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 iPolloWork Windows enterprise TLS/OS-trust fixes in a Daytona Windows sandbox.

Quality

81%

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

81%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.

The body is a highly executable, well-sequenced Windows repro runbook with strong validation checkpoints and genuine non-obvious gotchas. Its main weakness is conciseness, due to several verbatim-repeated command blocks and the full ca-probe.js source being inlined alongside its bundle file.

Suggestions

Remove the verbatim restatements under 'The release command shape from the verified session was' and 'The Windows download/extract shape from the verified session was' since the full commands already appear above.

Drop the inlined ca-probe.js source block and keep only the reference to scripts/ca-probe.js, or vice versa, to avoid duplicating ~35 lines of code that already live in the bundle.

Consider moving the 'Shell/quoting gotchas' section into a references/ file linked from the body to tighten the main workflow and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Most content is genuine non-obvious operational knowledge that earns its tokens, but several commands are restated verbatim ('The release command shape from the verified session was', 'The Windows download/extract shape from the verified session was', and the 'Core repro cleanup shape' comment) which is clear padding. It is not a 2 because the bulk is efficient, and not a 4 because of these repeated command blocks.	3 / 5
Actionability	The body provides fully copy-paste-ready daytona/PowerShell/cmd commands, a complete encoded-command pattern, and an executable inlined ca-probe.js with an expected result. This matches the anchor for fully executable, copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced (sections 1-5 plus Cleanup) with explicit validation checkpoints (netstat listener check, ca-probe JSON verification, VNC pass/fail outcomes) and a feedback loop (restart app if CA added after first launch). This matches the anchor for a clear sequence with explicit validation and error-recovery guidance.	5 / 5
Progressive Disclosure	Sections are well organized and the one bundle file (scripts/ca-probe.js) is correctly referenced and present, but its full source is also inlined and the long shell-gotcha material lives in the single SKILL.md rather than a separate reference file. It is above anchor 3 (good structure, real referenced bundle) but short of 5 due to inlined content that could be split out.	4 / 5
	Total	17 / 20 Passed

Description

81%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.

The description is trigger-rich and highly distinctive with an explicit 'Use when' clause, but its 'what' is delivered as a keyword list rather than a concrete multi-action capability statement. It scores well overall with the main limitation being specificity of stated actions.

Suggestions

Replace the leading keyword run-on with a concise capability sentence naming 2-3 concrete actions (e.g., 'Install a fake corporate CA into the Windows machine store and verify iPolloWork uses the OS trust path') to lift specificity.

Keep the natural trigger terms but move them into the 'Use when' clause so the 'what' reads as capabilities and the 'when' reads as triggers.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action ('validating iPolloWork Windows enterprise TLS/OS-trust fixes') but does not list multiple specific actions, leaving coverage non-comprehensive. It sits above anchor 2 (which only names a domain) but lacks the several concrete actions needed for a 4.	3 / 5
Completeness	Both a 'what' (the leading keyword list plus the validating-fixes purpose) and an explicit 'when' ('Use when validating iPolloWork Windows enterprise TLS/OS-trust fixes in a Daytona Windows sandbox') are present. It is not a 5 because the 'what' is keyword enumeration rather than a crisp, concrete capability sentence with explicit trigger phrases.	4 / 5
Trigger Term Quality	It covers a comprehensive set of natural phrases users would say, including synonyms ('enterprise CA', 'corporate certificate', 'GPO cert', 'self-hosted cert') and the exact error string 'TLS fetch failed'. This matches the anchor for comprehensive natural-term coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	The triggers are tightly scoped to a clear niche ('daytona windows', 'iPolloWork enterprise TLS/OS-trust', 'GPO cert'), making conflict with other skills minimal. This matches the anchor for a clear niche with distinct triggers.	5 / 5
	Total	17 / 20 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: Devin-AXIS/iPolloWork
Path: .opencode/skills/daytona-windows-cert/SKILL.md
Commit: 52934c1

Reviewed: about 14 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.