write-script-bunnative

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

Quality

66%

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-bunnative/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, accurate skill body with strong CLI/code guidance and useful deploy/metadata guards, but it is monolithic: the large inline API reference inflates the token budget and keeps progressive disclosure from scoring higher.

Suggestions

Move the bulk windmill-client API reference into a references/ file (e.g. references/windmill-client-api.md) and keep only the top helper signatures inline with a pointer.

Promote the core write-a-native-script flow into a short numbered checklist with an explicit validation step (e.g. run wmill script preview, then generate-metadata, then diff the lock).

Tighten the repeated runtime-constraint prose (the 'fetch + standard library only' rule appears in several sections) into one canonical statement.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic-concept padding), but the ~600-line inline windmill-client API reference is a heavy token load that could be trimmed or moved, fitting the score-3 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Fully executable: copy-paste-ready //native TypeScript examples, exact wmill CLI commands with arguments, and complete function signatures covering common cases (main, preprocessor, S3, resource types), matching the score-5 anchor.	5 / 5
Workflow Clarity	Clear sequencing for preview-vs-run and metadata sync with explicit checkpoints (dry-run, diff regenerated locks, report version bumps to the user) and a deploy guard, but the core write-a-script path is not a numbered sequence with an explicit validate step, so it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	Good section headers and a couple of signaled external pointers (AGENTS.wmill.md, the preview skill), but the entire SDK API reference is inlined in SKILL.md with no bundle files to offload it, matching the score-3 'content that should be separate is inline' anchor.	3 / 5
	Total	15 / 20 Passed

Description

62%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.

The description is clear, uses third-person imperative voice, and answers both what and when, but it is narrow: a single trigger phrasing and one concrete constraint with no synonyms or broader capability list.

Suggestions

Add 1-2 synonyms / trigger variations (e.g. 'native worker', 'Bun isolate') so users phrase the need differently still match.

List the concrete capabilities the skill enables (e.g. export async main, fetch-only runtime, parallelized native worker) rather than only the //native constraint.

Expand the 'when' clause to multiple concrete triggers (e.g. 'Use when writing or debugging Bun Native scripts, adding //native scripts, or targeting the native worker').

Dimension	Reasoning	Score
Specificity	Names the domain ('writing Bun Native scripts') and one concrete constraint ('must start with //native to run on the native worker'), but lists only a single action rather than multiple specific capabilities, matching the score-3 anchor of domain + 1-2 concrete actions.	3 / 5
Completeness	Both 'what' (writing Bun Native scripts that start with //native) and 'when' ('MUST use when writing Bun Native scripts') are present and explicit, but the trigger clause covers only one phrasing rather than multiple concrete trigger phrases, so it stops at 4 rather than 5.	4 / 5
Trigger Term Quality	'Bun Native scripts' and '//native' are relevant keywords a user would say, but there are no synonyms or common variations (e.g. 'native worker', 'Bun isolate'), fitting the score-3 anchor of some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	The '//native' / 'native worker' framing carves a clear niche distinct from a regular Bun script skill, but there is minor overlap risk with a general Bun skill, matching the score-4 'mostly distinct; minor overlap risk' anchor rather than the fully-distinct 5.	4 / 5
	Total	14 / 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-bunnative/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.