CtrlK
BlogDocsLog inGet started
Tessl Logo

browser

This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP server required.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with externalized scripts, but two defects hold it back: every command example uses the wrong file extension (`.js` instead of the actual `.cjs`), making them non-executable, and the workflow lacks validation checkpoints or error-recovery loops.

Suggestions

Correct the script file extensions throughout the body and Workflow section: change `scripts/start.js`, `nav.js`, `eval.js`, `screenshot.js`, and `pick.js` to their actual `.cjs` names so all commands are copy-paste executable.

Add explicit validation checkpoints to the workflow — after `start.js` confirm Chrome is listening on localhost:9222, after `nav.js` verify the page loaded before running `eval.js`, and after `pick.js`/`eval.js` check that a valid result was returned before continuing.

Document failure recovery (Chrome not running, port 9222 in use, element not found) with a fix-and-retry loop so Claude can recover from errors without guessing.

DimensionReasoningScore

Conciseness

Lean and task-focused with no padded explanations of concepts Claude already knows; lines like "Minimal Chrome DevTools Protocol (CDP) helpers" and "Use single expressions or IIFE for multiple statements" add only non-obvious, useful detail, so every token earns its place.

3 / 3

Actionability

Commands are concrete and specific ("scripts/start.js --profile", "scripts/eval.js 'document.title'") but reference `.js` files while the actual bundle files are `.cjs`, so they are not copy-paste executable as written — a missing key detail that caps it below the anchor-3 "fully executable" bar; not a 1 because the guidance is concrete, not vague or pseudocode.

2 / 3

Workflow Clarity

A clear 5-step sequence is present ("1. Launch Chrome... 5. Return gathered data") but there are no validation checkpoints (e.g., confirm Chrome is reachable on localhost:9222, verify the page loaded before eval, confirm pick.js found an element), matching the anchor-2 "sequence present but checkpoints missing."

2 / 3

Progressive Disclosure

Well-organized into Setup, Scripts, Workflow, and Key Points sections with implementation externalized as one-level-deep bundle files, each script given its own signaled heading with brief usage — easy navigation and content appropriately split, not a monolithic wall of text.

3 / 3

Total

10

/

12

Passed

Description

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.

A strong description that answers both what and when with an explicit trigger clause, names multiple concrete actions, and includes a distinguishing note that sets it apart from MCP-based browser tools. Minor jargon (CDP, DOM elements) does not materially weaken it.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements" — matching the anchor for comprehensive concrete actions; not below because it is not merely naming a domain.

3 / 3

Completeness

Clearly answers both what ("browser automation tasks using Chrome DevTools Protocol (CDP)") and when ("Triggers when users need to...") with explicit triggers, matching the anchor-3 example that pairs a capability list with a "Use when"/"Triggers when" clause.

3 / 3

Trigger Term Quality

Uses an explicit "Triggers when users need to launch Chrome... navigate pages... capture screenshots" clause with natural user-facing verbs; coverage goes well beyond the sparse anchor-2 example ("Works with PDF files"). The technical terms "CDP"/"DOM elements" keep it from being flawless but natural terms dominate.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Chrome/CDP browser automation) and explicitly distinguishes itself with "No MCP server required", making it unlikely to trigger for non-browser or MCP-based browser skills; not below because the triggers are specific rather than generic.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 13 missing

Warning

Total

15

/

16

Passed

Repository
stellarlinkco/myclaude
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.