dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
57
64%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/automation/dev-browser/skills/dev-browser/SKILL.mdQuality
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific concrete actions, comprehensive natural trigger terms that users would actually say, explicit 'Use when' guidance, and a clear distinctive niche around browser automation. The mention of 'persistent page state' adds a technical differentiator that helps distinguish it from simpler web-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: navigate websites, fill forms, take screenshots, extract web data, test web apps, automate browser workflows. Also mentions 'persistent page state' as a distinguishing capability. | 3 / 3 |
Completeness | Clearly answers both 'what' (browser automation with persistent page state) and 'when' (explicit 'Use when...' clause with detailed trigger phrases and use cases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would actually say: 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into'. These are highly natural and varied. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around browser automation with specific triggers like URLs, clicking, screenshots, and scraping. The mention of 'persistent page state' further distinguishes it from generic web or automation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a stub—it provides only installation instructions and a pointer to --help, with no actual guidance on browser automation. Given the rich description (navigating websites, filling forms, screenshots, scraping, testing), the body content fails to deliver any actionable, structured, or useful instruction. It is concise but vacuous.
Suggestions
Add concrete, executable code examples for core use cases: navigating to a URL, clicking elements, filling forms, and taking screenshots.
Define a clear workflow for typical browser automation tasks with explicit steps and validation (e.g., verify page loaded, confirm element exists before clicking).
Include at least 2-3 real examples showing input commands and expected outputs for common trigger phrases like 'go to [url]' or 'take a screenshot'.
If the tool has extensive documentation, create supporting reference files (e.g., EXAMPLES.md, API.md) and link to them from the skill body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely lean with no unnecessary explanation. Every line serves a purpose. However, it's arguably too lean—it's concise to the point of being unhelpful. | 3 / 3 |
Actionability | The skill provides only installation commands and a --help pointer. There are no concrete examples of browser automation, no code snippets for navigating pages, filling forms, taking screenshots, or any of the tasks described in the skill description. 'Run --help' is the opposite of actionable guidance. | 1 / 3 |
Workflow Clarity | There is no workflow described at all. For a browser automation skill that involves multi-step processes (navigate, interact, validate, screenshot), there are zero steps, no sequencing, and no validation checkpoints. | 1 / 3 |
Progressive Disclosure | There are no references to any supporting files, no bundle files exist, and the content is a stub with no structure beyond installation. There's nothing to navigate to and no organization of the rich topic space described in the skill description. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- numman-ali/n-skills
- Commit
a518c67
- 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.