write-script-deno

Use ONLY when a TypeScript script specifically requires the Deno runtime (Deno stdlib or deno.land URL imports). For all other TypeScript, use write-script-bun instead.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./system_prompts/auto-generated/skills/write-script-deno/SKILL.md

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 skill body with strong workflow and validation guidance. Its main weakness is progressive disclosure: roughly half the file is an inlined SDK API reference with no separate reference files to offload it to.

Suggestions

Move the bulk of the windmill-client API reference into a references/ file (e.g. references/windmill-client.md) and keep only the most-used helpers inline with a clear pointer.

Trim the full JSDoc blocks in the inlined SDK section to signature + one-line purpose to recover token budget.

Consider extracting the metadata-sync detail into its own reference, leaving SKILL.md as an overview with the preview/run decision rules.

Dimension	Reasoning	Score
Conciseness	Mostly efficient action guidance rather than padded concept explanations, but the ~400-line inlined windmill-client API reference with full JSDoc is a large block of tokens that could be tightened or split out.	3 / 5
Actionability	Fully executable: concrete CLI commands with flags, copy-paste TypeScript examples, per-language argument-placeholder syntax, and exact `wmill` invocations cover the common cases.	5 / 5
Workflow Clarity	Clear sequence (write -> preview-not-run -> generate-metadata -> deploy only when asked) with real validation feedback loops (dry-run, diff regenerated locks, report version bumps); minor gaps keep it just short of a 5.	4 / 5
Progressive Disclosure	Has good section headers organizing the content, but a very large API reference that belongs in a separate reference file is inlined directly in SKILL.md, and the bundle ships no references/ files at all.	3 / 5
	Total	15 / 20 Passed

Description

65%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 sharp, distinctive routing description that excels at telling Claude when to use this skill over its Bun sibling. Its weakness is that it states the trigger but not the capability — the 'what' is never made explicit in the description text.

Suggestions

Lead with a short 'what' clause before the trigger, e.g. 'Write TypeScript scripts that run on the Deno runtime. Use ONLY when a script requires Deno stdlib or deno.land URL imports.'

Add a natural synonym such as 'Deno scripts' or '.ts' to broaden trigger coverage beyond the technical 'deno.land URL imports' phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain (TypeScript/Deno) and two concrete technical signals ("Deno stdlib or deno.land URL imports") but lists only 1-2 criteria rather than several specific actions.	3 / 5
Completeness	The 'when' is exceptionally explicit ("Use ONLY when a TypeScript script specifically requires the Deno runtime") but the description never states what the skill does — the 'what' is only implied by the skill name.	3 / 5
Trigger Term Quality	Good natural-keyword coverage ("TypeScript", "Deno runtime", "Deno stdlib", "deno.land") that users would actually say, with only minor synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche with an explicit hand-off to the sibling skill ("For all other TypeScript, use write-script-bun instead"), giving it distinct triggers and minimal conflict risk.	5 / 5
	Total	15 / 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
skill_md_line_count	SKILL.md is long (785 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: windmill-labs/windmill
Path: system_prompts/auto-generated/skills/write-script-deno/SKILL.md
Commit: 74af4ed

Reviewed: about 18 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.