playwright-cli
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.
88
86%
Does it follow best practices?
Impact
90%
22.50xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
92%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 a strong description that clearly communicates what the skill does and when to use it. It lists concrete actions and includes an explicit 'Use when...' clause with natural trigger terms. The only minor weakness is potential overlap with other extraction or form-filling skills, which could be mitigated by mentioning the specific browser automation tool or framework used.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'browser interactions', 'web testing', 'form filling', 'screenshots', and 'data extraction'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (automates browser interactions for web testing, form filling, screenshots, data extraction) and 'when' (explicit 'Use when...' clause listing six trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'navigate websites', 'interact with web pages', 'fill forms', 'take screenshots', 'test web applications', 'extract information from web pages'. These cover a good range of natural user phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | While browser automation is a fairly distinct niche, terms like 'data extraction' and 'form filling' could overlap with non-browser skills (e.g., PDF form filling, API-based scraping). It doesn't mention specific tools (e.g., Playwright, Puppeteer) that would further narrow its scope. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable command reference for playwright-cli that respects Claude's intelligence and provides copy-paste ready examples. Its main weaknesses are the lack of validation/verification steps in workflows (e.g., checking that a form submission succeeded before proceeding) and the fact that the full command reference is inline rather than split into a separate file for progressive disclosure.
Suggestions
Add validation checkpoints to workflow examples, e.g., 'after clicking submit, run `playwright-cli snapshot` and verify the expected page loaded before continuing'
Consider moving the full command reference to a separate COMMANDS.md and keeping only the most common commands inline, with a link to the full reference
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It's essentially a command reference with examples—no unnecessary explanations of what a browser is, what Playwright does, or how web automation works. Every line serves as a reference or example. | 3 / 3 |
Actionability | All commands are concrete, copy-paste ready bash commands. The examples show complete workflows (form submission, multi-tab, debugging) with specific commands rather than pseudocode or abstract descriptions. | 3 / 3 |
Workflow Clarity | The core workflow is stated (navigate → interact → re-snapshot) and examples show sequences, but there are no validation checkpoints or error recovery steps. For browser automation involving form submissions and destructive actions, there's no guidance on verifying success (e.g., checking snapshot after click, handling failed navigations). | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and logical grouping of commands (Core, Navigation, Keyboard, Mouse, etc.). However, the comprehensive command reference could be split into a separate REFERENCE.md, keeping SKILL.md as a concise overview with the most common commands and linking to the full reference. | 2 / 3 |
Total | 10 / 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
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- 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.