CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-script-ansible

MUST use when writing Ansible playbooks.

Quality

61%

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-ansible/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 delivers fully executable, copy-paste-ready guidance with concrete commands and complete YAML examples, plus a well-gated workflow (preview validates before any deploy, with a diff-and-report loop after metadata regeneration). Its weaknesses are padding: roughly half the file is generic Windmill script-writing content rather than Ansible-specific material, and that bulk should live in separate reference files.

Suggestions

Move the generic wmill CLI, metadata-sync, general-principles, and preprocessor content into a shared reference file (e.g. references/wmill-cli.md) and keep SKILL.md focused on the Ansible header/plays format.

Tighten or drop content unrelated to Ansible — e.g. the per-language argument-placeholder details for SQL/GraphQL/Bash/PowerShell and the TypeScript/Python preprocessor section.

Replace the vague 'Place scripts in a folder' with the concrete folder path, and either inline or remove pointers to files not in the bundle (AGENTS.wmill.md, the 'preview' skill).

DimensionReasoningScore

Conciseness

The Ansible section is lean, but the wmill CLI section is dense multi-clause prose ('pushing is a deploy, and deploying just to test overwrites the workspace version with untested changes', the generate-metadata/imports-propagation paragraphs) and the general-principles, preprocessor, and per-language placeholder content pads a skill whose stated niche is Ansible playbooks. Mostly efficient but with several sections that could be tightened or cut.

3 / 5

Actionability

Concrete commands throughout ('wmill script preview <script_path>', 'wmill generate-metadata --dry-run', 'wmill resource-type list --schema') and complete runnable YAML for the header, extra_vars, env lookup, and result.json output. Minor gaps: 'Place scripts in a folder' names no folder, and 'AGENTS.wmill.md' and the 'preview' skill are referenced but not in the bundle.

4 / 5

Workflow Clarity

The write→preview→generate-metadata→deploy sequence is clear with intent-based decision rules, and preview validation gates deploy; generate-metadata has an explicit feedback loop ('diff the regenerated .lock / .script.lock files and tell the user which dependency versions changed'). Not a 5 because the Ansible-specific path itself has no explicit validation step.

4 / 5

Progressive Disclosure

All ~167 lines live inline in SKILL.md with well-labeled sections, but large blocks that belong in separate reference files are inlined: the wmill CLI/metadata-sync guide, general Windmill principles, and preprocessor scripts. The section organization is good, matching the 3-anchor ('content that should be separate is inline') rather than the minimal-structure 2-anchor.

3 / 5

Total

14

/

20

Passed

Description

40%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 a bare trigger clause with a clear niche but no statement of capabilities: it says when to use the skill without saying what the skill does. It needs a concrete 'what' (writing Windmill Ansible scripts with a Windmill header plus standard plays) and richer natural trigger terms.

Suggestions

Add a 'what' clause stating concrete capabilities, e.g. 'Write Windmill Ansible scripts: a YAML document with a Windmill header (extra_vars, inventory, files, dependencies, options, vault_password) followed by standard plays, run via wmill script preview.'

Include the fact this is for Windmill-hosted Ansible so generic local-Ansible requests don't trigger it, e.g. 'Use when writing or testing Ansible playbooks to run on Windmill.'

Broaden natural trigger terms with synonyms users would say — 'playbook', 'playbooks', 'roles', 'tasks', 'Ansible automation'.

DimensionReasoningScore

Specificity

The description names the domain ('writing Ansible playbooks') but lists no concrete capabilities or actions, matching the 'names the domain but actions are minimal or generic' anchor rather than the 3-anchor which requires 1-2 concrete actions.

2 / 5

Completeness

The 'when' is explicit ('use when writing Ansible playbooks') but the 'what' is entirely missing — nothing describes what the skill actually does (Windmill Ansible script format, header keys, etc.), matching the 'only when is present without what' anchor.

2 / 5

Trigger Term Quality

'writing', 'Ansible', and 'playbooks' are natural terms, but common variations users would say ('playbook', 'roles', 'tasks', 'automation', YAML) are absent, matching the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

'Ansible playbooks' is a clear niche with minimal conflict risk, but omitting that this targets Windmill-hosted Ansible scripts means generic Ansible requests would also trigger it, matching 'mostly distinct; minor overlap risk with closely related skills' rather than the fully distinct 5-anchor.

4 / 5

Total

11

/

20

Passed

Validation

100%

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-ansible/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.