domain score 2.

3 / 3

Completeness

Explicitly answers both what ("Automates browser interactions for...") and when ("Use when the user needs to navigate websites...") with an explicit Use-when trigger clause, matching the top anchor; not score 2 because the when is stated, not merely implied.

3 / 3

Trigger Term Quality

Covers natural phrases users actually say ("fill forms", "take screenshots", "test web applications", "navigate websites", "extract information") with good variation, satisfying the broad-coverage anchor rather than the partial score 2.

3 / 3

Distinctiveness Conflict Risk

Browser automation is a clear niche with triggers (websites, web pages, forms, screenshots) unlikely to collide with other skills, matching the distinct-niche anchor; not score 2 because the scope is unambiguous rather than overlapping.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
quran/quran.com-frontend-next
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.