write-script-bunnative

MUST use when writing Bun Native scripts. The script must start with //native to run on the native worker.

Quality

61%

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-bunnative/SKILL.md

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 skill is highly actionable with concrete commands and executable examples, and its prose is lean, but it is hampered by a monolithic inline SDK reference and the absence of validation feedback loops for destructive operations. Splitting the API reference into a referenced file and adding post-deploy verification steps would meaningfully improve it.

Suggestions

Move the ~600-line windmill-client SDK reference into a separate references/ file and link to it from a concise overview, keeping one-level-deep navigation.

Add an explicit verification step after destructive operations (e.g. confirm a deploy succeeded or that preview output matches expectations before proceeding).

Tighten the inline SDK block by keeping only the signatures most relevant to native scripts and pointing to the full reference for the rest.

Dimension	Reasoning	Score
Conciseness	The prose sections (CLI commands, preview-vs-run, metadata sync) are dense and assume Claude's competence, but the body embeds a ~600-line inline windmill-client SDK reference that pads the context window and could live in a separate file.	2 / 3
Actionability	Concrete executable code (//native + main, fetch, RT namespace, S3 ops), specific commands (wmill script preview, generate-metadata --dry-run, rehash), and exact per-language placeholder syntax make the guidance copy-paste ready.	3 / 3
Workflow Clarity	The preview/run/deploy decision tree and metadata-sync flow are well sequenced, but destructive and side-effectful operations (deploy, preview execution) lack an explicit validate-then-fix feedback loop, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the content is monolithic, with a large inline API reference that the rubric explicitly flags as content that should be split into a separate, clearly signaled file.	2 / 3
	Total	9 / 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 has a clear, distinctive trigger and identifies the domain well, but it is thin on enumerated capabilities and natural-term coverage. Strengthening the what-clause and adding common phrasings would lift it from adequate to strong.

Suggestions

List 2-3 concrete capabilities the skill performs (e.g. write/preview/deploy Bun Native TypeScript scripts) instead of stating only the //native constraint.

Add common user phrasings to the trigger (e.g. "Use when the user asks to write, test, or preview Bun Native / native-worker TypeScript scripts").

Keep the //native requirement but frame it as part of what the skill does rather than the sole capability.

Dimension	Reasoning	Score
Specificity	Names the domain ("writing Bun Native scripts") and one concrete requirement ("The script must start with //native"), but does not enumerate multiple specific actions, so it falls short of the score-3 multi-action anchor.	2 / 3
Completeness	It includes an explicit "MUST use when" trigger (the when) and states the //native constraint (a thin what), but the "what does this skill do" is only implied rather than clearly enumerated, leaving it below the score-3 bar.	2 / 3
Trigger Term Quality	"writing Bun Native scripts" is a natural phrase a user might say, but coverage is thin — it omits common variations like "Bun scripts", "native worker", or "TypeScript native".	2 / 3
Distinctiveness Conflict Risk	"Bun Native" plus the distinctive //native directive carves out a clear niche with a trigger unlikely to fire for unrelated skills.	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 (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-bunnative/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.