chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
70
57%
Does it follow best practices?
Impact
92%
5.75xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/chrome-devtools-cli/SKILL.mdQuality
Discovery
50%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 reasonably specific niche (Chrome DevTools automation via CLI/shell) but lacks concrete action examples and explicit trigger guidance. It uses second-person framing ('Use this skill to') which is borderline but not penalized as heavily as first-person. The description would benefit from listing specific capabilities and adding a clear 'Use when...' clause with natural trigger terms.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'Chrome DevTools', 'browser automation', 'headless Chrome', 'CDP', 'web scraping via CLI'.
List specific concrete actions such as 'capture screenshots', 'extract page content', 'monitor network requests', 'run JavaScript in browser context' to improve specificity.
Rephrase to third person voice (e.g., 'Writes shell scripts and runs shell commands to automate browser tasks via Chrome DevTools CLI') and clarify what distinguishes this from general shell scripting skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (shell scripts, shell commands, Chrome DevTools, browser automation) and some actions ('write shell scripts', 'run shell commands', 'automate tasks'), but doesn't list specific concrete actions like 'capture screenshots', 'inspect network requests', 'extract DOM elements', etc. | 2 / 3 |
Completeness | The description addresses 'what' (write shell scripts, run shell commands for browser automation via Chrome DevTools CLI) but the 'when' is only implied through 'Use this skill to...' rather than providing explicit trigger conditions like 'Use when the user asks about browser automation, Chrome DevTools, or headless browsing'. | 2 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'shell scripts', 'shell commands', 'Chrome DevTools', 'CLI', and 'browser', but misses common user variations like 'DevTools protocol', 'headless Chrome', 'browser automation', 'puppeteer', 'CDP', 'web scraping', or 'inspect element'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of shell scripting AND Chrome DevTools is somewhat distinctive, but 'shell scripts' and 'shell commands' are very broad and could overlap with general shell/bash skills, while 'automate tasks in the browser' could overlap with browser automation or web scraping skills. | 2 / 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.
The skill excels at actionability with comprehensive, executable CLI examples covering all tool categories. However, it trades conciseness and progressive disclosure for exhaustive inline command listings that could be better organized into referenced files. The workflow section is a good start but lacks validation checkpoints and error recovery guidance important for stateful browser automation.
Suggestions
Move the exhaustive command listings into a separate reference file (e.g., references/commands.md) and keep only 2-3 representative examples per category in the main SKILL.md.
Add validation checkpoints to the AI Workflow, e.g., 'After click/fill, take_snapshot to verify the action succeeded before proceeding' to create a feedback loop.
Reduce redundant examples that only differ by one flag (e.g., the --includeSnapshot variants) by noting the flag once as a general pattern rather than repeating it for every command.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but the exhaustive listing of every command variant with comments is verbose. Many of these flag combinations could be inferred from --help or a few representative examples rather than enumerating every permutation. | 2 / 3 |
Actionability | Every command is concrete, copy-paste ready, and includes real flags and arguments. The examples show actual CLI invocations with specific parameters, making it immediately executable. | 3 / 3 |
Workflow Clarity | The 3-step AI Workflow (Execute → Inspect → Act) provides a clear sequence, but there are no validation checkpoints or error recovery steps. For browser automation involving stateful interactions, missing feedback loops (e.g., verifying a click succeeded via snapshot before proceeding) is a gap. | 2 / 3 |
Progressive Disclosure | The skill references installation.md appropriately, but the main file is a long wall of command examples that could be split into separate reference files (e.g., navigation-commands.md, network-commands.md). The inline command catalog makes the overview heavy when a summary with links to detailed references would be more navigable. | 2 / 3 |
Total | 9 / 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
- ChromeDevTools/chrome-devtools-mcp
- Commit
1b857c9
- 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.