CtrlK
BlogDocsLog inGet started
Tessl Logo

write-script-java

MUST use when writing Java scripts.

60

Quality

70%

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 ./system_prompts/auto-generated/skills/write-script-java/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is highly actionable with concrete commands and complete Java code examples, and it conveys genuinely novel wmill operational knowledge. It is held back by verbosity and repeated restatements, a lack of explicit validation feedback loops, and a single monolithic file with no progressive disclosure structure.

Suggestions

Deduplicate the deploy-vs-run-vs-preview distinction into one authoritative section and remove the repeated restatements elsewhere to tighten conciseness.

Add an explicit validate->fix->retry feedback loop (e.g. after generate-metadata, fail fast on lock/hash mismatch with a concrete recovery step) to strengthen workflow clarity.

Move the detailed metadata-sync and CLI-command reference into a bundled references file and keep SKILL.md as a concise overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient and conveys wmill-specific operational knowledge Claude would not already know, but the metadata-sync section is dense and the deploy-vs-run distinction is restated across multiple sections, so it could be tightened rather than earning the lean level-3 anchor.

2 / 3

Actionability

It provides concrete, copy-paste-ready commands (e.g. "wmill script preview <path>", "wmill generate-metadata --dry-run") and complete executable Java examples (Main class with public static main, //requirements Maven syntax), matching the fully-executable level-3 anchor.

3 / 3

Workflow Clarity

Decision flows for preview vs run vs sync push and metadata sync are sequenced with some inspection checkpoints (--dry-run, diffing regenerated locks), but there is no explicit validate->fix->retry feedback loop for these mutating operations, fitting the level-2 anchor with validation gaps.

2 / 3

Progressive Disclosure

All content is inline in one ~88-line file with no bundle files present; it is organized into headed sections but references external docs (AGENTS.wmill.md, the preview skill) inline rather than splitting material, fitting the level-2 "some structure but could be better organized" anchor.

2 / 3

Total

9

/

12

Passed

Description

75%

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 concise and includes an explicit "use when" trigger scoped to Java scripts, which satisfies completeness and distinctiveness well. Its main weakness is specificity and trigger-term breadth, as it names only a single action and lacks common keyword variations.

Suggestions

Expand the description to list the concrete actions the skill performs (e.g. scaffolding a Main class, adding Maven dependencies, previewing vs deploying) to lift specificity.

Add natural keyword variations a user might say (e.g. "Java", "Java script", "JVM script") to broaden trigger-term coverage.

Keep the explicit "Use when..." clause but pair it with a short capability list to cover both what and when more richly.

DimensionReasoningScore

Specificity

The description "MUST use when writing Java scripts" names a concrete domain (Java scripts) and a single action (writing), but does not list multiple specific actions, matching the "names domain and some actions, but not comprehensive" anchor rather than the multi-action level 3.

2 / 3

Completeness

It explicitly answers both what ("writing Java scripts") and when ("MUST use when writing Java scripts") with an explicit "use when" trigger clause, satisfying the level-3 anchor for clearly answering both what AND when.

3 / 3

Trigger Term Quality

"writing Java scripts" is a natural phrase a user might say, but coverage is thin with no common variations (e.g. "Java", "scripts", "JVM"), fitting the "some relevant keywords but missing common variations" anchor.

2 / 3

Distinctiveness Conflict Risk

The Java-specific niche ("writing Java scripts") is distinct and unlikely to trigger for non-Java skills, matching the "clear niche with distinct triggers; unlikely to conflict" anchor.

3 / 3

Total

10

/

12

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.

Validation16 / 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.