CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-script-bunnative

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

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

The body is dense with non-obvious, high-value platform knowledge and is exceptionally actionable — exact commands, executable snippets, and full API signatures — with genuinely strong validation loops around metadata regeneration and deployment. Its weaknesses are structural: a ~600-line inline API reference that belongs in a separate reference file and noticeable repetition of the deploy/metadata safety guidance across sections.

Suggestions

Move the windmill-client TypeScript SDK API reference (lines 212-849) into a references/ file (e.g. references/windmill-client.md) and keep a short 'prefer these helpers' summary plus a pointer in SKILL.md.

Consolidate the repeated 'generate-metadata is not a deploy' and 'deploy only when explicitly asked' guidance into one authoritative section and reference it from the others.

Tighten the S3 section: the operation examples at lines 194-210 duplicate signatures already documented in the API reference below.

DimensionReasoningScore

Conciseness

Mostly efficient, platform-specific knowledge with no filler explaining concepts Claude already knows, but several points are repeated across sections — 'generate-metadata is not a deploy' appears three times (lines 14, 33, 45) and deploy-only-when-asked recurs in four places — fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'. Not a 4 because the repetition and the ~600-line inline API dump are more than minor trimmable instances.

3 / 5

Actionability

Fully executable guidance throughout: exact CLI commands with flags ('wmill script preview <path>', 'wmill generate-metadata --dry-run', 'wmill generate-metadata rehash', 'wmill resource-type list --schema'), complete copy-paste TypeScript examples, and full function signatures with parameters and defaults. This matches 'copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The write → preview → generate-metadata → deploy sequence is clearly ruled by user intent, with explicit validation checkpoints and feedback loops: preview validates before any deploy, '--dry-run ... then narrow with a path argument' recovers from over-broad regeneration, and 'diff the regenerated .lock ... and tell the user which dependency versions changed' gates deploys on reviewed version bumps. Destructive risk (deploy overwriting the workspace version) is explicitly guarded.

5 / 5

Progressive Disclosure

The body has real section structure and headers, but the full windmill-client API reference (~600 lines of signatures, lines 212-849) is inlined into SKILL.md when it clearly belongs in a references/ file — no bundle files exist at all. This sits between anchor 2 ('content that clearly belongs in separate files is inlined') and anchor 3 ('some structure but content that should be separate is inline'); the good headers and the deliberate 'included below — consult it' signal place it at 3, not 2, but the missing split keeps it from 4.

3 / 5

Total

16

/

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 short, third-person-adjacent, and delivers an explicit trigger ('MUST use when writing Bun Native scripts') plus the single most important technical constraint (//native first line). Its main weakness is that it conveys only one capability detail, missing synonyms like 'TypeScript' or 'Windmill' and any hint of the broader workflow guidance the skill contains.

Suggestions

Add capability verbs so the 'what' is comprehensive, e.g. 'Write, preview, and sync Bun Native TypeScript scripts for Windmill...'.

Include natural synonyms users would say — 'native TypeScript', 'Windmill script', 'bun script' — to improve trigger coverage.

Consider mentioning the follow-up workflow (preview locally, regenerate metadata, deploy) so the description reflects the skill's actual scope.

DimensionReasoningScore

Specificity

The description names the domain ('writing Bun Native scripts') and one concrete technical fact ('The script must start with //native to run on the native worker'), matching the anchor for naming a domain with 1-2 concrete elements but not comprehensive coverage. It does not list the skill's actual capabilities (previewing, metadata sync, resource types, S3 operations), so it is not a 4.

3 / 5

Completeness

It has an explicit and strong 'when' ('MUST use when writing Bun Native scripts') and a concrete partial 'what' (the //native first-line requirement), fitting the anchor where both are present but one could be more specific. Not a 5 because the 'what' omits what the skill actually covers beyond the //native rule (preview/run workflow, metadata sync, SDK usage); not a 3 because the 'when' is fully explicit, not weakly implied.

4 / 5

Trigger Term Quality

'writing Bun Native scripts' is a natural phrase a user of this platform would say, and '//native' / 'native worker' are relevant keywords. However, common variations and synonyms are missing — 'TypeScript', 'native TypeScript', 'Windmill', 'bun script' — so keyword coverage is only partial rather than good.

3 / 5

Distinctiveness Conflict Risk

'Bun Native' plus the '//native' marker is a clear niche with distinct triggers, but it could overlap with a general Bun or Windmill script-writing skill, matching 'mostly distinct; minor overlap risk with closely related skills'. Not a 5 because the term 'scripts' alone is broad and a sibling skill for regular bun scripts would compete on similar phrasing.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (849 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

Reviewed

Table of Contents

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.