CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

A well-structured, actionable body that gives Claude executable harness patterns and a clear verification loop without padding. The main improvement would be making the failure path explicit (what to do when verification fails) to strengthen the workflow feedback loop.

Suggestions

Add an explicit failure/retry branch to the Interaction Loop (e.g., 'If the expected state did not change, re-capture the snapshot, re-select the target, and retry once') to turn verification into a true feedback loop.

Replace opaque placeholders like <port> and <debug-port> with a brief note on how to discover the value (dev-server output / launch flag) so the examples are fully copy-paste ready.

DimensionReasoningScore

Conciseness

Lean and efficient throughout — it assumes Claude knows what Playwright/CDP are and avoids explaining basic concepts — with only minor spots (e.g., restating 'Use local browser automation to verify UI behavior with evidence') that could be trimmed.

4 / 5

Actionability

Provides two concrete, near-executable code samples (Playwright launch and CDP connect) plus explicit setup and interaction steps; placeholders like <port> and <app-root-selector> are explained, leaving only minor gaps from copy-paste readiness.

4 / 5

Workflow Clarity

The Setup Pattern and Interaction Loop are clearly sequenced, and the loop includes a 'Verify the expected state change' checkpoint and guardrails; not a full 5 because validation/feedback on failure is implicit rather than an explicit fix-and-retry loop.

4 / 5

Progressive Disclosure

Content is well organized into focused sections (What It Is Used For, Setup Pattern, harnesses, Interaction Loop, CDP Capabilities, Page Selection, Guardrails) with no external bundle files needed; stops short of 5 only because a few capability lists could be split into references if the skill grows.

4 / 5

Total

16

/

20

Passed

Description

88%Weight 40%Scale 1-5

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 clearly states what the skill does and when to use it, with concrete capability coverage and explicit trigger guidance. It could add a few more natural synonyms (e.g., 'browser automation', 'Playwright') to broaden trigger matching.

Suggestions

Add natural trigger synonyms users might say, such as 'browser automation', 'Playwright probe', or 'take a UI screenshot', to improve trigger matching.

Consider naming the concrete tools (Playwright/CDP) in the description so users referencing those tools surface this skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'drive and inspect a web, IDE, or Electron UI', 'screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' ('Build or adapt a local browser/CDP harness to drive and inspect... UI') and 'when' ('Use for local UI verification, screenshots...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user-facing terms like 'local UI verification', 'screenshots', 'accessibility snapshots', 'visual diffs', and 'reproducing UI bugs', but omits common phrasings like 'browser automation' or named tools users might say.

4 / 5

Distinctiveness Conflict Risk

The 'local browser/CDP harness' framing carves a clear niche for local verification, but spanning 'web, IDE, or Electron UI' leaves minor overlap risk with general browser-automation skills.

4 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cursor/plugins
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.