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

67%

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

77%

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 clear, validated workflows for editing, testing, and syncing Windmill Deno scripts. Its main weakness is conciseness and structure: a massive inlined SDK reference and some redundancy inflate the token budget without proportional value.

Suggestions

Move the ~600-line windmill-client SDK API reference (lines 174–802) into a `references/windmill-client-api.md` file and keep only a pointer plus the most-used methods in the body.

Consolidate the repeated preview-vs-run-vs-deploy explanations (lines 10–15, 17–27, 39–45) into a single section to remove redundancy.

If the SDK reference stays inline, add a one-line table of contents or navigation cue so readers can jump past it to the operational guidance.

Dimension	Reasoning	Score
Conciseness	Operational prose on preview-vs-run intent and metadata hash drift is genuinely useful, but the ~600-line inlined windmill-client SDK reference and repeated re-statements of the deploy/preview distinction add substantial unnecessary token cost.	2 / 3
Actionability	Commands are concrete and flagged (`wmill script preview <path>`), TypeScript snippets are executable and copy-paste ready, and per-language arg shapes are specified exactly.	3 / 3
Workflow Clarity	Multi-step flows are sequenced with explicit validation checkpoints: a preview-vs-run decision tree, a `--dry-run` inspection step before narrowing, and a diff-and-report feedback loop for dependency bumps.	3 / 3
Progressive Disclosure	No bundle files exist, and the large inline SDK API reference is exactly the case of content that should be split into a separate reference file rather than kept inline, despite reasonable section headers.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 sharply scoped to the Deno runtime with an explicit redirect to the Bun alternative, making its conflict risk very low. It is held back from a top score because it states the trigger condition clearly but leaves the skill's actual capability implied rather than named.

Suggestions

Add an explicit 'what' clause, e.g. 'Write TypeScript scripts that run on the Deno runtime in Windmill.' before the trigger sentence.

Expand trigger terms with common variations a user might say ('Deno', 'npm:', 'Deno library') to broaden natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	It names a concrete domain and trigger (TypeScript scripts needing the Deno runtime, Deno stdlib, deno.land URL imports) but does not enumerate multiple distinct concrete actions — essentially a single routing decision.	2 / 3
Completeness	The 'when' is explicit ('Use ONLY when...'), but the 'what' (writing/generating Deno TypeScript scripts) is only implied rather than stated, so it does not clearly answer both.	2 / 3
Trigger Term Quality	Terms like 'TypeScript script', 'Deno runtime', 'Deno stdlib', and 'deno.land URL imports' are specific to the intended audience but lack broader coverage of common natural variations.	2 / 3
Distinctiveness Conflict Risk	A clearly defined Deno-runtime niche with an explicit disambiguator ('For all other TypeScript, use write-script-bun instead') makes it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 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 (802 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: 33d2845

Reviewed: 2 days 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.