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.
68
57%
Does it follow best practices?
Impact
81%
1.22xAverage 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 scripts) but lacks concrete action examples and explicit trigger guidance. It uses second-person framing ('Use this skill to') which is borderline but not first/second person voice in the main clause. 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', 'interact with web pages programmatically'.
Rewrite in third person voice (e.g., 'Writes shell scripts and runs shell commands to automate browser tasks via Chrome DevTools CLI') to improve clarity and follow conventions.
| 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 'what' is partially addressed (write shell scripts, run 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 running headless browser commands'. | 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', 'web scraping', 'puppeteer', or 'CDP'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of shell scripting AND Chrome DevTools via CLI is somewhat distinctive, but 'write shell scripts or run shell commands' is broad enough to overlap with general shell/bash scripting skills, and '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 concrete, executable commands and a clear snapshot example showing the UID-based interaction model. However, it suffers from being overly comprehensive inline—the exhaustive command catalog bloats the file when most variants could be discovered via --help or placed in a reference file. The workflow section is adequate but lacks validation/error-handling guidance for stateful browser automation.
Suggestions
Move the detailed command reference sections (Navigation, Emulation, Performance, Network, Debugging, Extensions, Experimental, Service Management) into a separate references/commands.md file and link to it from SKILL.md.
Add validation checkpoints to the AI Workflow, e.g., 'After click/fill, take_snapshot to verify the expected state change occurred' and 'If navigation fails or element is not found, retry or inspect console messages.'
Trim inline examples to 1-2 representative commands per category, noting that --help is available for discovering all flags and variants.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but the exhaustive listing of every command variant with comments is verbose. Many of these flag combinations (e.g., multiple navigate_page variants, pagination options) could be discovered via --help and don't need to be enumerated inline. | 2 / 3 |
Actionability | Every command is concrete, copy-paste ready, and includes real arguments and flags. The snapshot example shows actual output format with UIDs, making it clear how to chain commands together. | 3 / 3 |
Workflow Clarity | The 3-step AI Workflow (Execute → Inspect → Act) provides a clear high-level 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, handling navigation failures) is a gap. | 2 / 3 |
Progressive Disclosure | There is a reference to installation.md for setup, which is good. However, the massive command reference (~100 lines of examples) is inlined rather than split into a separate reference file, making the SKILL.md much longer than needed for an overview. The command catalog would be better as a referenced file. | 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
faac61d
- 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.