CtrlK
BlogDocsLog inGet started
Tessl Logo

preview

MUST use when opening the Windmill dev page / visual preview of a flow, script, or app. Triggers on words like preview, open, navigate to, visualize, see the flow/app/script, and after writing a flow/script/app for visual verification.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An exceptionally actionable, well-structured skill body: exact commands, expected output shapes, a decision table covering all common cases, and an anti-patterns section that anticipates real failure modes. The only deductions are mild redundancy between the decision rationale and the anti-patterns, and a launch.json subsection that could be split into a reference file for token efficiency.

Suggestions

Deduplicate the proxy-rationale: the anti-pattern 'Starting the proxy when no embedder needs a localhost URL' restates the 'Never start the proxy just in case' rule from the decisions section — keep one.

Move the launch.json entry examples and port conventions to a references/ file (e.g. launch-json.md) so the MCP-only path is loaded on demand.

The Non-visual alternative section could name the flag semantics (-d '<args>') briefly or point to a reference, since it currently gives commands without explaining how to discover required args.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — no explanation of what Windmill or a dev server is, and every section carries operational content. Falls short of 5 due to mild repetition: the proxy-vs-direct rationale appears in the decision section, again in the command section, and a third time as an anti-pattern ('Starting the proxy when no embedder needs a localhost URL').

4 / 5

Actionability

Fully executable throughout: exact invocations with flags ('wmill dev --proxy-port 4000 --path <wmill_path> --no-open'), copy-paste launch.json JSON blocks, the expected stdout line shapes to capture URLs from, and a concrete relay phrasing for the user. Minor placeholders (<wmill_path>) are appropriately parameterized, and the skill explicitly says not to construct URLs manually.

5 / 5

Workflow Clarity

The two independent decisions are cleanly separated, a decision table maps every common case to a concrete action, the launch.json path is a numbered two-step procedure with an explicit gating checkpoint ('Only take this path if you actually have such a tool'), and the anti-patterns section enumerates failure modes with recovery guidance. No destructive or batch operations, so no validation cap applies.

5 / 5

Progressive Disclosure

A single well-organized file with clear section headers and no nested references — everything is one level deep by construction. Falls short of 5 only because the launch.json subsection (~40 lines of entry conventions and JSON examples) could plausibly live in a reference file; there are no bundle files, so the whole payload loads on every invocation.

4 / 5

Total

18

/

20

Passed

Description

70%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 trigger-focused description with excellent natural trigger terms and an explicit use-when clause, but it under-describes what the skill actually does, listing only one action (opening the preview) rather than its concrete capabilities. Distinctive within the Windmill domain though somewhat reliant on generic words like 'open'.

Suggestions

Add one or two concrete capabilities to the 'what' half, e.g. 'Starts wmill dev (direct or proxy mode), opens the dev page, and configures .claude/launch.json for MCP preview integrations' — this would raise specificity and completeness.

Tighten the generic trigger word 'open' to something domain-tied (e.g. 'open the flow preview') to reduce collision risk with unrelated preview skills.

Mention the non-visual alternative (wmill flow/script preview) as a trigger case for users asking to 'test' a flow, which is a natural synonym currently missing.

DimensionReasoningScore

Specificity

The description names the domain ("Windmill dev page / visual preview of a flow, script, or app") but covers only a single action — opening the preview — with no mention of what the skill concretely does (proxy vs direct modes, launch.json integration, non-visual preview). This matches the anchor 'names domain and 1-2 concrete actions' rather than 4, which requires several specific actions listed.

3 / 5

Completeness

Both what ('opening the Windmill dev page / visual preview of a flow, script, or app') and when (explicit trigger words and a post-write case) are answered. Not 5 because the 'what' is a single thin clause rather than a concrete enumeration of capabilities.

4 / 5

Trigger Term Quality

Natural phrases users would actually say are present: 'preview', 'open', 'navigate to', 'visualize', 'see the flow/app/script', plus a post-task trigger ('after writing a flow/script/app for visual verification'). Falls short of 5 because some natural synonyms are missing and 'open' is over-broad rather than domain-tied.

4 / 5

Distinctiveness Conflict Risk

The Windmill-specific framing carves a clear niche, but generic trigger words like 'open' and 'preview' create minor overlap risk with other preview/run/screenshot skills. Not 5; clearly above 3 because the domain anchor keeps it mostly distinct.

4 / 5

Total

15

/

20

Passed

Validation

100%

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
windmill-labs/windmill
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.