CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/daytona-windows-cert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 highly actionable, well-sequenced Windows repro procedure with strong validation checkpoints, held back by redundant command restatements and an inlined bundle file that should be referenced instead.

Suggestions

Remove the 'verified session was:' restatements that duplicate commands already shown in each section.

Replace the inlined ca-probe.js listing with a one-line pointer to scripts/ca-probe.js, since the file is already bundled and copied into the VM.

Add an explicit 'if the listener is not up, re-run the scheduled task' style feedback loop so error recovery is not left implicit.

DimensionReasoningScore

Conciseness

Mostly efficient, but several commands are shown and then restated verbatim under 'the verified session was:' headers, and the full ca-probe.js is inlined despite existing as a bundle file.

3 / 5

Actionability

Copy-paste-ready bash and PowerShell commands with exact paths, the encoded-command trick, and clearly flagged placeholders cover the common cases end to end.

5 / 5

Workflow Clarity

A clearly numbered 1-5 sequence with Prereqs and Cleanup plus explicit validation checkpoints (netstat, expected ca-probe JSON, VNC pass/fail), but error-recovery feedback loops are only implicit via the doctor script and gotchas.

4 / 5

Progressive Disclosure

Section structure is good and repo support-script references are single-level, but the ca-probe.js bundle file's full contents are inlined in the body instead of being referenced, duplicating content that already lives in a separate file.

3 / 5

Total

15

/

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.

A trigger-keyword-dense description with strong natural terms and a clear, distinct niche, weakened only by a thin 'what' that understates the concrete actions the skill performs.

Suggestions

Replace the leading keyword dump with one or two concrete verbs describing what the skill does (e.g. 'install a corporate CA, serve healthy/broken HTTPS, and prove the Windows app uses OS trust').

Expand the 'Use when' clause to surface the certificate-specific failure trigger more explicitly rather than restating the 'validating fixes' phrase.

DimensionReasoningScore

Specificity

Names the domain ('OpenWork Windows enterprise TLS/OS-trust') and one concrete action ('validating...fixes in a Daytona Windows sandbox'), but the leading keyword list is not a set of actions, so coverage is not comprehensive.

3 / 5

Completeness

Both what and when are present with an explicit 'Use when' clause and trigger phrases, but the 'what' is a single thin action rather than the multiple concrete steps the skill actually performs.

4 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms ('enterprise CA', 'corporate certificate', 'GPO cert', 'self-hosted cert') and a literal error string users would paste ('TLS fetch failed', 'fetch failed').

5 / 5

Distinctiveness Conflict Risk

Clear niche (Windows enterprise TLS/OS-trust validation in a Daytona Windows sandbox) with distinct 'daytona windows' triggers that separate it from the generic daytona skill.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 5 missing, 5 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
different-ai/openwork
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.