CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 content is a highly actionable, well-structured command reference with clear workflows and a ref-invalidation feedback loop. The main gaps are mild redundancy in the wait/timeout examples and the absence of external reference files for a body that is longer than the simple-skill threshold.

Suggestions

Consolidate the 'Timeouts and Slow Pages' section into the Essential Commands 'Wait' block to remove the duplicated wait examples and tighten the body.

Split the full command catalog (e.g. Semantic Locators, JavaScript Evaluation, Session Management) into a references/ file referenced from the overview, adding one-level-deep navigation now that the body exceeds the simple-skill line count.

Add an explicit error-recovery note to the Ref Lifecycle section (e.g. 'if a ref is stale or not found, re-snapshot and retry') to elevate workflow clarity.

DimensionReasoningScore

Conciseness

The body is a lean command catalog that assumes Claude's competence and avoids explaining basic concepts, but 'wait --load networkidle' is repeated across sections and the 'Timeouts and Slow Pages' section duplicates Essential Commands wait entries that could be trimmed.

4 / 5

Actionability

Almost entirely executable, copy-paste-ready agent-browser commands with inline comments, plus worked patterns (form submission, auth, data extraction) that cover the common cases.

5 / 5

Workflow Clarity

A clear 4-step core workflow (Navigate, Snapshot, Interact, Re-snapshot) is reinforced by the Ref Lifecycle feedback loop and wait-for-load/url checkpoints; it lacks explicit error-recovery guidance, so it sits just below the top anchor.

4 / 5

Progressive Disclosure

No bundle files exist and the body is well-organized into clearly headed sections, but at ~195 lines with no one-level-deep references to signal, it does not meet the top anchor's clear-overview-with-references bar.

4 / 5

Total

17

/

20

Passed

Description

88%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 concrete, complete, and well-triggered, clearly stating both capabilities and when to invoke the skill. It is slightly below top marks on trigger-term breadth and distinctiveness due to a niche dev-server trigger and minor overlap with generic web tasks.

DimensionReasoningScore

Specificity

Lists many concrete actions ('interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data') with comprehensive coverage, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

Explicitly answers 'what' ('Browser automation CLI for AI agents') and 'when' via a concrete 'Use when the user needs to...' clause plus an extra trigger ('Also triggers when a dev server starts'), matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural keywords users would say ('test web apps', 'take screenshots', 'fill forms', 'websites'), but 'dev server output' is slightly niche and a few synonyms (e.g. scrape, crawl) are missing, falling just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The browser-automation-CLI niche is distinct with specific triggers, but phrases like 'navigate pages, fill forms, extract data' carry minor overlap risk with generic web-interaction or scraping skills.

4 / 5

Total

18

/

20

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

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
openai/plugins
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.