write-script-bun

MUST use when writing TypeScript scripts. Bun is the default and preferred TypeScript runtime — pick it for TypeScript unless the script specifically needs Deno.

Quality

83%

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

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 concrete commands, executable examples, and a well-sequenced workflow that includes validation and feedback loops. Its main weakness is structure: the large inline API reference should be a separate, one-level-deep reference file rather than embedded in the main skill.

Suggestions

Move the ~600-line windmill-client API reference into a separate bundled file (e.g. references/windmill-client-api.md) and link to it from SKILL.md, keeping only the most-used methods inline to improve progressive_disclosure and conciseness.

Deduplicate the deploy guidance, which is restated across the CLI commands, preview-vs-run, and after-writing sections, into a single authoritative 'Deploying' block.

Confirm the referenced external targets (AGENTS.wmill.md, rt.d.ts, the preview and write-script-bunnative skills) actually resolve at the locations implied, since no bundle files are present to back them.

Dimension	Reasoning	Score
Conciseness	The instructional sections (CLI commands, preview-vs-run, metadata sync) are tight, but the roughly 600-line inlined windmill-client API reference and repeated deploy guidance add bulk that could be trimmed or offloaded, so it is mostly efficient with notable tightening needed.	2 / 3
Actionability	It gives executable commands (wmill script preview, generate-metadata --dry-run, rehash), complete copy-paste code examples for main/resource-types/S3, and explicit intent-based decision rules, all of which are concrete and runnable.	3 / 3
Workflow Clarity	The write→preview→generate-metadata→deploy flow is clearly sequenced with validation checkpoints (dry-run, diffing regenerated .lock files) and feedback loops, and it gates the destructive deploy step on an explicit user request.	3 / 3
Progressive Disclosure	No bundle files exist, yet the full windmill-client API reference is inlined inline in SKILL.md rather than split into a separate reference file; header organization is decent but content that should be separate remains inline.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 clearly answers both what (pick Bun as the default TS runtime) and when (writing TypeScript scripts), with strong, distinctive trigger terms. Its only weakness is specificity: it states a runtime-preference rule rather than enumerating the concrete script-lifecycle actions the skill actually performs.

Dimension	Reasoning	Score
Specificity	It names the domain ("writing TypeScript scripts") and a concrete routing action ("pick it for TypeScript unless the script specifically needs Deno") but does not list the multiple concrete actions the skill performs (preview, run, generate-metadata, deploy), so it is not comprehensive.	2 / 3
Completeness	It has an explicit trigger ("MUST use when writing TypeScript scripts") and states what the skill does (choose Bun as the default TypeScript runtime), clearly answering both what and when.	3 / 3
Trigger Term Quality	"writing TypeScript scripts", "TypeScript", "Bun", and "Deno" are exactly the natural terms a user would say when they need this skill, giving good coverage of the core trigger vocabulary.	3 / 3
Distinctiveness Conflict Risk	The TypeScript/Bun niche is explicit and is even contrasted against Deno ("unless the script specifically needs Deno"), making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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 (800 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: windmill-labs/windmill
Path: system_prompts/auto-generated/skills/write-script-bun/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.