daytona-electron-test

do e2e tests, run e2e, test on Daytona, run Electron on Daytona, validate feature, real desktop flow, CDP/noVNC, PR proof. Launch and drive OpenWork Electron in Daytona with validated frame evidence.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%

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

A highly actionable runbook with concrete commands, executable snippets, and well-sequenced validated workflows. Its main weaknesses are cross-section redundancy that hurts conciseness and the absence of progressive disclosure into bundle files for a skill of this length.

Suggestions

Deduplicate cross-section content: consolidate the three secrets-volume descriptions and the repeated pkill/exec gotcha into a single authoritative section, with other sections linking back.

Split the large inline material into one-level-deep bundle files (e.g. references/selectors.md for the selector map, references/troubleshooting.md, references/recording.md) and keep SKILL.md as a navigable overview pointing to them.

Move the lengthy two-sandbox Den marketplace eval and before/after recording sections into referenced files so the core "fastest path" flow stays lean.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids teaching basic concepts, but at ~600 lines it repeats material across sections (the secrets-volume setup appears in three sections and the pkill/exec gotcha in two), so it could be tightened and does not meet the "every token earns its place" anchor.	2 / 3
Actionability	It provides copy-paste-ready bash commands, executable JS snippets, and a selector table mapping each control to a stable selector and source file, matching the fully-executable anchor with only appropriate runtime placeholders like <CDP_URL>.	3 / 3
Workflow Clarity	Sub-workflows (workspace creation, OpenAI connect, the 8-step before/after recording) are clearly numbered with explicit validation checkpoints ("Verify: URL contains #/workspace/ws_", "Must contain Electron/", "Verify text includes 2 providers connected") plus a troubleshooting section for error recovery.	3 / 3
Progressive Disclosure	There are no bundle files and all ~600 lines live inline in SKILL.md; content that could be split (selector map, troubleshooting, recording workflow, Den marketplace section) is inline rather than one-level-deep referenced files, matching the "content that should be separate is inline" anchor, though organization into sections is clear so it is not a monolithic-1.	2 / 3
	Total	10 / 12 Passed

Description

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.

A strong, compact description that pairs an explicit set of natural trigger phrases with a concrete statement of what the skill does and a distinct niche. It earns full marks despite an unconventional keyword-list-then-sentence structure because both what and when are explicit.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions such as "Launch and drive OpenWork Electron in Daytona with validated frame evidence" plus "do e2e tests" and "validate feature", matching the anchor that lists several specific concrete actions rather than vague abstractions.	3 / 3
Completeness	It answers both "what" ("Launch and drive OpenWork Electron in Daytona with validated frame evidence") and "when" via an explicit list of trigger phrases, satisfying the anchor that requires explicit triggers and not triggering the missing-trigger-guidance cap at 2.	3 / 3
Trigger Term Quality	The opening list "do e2e tests, run e2e, test on Daytona, run Electron on Daytona, validate feature, real desktop flow, CDP/noVNC, PR proof" is a thorough set of natural phrases a user would actually say, matching the good-coverage anchor; it is not jargon-only or generic.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to OpenWork Electron on Daytona via CDP/noVNC with frame evidence, giving it distinct triggers unlikely to fire for unrelated skills despite a family of sibling daytona skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (606 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: different-ai/openwork
Path: .opencode/skills/daytona-electron-test/SKILL.md
Commit: 1345d51

Reviewed: about 13 hours 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.