write-script-go

MUST use when writing Go scripts.

Quality

50%

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-go/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, highly actionable skill body with concrete commands, executable Go examples, and well-gated workflows including validation checkpoints. Its main weakness is verbosity from repeated restatements of the same deploy/metadata rules and the absence of any progressive file-level disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient wmill-specific operational guidance that Claude would not already know, but the same points are repeated verbatim across sections ('not a deploy' appears ~4 times, 'only when the user explicitly asks to deploy/publish/push' appears ~3 times) and could be tightened.	2 / 3
Actionability	Provides concrete executable wmill commands ('wmill script preview <script_path>', 'wmill generate-metadata --dry-run') and complete, copy-paste-ready Go examples covering package 'inner', the main signature, return types, and error handling.	3 / 3
Workflow Clarity	Clear intent-gated decision rules for preview vs run vs sync push vs deploy, with explicit validation checkpoints (diff regenerated .lock/.script.yaml, report version bumps, --dry-run before narrowing, rehash for hash-only drift) and feedback loops for the remote-mutating/version-bumping operations.	3 / 3
Progressive Disclosure	Content is well-sectioned with headers, but there are no bundle files (references/scripts/assets absent) and the entire ~104-line body is inline in one file; the detailed metadata-sync prose is dense content that is not split into separate one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

22%

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 an overly terse trigger-only sentence: it states when to use the skill but not what it does or which concrete capabilities it provides. It is distinct enough to fire on Go-scripting requests yet underspecified relative to its siblings.

Suggestions

Add a what-clause naming concrete capabilities, e.g. 'Scaffold wmill Go scripts with the inner package, main signature, return types, and error handling, and keep wmill metadata in sync. Use when writing or editing Go scripts.'

Broaden trigger coverage to include 'golang', 'write/create a Go script', and 'wmill Go script' so natural user phrasings match.

Disambiguate from sibling skills by foregrounding the wmill-script context (e.g. 'for wmill Go scripts') rather than generic 'Go scripts'.

Dimension	Reasoning	Score
Specificity	The phrase 'MUST use when writing Go scripts' names the domain but lists no concrete capability actions (e.g. scaffolding the 'inner' package, wiring return types, syncing wmill metadata), functioning as a pure trigger rather than a capability description.	1 / 3
Completeness	It explicitly answers WHEN ('MUST use when writing Go scripts') but entirely omits WHAT the skill does; per the rubric, missing either what or when lands at the lowest anchor.	1 / 3
Trigger Term Quality	'writing Go scripts' and 'Go scripts' are natural terms a user would say, but coverage is thin and misses common variations such as 'golang', 'write a Go script', or 'create a Go script'.	2 / 3
Distinctiveness Conflict Risk	'Go scripts' is a recognizable niche, but the description gives no disambiguating capability and could still overlap with sibling write-script-* skills (e.g. write-script-python).	2 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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