daytona-windows-cert

test on Windows, enterprise CA, corporate certificate, GPO cert, TLS fetch failed, Windows sandbox, daytona windows, self-hosted cert. Use when validating OpenWork Windows enterprise TLS/OS-trust fixes in a Daytona Windows sandbox.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

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, well-sequenced Windows repro playbook with concrete commands and explicit validation. It loses points on conciseness (redundant verified-session command restatements) and progressive disclosure (monolithic inline content duplicating an existing bundle file).

Suggestions

Remove the redundant 'verified session' command restatements (e.g. the gh release and curl/tar shape blocks) that duplicate the commands already shown just above them.

Move the full ca-probe.js source out of SKILL.md and reference the existing scripts/ca-probe.js bundle with a one-line pointer, since the file already exists.

Consider extracting the multi-step TLS-repro setup into a referenced reference script section so SKILL.md stays a lean overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no tutorializing of TLS/CA concepts), but it pads length by restating command blocks as "The release command shape from the verified session was..." and "The Windows download/extract shape from the verified session was..." immediately after giving the same commands, so it could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready bash/PowerShell/JS with concrete paths, sandbox IDs, download URLs, and a complete inline ca-probe.js, leaving no key detail abstract.	3 / 3
Workflow Clarity	Sections 1–5 plus Cleanup give a clear sequence with explicit validation checkpoints (listener netstat check, verified probe JSON result, VNC checks of both healthy and broken endpoints) and feedback/gating for a risky repro operation.	3 / 3
Progressive Disclosure	The body is a long, mostly-monolithic SKILL.md that inlines the full ca-probe.js even though the bundle file scripts/ca-probe.js exists and is referenced, and restates repo support-asset paths inline rather than pointing one level deep to a lean overview, matching the level-2 anchor of some structure with content that could be separate kept inline.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 keyword-rich, tightly-scoped description with an explicit Use-when trigger clause and strong natural trigger coverage. Its only weakness is that it leads with trigger keywords rather than enumerating multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	The description names the domain (enterprise CA, OS-trust, TLS) and an action ("validating OpenWork Windows enterprise TLS/OS-trust fixes") but does not list multiple concrete actions, matching the level-2 anchor of naming a domain and some actions without being comprehensive.	2 / 3
Completeness	It states what the skill does ("validating OpenWork Windows enterprise TLS/OS-trust fixes") and includes an explicit "Use when ... in a Daytona Windows sandbox" trigger clause, clearly answering both what and when.	3 / 3
Trigger Term Quality	It opens with natural trigger terms a user would actually say ("test on Windows", "Windows sandbox", "daytona windows", "TLS fetch failed", "enterprise CA", "corporate certificate", "GPO cert", "self-hosted cert"), giving good coverage of natural phrasings.	3 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to Windows + Daytona + enterprise CA + OpenWork OS-trust with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 5 missing, 5 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: different-ai/openwork
Path: .opencode/skills/daytona-windows-cert/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.