write-script-bash

MUST use when writing Bash scripts.

Quality

63%

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-bash/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.

The body is highly actionable with executable commands and clear validation checkpoints, supported by well-structured sections. Its main weaknesses are verbosity in the metadata guidance and the absence of any progressive disclosure into separate reference files.

Suggestions

Tighten the 'Keep metadata in sync' paragraphs into a scannable list of rules, moving the dry-run/rehash/import-propagation detail to a reference file.

Split the detailed Windmill CLI metadata guidance into a references/ file and link to it from SKILL.md so the overview stays lean and progressive disclosure reaches one level deep.

Consider a short numbered 'write -> generate-metadata -> preview -> deploy' checklist near the top to make the core workflow sequence immediately scannable.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and avoids explaining basics, but the metadata-sync prose (dry-run, rehash, import propagation) is dense and could be tightened, fitting 'mostly efficient but could be tightened' rather than the lean level 3.	2 / 3
Actionability	Concrete wmill commands with exact flags and fully executable bash examples for arguments, JSON output, and env vars make the guidance copy-paste ready, matching the level 3 anchor.	3 / 3
Workflow Clarity	Decision rules for preview vs run vs deploy are explicit, and there are validation checkpoints plus feedback loops (preview before deploy, --dry-run to inspect stale items, diffing .lock to catch version bumps), matching the level 3 anchor.	3 / 3
Progressive Disclosure	Sections are well organized, but at ~94 lines everything is inline in a single file with no split-out reference material, so content that could be separate stays inline rather than achieving one-level-deep references at level 3.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 terse and carries an explicit trigger, but it is too thin to convey concrete capabilities or a clear 'what' beyond the 'when'. It sits squarely at the midpoint across all dimensions.

Suggestions

Add concrete capabilities the skill performs, e.g. 'Scaffold Windmill Bash scripts, wire positional arguments, and emit JSON results' to lift specificity and the 'what' side of completeness.

Expand trigger terms to natural variations users say ('bash script', 'shell script', '.sh') to improve trigger-term coverage.

Keep the explicit 'Use when ...' clause but pair it with a distinct 'what' statement so what and when are both clearly answered.

Dimension	Reasoning	Score
Specificity	The phrase 'writing Bash scripts' names the domain and a single action, but offers no comprehensive list of concrete capabilities, matching the 'names domain and some actions' anchor rather than the multi-action level 3.	2 / 3
Completeness	An explicit 'use when' trigger is present ('MUST use when writing Bash scripts'), but the 'what does this do' is only weakly implied and merged with the trigger, so it does not clearly answer both what and when at level 3.	2 / 3
Trigger Term Quality	'writing Bash scripts' is a natural term a user would say, but coverage is limited to one phrasing with no common variations (e.g. shell script, .sh), fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Bash-specific scoping gives a recognizable niche, but the terse single phrase could still overlap with sibling script-writing skills, matching 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 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-bash/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.