control-ui
Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly communicates both what the skill does (building/adapting browser/CDP harnesses for UI inspection) and when to use it (UI verification, screenshots, visual diffs, etc.). It uses concrete, domain-specific terminology that serves as effective trigger terms while maintaining a distinct niche that minimizes conflict with other skills. The description is concise yet comprehensive, written in proper third-person imperative voice.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'build or adapt a local browser/CDP harness', 'drive and inspect a web, IDE, or Electron UI', 'screenshots', 'accessibility snapshots', 'perf profiles', 'visual diffs', 'reproducing UI bugs'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI') and when ('Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs'). The 'Use for' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'browser', 'CDP', 'screenshots', 'accessibility snapshots', 'visual diffs', 'UI bugs', 'Electron', 'perf profiles', 'UI verification'. Good coverage of terms a user working with browser automation or UI testing would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: local browser/CDP-based UI harness for inspection and verification. The combination of CDP, browser harness, Electron, accessibility snapshots, and visual diffs creates a very specific domain unlikely to conflict with other skills like general testing or web development skills. | 3 / 3 |
Total | 12 / 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 executable code examples and clear workflow sequencing including validation steps. Its main weakness is moderate verbosity—some sections like 'What It Is Used For' and 'CDP Capabilities' could be trimmed since they describe concepts Claude already understands. The content would benefit from slightly tighter prose and potentially splitting advanced CDP details into a reference file.
Suggestions
Trim or remove the 'What It Is Used For' section—the skill description already covers this, and Claude can infer use cases from the instructions.
Condense the 'CDP Capabilities' bullet list into a single line like 'Use raw CDP for perf profiling, heap snapshots, network manipulation, rendering emulation, and console streaming when higher-level APIs are insufficient.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some sections that could be tightened. The 'What It Is Used For' section is somewhat redundant given the description, and some explanations (e.g., 'Do not add Playwright as a project dependency just for this probe unless the user asks') are reasonable but slightly verbose. The CDP Capabilities bullet list describes things Claude already knows about CDP. | 2 / 3 |
Actionability | Provides fully executable JavaScript code examples for both web and CDP harnesses, with concrete Playwright API calls, specific selectors (getByRole), and clear patterns for page selection. The interaction loop and setup pattern give specific, actionable steps. | 3 / 3 |
Workflow Clarity | The Interaction Loop provides a clear sequence with explicit validation checkpoints (capture before, act, capture after, verify state change). The Setup Pattern is well-sequenced. The page selection section includes error recovery (listing available pages instead of guessing). Guardrails section adds safety constraints for destructive/risky operations. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers, but it's a moderately long monolithic file with no references to supporting files. The CDP Capabilities section and some other content could be split into reference files. However, since no bundle files exist, the content is reasonably self-contained for its scope. | 2 / 3 |
Total | 10 / 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
- cursor/plugins
- Commit
7dd9fea
- 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.