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.
72
64%
Does it follow best practices?
Impact
Pending
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 uses third person voice, provides specific concrete actions, includes comprehensive natural trigger phrases users would actually say, and clearly distinguishes itself as a browser automation skill. The explicit 'Use when...' clause and 'Trigger phrases include...' section make it highly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'navigate websites, fill forms, take screenshots, extract web data, test web apps, automate browser workflows' - these are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Browser automation with persistent page state' plus specific actions) AND when (explicit 'Use when...' clause with detailed trigger phrases). The 'Trigger phrases include...' section provides additional explicit guidance. | 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 match real user language patterns. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on browser/web automation with distinct triggers like 'go to [url]', 'click on', 'scrape', 'log into'. The 'persistent page state' qualifier and web-specific terminology make it unlikely to conflict with other 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 extremely minimal to the point of being unhelpful. While concise, it fails to provide any actionable guidance for browser automation tasks described in its purpose. It essentially just points to --help without teaching Claude how to actually use the tool for navigation, form filling, screenshots, or any browser workflows.
Suggestions
Add concrete, executable examples showing common browser automation tasks (navigate to URL, click element, fill form, take screenshot)
Include at least one complete workflow example demonstrating a multi-step browser interaction with validation
Document the key commands/API methods with copy-paste ready code snippets rather than just pointing to --help
Add a quick reference section showing the most common use cases that match the skill's trigger phrases
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely lean with no unnecessary explanation. Every line serves a purpose - installation and usage pointer. | 3 / 3 |
Actionability | Provides only installation commands and a help pointer. No concrete examples of browser automation, no code showing how to navigate, click, fill forms, or take screenshots as described in the skill's purpose. | 1 / 3 |
Workflow Clarity | No workflow is described. For a browser automation skill that should handle navigation, form filling, screenshots, and web scraping, there are no steps, sequences, or validation checkpoints provided. | 1 / 3 |
Progressive Disclosure | The content just says 'run --help' without providing any overview of capabilities, examples, or references to detailed documentation. This is a dead end rather than progressive disclosure. | 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
8de01ac
- 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.