electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
86
83%
Does it follow best practices?
Impact
89%
3.42xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 skill description with excellent trigger term coverage, clear 'when to use' guidance, and a distinctive niche. Its main weakness is that the actual capabilities described are somewhat generic ('automate', 'interact with', 'control') rather than listing specific concrete actions the skill can perform within Electron apps.
Suggestions
Replace generic verbs like 'automate', 'interact with', and 'control' with specific concrete actions such as 'click UI elements', 'extract content', 'fill input fields', 'navigate between views', or 'capture screenshots' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Electron desktop apps) and the mechanism (Chrome DevTools Protocol via agent-browser), and lists example apps, but the actual actions are vague — 'automate', 'interact with', 'control', 'connect to' are generic verbs rather than concrete actions like 'click buttons', 'extract data', 'fill forms', 'navigate menus'. | 2 / 3 |
Completeness | Clearly answers both 'what' (automate Electron desktop apps via Chrome DevTools Protocol) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios, plus a 'Triggers include' section with concrete example phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including specific app names (VS Code, Slack, Discord, Figma, Notion, Spotify), variations like 'Electron app', 'desktop app', 'native app', and concrete trigger phrases users would say like 'automate Slack app', 'control VS Code', 'test this Electron app'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the Electron + Chrome DevTools Protocol niche is very specific and unlikely to conflict with web browser automation skills or general desktop automation. The explicit mention of specific Electron apps further narrows the scope. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent executable examples and clear workflow sequencing. Its main weakness is verbosity — the exhaustive platform-specific examples, long list of supported apps, and numerous common patterns make it longer than necessary given that Claude can generalize from fewer examples. The content would benefit from trimming repetitive examples and potentially splitting detailed sections into referenced files.
Suggestions
Reduce platform-specific launch examples to one per platform (the pattern is identical — just the app name/path changes), and state the general pattern instead of listing every app.
Remove or drastically shorten the 'Supported Apps' section — the principle 'any Electron app supports --remote-debugging-port' is sufficient without an exhaustive list.
Consider moving 'Common Patterns' and 'Troubleshooting' into separate referenced files to keep the main SKILL.md as a concise overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary content: the exhaustive per-platform launch examples for many apps are repetitive (the pattern is obvious after one example), the 'Supported Apps' list at the end adds little value since the principle is already stated, and some explanatory text could be trimmed. | 2 / 3 |
Actionability | Fully executable commands throughout with copy-paste ready bash examples. Every pattern includes concrete commands with specific flags, ports, and element references. The troubleshooting section provides specific diagnostic commands like `lsof -i :9222`. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced (launch → connect → snapshot → interact → re-snapshot) with explicit steps. The 'Inspect and Navigate' pattern includes a sleep/wait step and re-snapshot after navigation. Troubleshooting provides clear error recovery paths for common failure modes. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and logical grouping, but it's a long monolithic file (~170 lines of content). The platform-specific launch examples, common patterns, and troubleshooting sections could be split into separate referenced files to keep the main skill lean. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- vercel-labs/agent-browser
- Commit
fa043a4
- 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.