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

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./system_prompts/auto-generated/skills/write-script-bun/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 decision guidance and feedback loops for metadata sync and deploy gating. Its main weakness is token efficiency and progressive disclosure: a large SDK API reference is inlined rather than split into a bundled reference file, and some S3 examples are duplicated.

Suggestions

Move the windmill-client SDK API reference (lines 172-791) into a bundled references/ file (e.g. references/windmill-client-api.md) and link to it from the body, keeping only 2-3 key examples inline; this improves both conciseness and progressive_disclosure.

De-duplicate the S3 load/stream/write examples that appear both in the S3 Object Operations section and again in the SDK reference to reduce token cost.

Add a short consolidated checklist (write -> generate-metadata -> diff/version-report -> preview -> deploy-on-explicit-ask) so the multi-step workflow reaches the top workflow_clarity anchor.

Dimension	Reasoning	Score
Conciseness	Prose is largely efficient and assumes Claude's competence, but ~620 lines of inlined windmill-client SDK signatures (lines 172-791) and duplicate S3 examples (shown in both the TypeScript section and the SDK reference) push token cost up; not a 2 because the bulk is genuine reference rather than concept explanation Claude already knows, not a 4 because the inline API dump and duplication could be trimmed.	3 / 5
Actionability	Concrete executable commands (wmill script preview, generate-metadata, rehash, --dry-run), complete TypeScript examples, and full API signatures with parameters are copy-paste ready and cover common cases; fits the fully-executable anchor.	5 / 5
Workflow Clarity	Clear sequencing with decision rules (preview-vs-run by intent, deploy only on explicit ask) and a real feedback loop (generate-metadata -> diff .lock -> report version bumps, --dry-run to narrow scope); not a 5 because there is no consolidated checklist and some validation guidance is implicit rather than enumerated.	4 / 5
Progressive Disclosure	Good section headers and signaled external references (AGENTS.wmill.md, rt.d.ts, preview/write-script-bunnative skills), but no bundle files exist and the ~620-line SDK API reference is inlined in SKILL.md where it clearly belongs in a separate reference file, matching the 'content that should be separate is inline' anchor; not a 4 because the large reference is not split out, not a 2 because headers and external pointers provide real structure.	3 / 5
	Total	15 / 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 clear, third-person description with an explicit trigger clause and a distinct Bun-runtime niche, but it leans on a single runtime-selection action rather than enumerating capabilities. Stronger than mid-anchor on trigger coverage and completeness yet short of the top anchor on specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ("writing TypeScript scripts") and a concrete decision ("pick it for TypeScript unless the script specifically needs Deno"), but the only actions are writing scripts and choosing a runtime rather than a comprehensive capability list, matching the 1-2-concrete-actions anchor; not a 2 because it does name two concrete actions, not a 4 because coverage is thin.	3 / 5
Completeness	Explicit "MUST use when writing TypeScript scripts" supplies a clear when, and "Bun is the default and preferred TypeScript runtime — pick it for TypeScript" supplies a what; not a 5 because the what is a narrow runtime-selection statement rather than a richer capability description with multiple concrete triggers.	4 / 5
Trigger Term Quality	Natural terms a user would say are present ("writing TypeScript scripts", "TypeScript", "Bun", "Deno"); good but not comprehensive coverage since ".ts" extension and "TS" shorthand are missing, placing it just below the 5 anchor and above the 3.	4 / 5
Distinctiveness Conflict Risk	Scoped to TypeScript scripts with a Bun-vs-Deno decision and an explicit Deno exception, giving a clear niche; minor overlap risk with the closely related write-script-bunnative skill keeps it just below 5.	4 / 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 (791 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: 7915540

Reviewed: 3 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.