daytona-chrome-cdp

Launch and control standalone Chrome in a Daytona sandbox via CDP. Use for web sign-in, OAuth, Den Web setup, browser-only flows, or when the app should not be driven through Electron CDP.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

100%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 tight, executable, well-sequenced skill body that provides copy-paste commands, explicit validation against assuming success, and a clean teardown step, all within an appropriately sectioned single file. No substantive weaknesses identified.

Dimension	Reasoning	Score
Conciseness	Lean and efficient; assumes Claude's competence and presents only executable commands and minimal framing, with every section earning its place.	5 / 5
Actionability	Fully executable, copy-paste-ready commands (Chrome launch flags, preview-url extraction, browser tool calls) with concrete fallbacks ('try google-chrome...') covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced workflow (Launch -> Get CDP URL -> Verify -> Drive -> Stop) with an explicit validation checkpoint ('Do not assume navigation or sign-in worked until the post-action snapshot or URL proves it') and a userAgent disambiguation check.	5 / 5
Progressive Disclosure	A short (~67 line) single-purpose skill with well-organized section headers and no need for external references, satisfying the simple-skill exception for progressive disclosure.	5 / 5
	Total	20 / 20 Passed

Description

87%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, concise description that covers what the skill does and when to use it with concrete, natural trigger terms and a clear differentiator against the Electron CDP alternative. Specificity of the action list is the only minor gap.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Launch and control standalone Chrome in a Daytona sandbox via CDP') but coverage of actions is slightly limited (launch/control) rather than a comprehensive list.	4 / 5
Completeness	Explicitly answers both what it does ('Launch and control standalone Chrome... via CDP') and when to use it ('Use for web sign-in, OAuth, Den Web setup... or when the app should not be driven through Electron CDP') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes several natural user-facing triggers ('web sign-in', 'OAuth', 'Den Web setup', 'browser-only flows') with good coverage, though a few synonyms or phrasings a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (standalone Chrome distinct from Electron CDP) with a differentiating 'when not to use Electron CDP' clause, minimizing conflict with sibling browser skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: different-ai/openwork
Path: .opencode/skills/daytona-chrome-cdp/SKILL.md
Commit: 7b76a2b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.