install-playwright-mcp
Install Playwright MCP server for browser automation in Claude Code
63
52%
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 ./plugins/claude-code-dev/skills/install-playwright-mcp/SKILL.mdQuality
Discovery
40%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 identifies a clear, specific technology stack (Playwright MCP server for Claude Code) which makes it distinctive, but it's too narrow in scope (only mentions installation) and critically lacks any 'Use when...' guidance. The description reads more like a task title than a skill description that helps Claude choose when to apply it.
Suggestions
Add a 'Use when...' clause with trigger terms like 'install Playwright', 'setup browser automation', 'configure MCP', 'add browser testing capability'
Expand the capabilities beyond just installation - include what the skill enables (e.g., 'Enables automated browser control, web scraping, and UI testing')
Add common user phrases like 'web automation', 'browser testing', 'headless browser', 'web scraping setup'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Playwright MCP server, browser automation, Claude Code) and one action (Install), but doesn't list multiple concrete actions or capabilities beyond installation. | 2 / 3 |
Completeness | Describes what (install Playwright MCP server) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Playwright', 'MCP server', 'browser automation', and 'Claude Code', but missing common variations users might say like 'web testing', 'browser control', 'automated browsing', or 'setup'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining Playwright, MCP server, and Claude Code - unlikely to conflict with other skills due to the precise technology stack mentioned. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable installation commands with good coverage of configuration options. However, it includes unnecessary explanatory content (what Playwright does, tool listings) that Claude already knows or can discover, and the execution instructions section is redundant and vague about error handling.
Suggestions
Remove the 'What This Does' section and 'Available Tools After Installation' list - Claude can discover these capabilities from the MCP server itself
Add specific success/failure indicators in verification (e.g., 'Output should show: MCP server playwright added successfully')
Consolidate or remove the 'Execution Instructions' section as it largely repeats the installation commands already provided
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary sections like 'What This Does' explaining what Playwright MCP does (Claude knows this), and the 'Available Tools After Installation' list which is reference material Claude can discover. The execution instructions at the end also repeat information already covered. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready bash commands for all scenarios including scope options, headless mode, browser selection, viewport configuration, and isolated sessions. Clear verification steps are included. | 3 / 3 |
Workflow Clarity | The verification section provides a clear 3-step sequence, but the 'Execution Instructions' section at the end is vague ('Verify success by checking output') without specifying what success looks like or how to handle failures. No error recovery guidance is provided. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. The 'Available Tools' list and detailed configuration options could be referenced to separate files. For a skill of this length (~80 lines), some content could be better organized. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- jpoutrin/product-forge
- Commit
0ebe7ae
- 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.