ansible-validator

Comprehensive toolkit for validating, linting, testing, and automating Ansible playbooks, roles, and collections. Use this skill when working with Ansible files (.yml, .yaml playbooks, roles, inventories), validating automation code, debugging playbook execution, performing dry-run testing with check mode, or working with custom modules and collections.

Quality

89%

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

Quality

Content

85%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, well-sequenced validation workflow with a properly structured one-level-deep bundle. Its main weakness is redundancy: the same scripts, references, and security guidance are restated across the decision tree, summary sections, and tables, inflating token cost without adding information.

Suggestions

Collapse the duplication between the decision tree, 'Core Capabilities (Summary)', and the Scripts Reference table — e.g. keep the decision tree as the sole workflow map and have it point to the script/reference tables instead of restating commands.

Consolidate the three separate security treatments (decision-tree step, 'Core Capabilities' sections 3 and 7) into one section referencing references/security_checklist.md.

Fix the decision-tree numbering (two steps are labeled '6.') and mention the assets/test/ fixtures so they are discoverable.

Dimension	Reasoning	Score
Conciseness	Individual sections are lean, but the body is structurally duplicative: the decision tree, 'Core Capabilities (Summary)', the Scripts Reference table, and the References table repeat the same scripts and files, and security scanning appears in three places. Matches 'mostly efficient but could be tightened'; not 4 because the repetition is systematic rather than minor.	3 / 5
Actionability	Fully executable guidance throughout: copy-paste bash commands (e.g. 'ansible-lint -x yaml[line-length] playbook.yml', 'bash scripts/test_role.sh <role-path>'), a complete scripts table with usage per script, and BAD/GOOD YAML examples. Not 4 because the common cases are covered with specific, ready-to-run invocations.	5 / 5
Workflow Clarity	The numbered decision tree sequences validation gates explicitly (syntax-check, yamllint, ansible-lint, --check --diff, molecule) with feedback loops ('Read references/common_errors.md when errors detected', molecule blocked-vs-code-failure handling) and a stated validation order in Notes. Not 4 because checkpoints and error-recovery paths are present at every stage; the duplicated '6.' numbering is a cosmetic typo.	5 / 5
Progressive Disclosure	Verified against the actual bundle: all referenced references/.md, scripts/.sh, and assets/* files exist, references are one level deep with no nested pointers, and each is signposted at its trigger point plus summarized in a References table. Not 4 because the split is appropriate and navigation is easy; only assets/test/ fixtures are undiscoverable from SKILL.md.	5 / 5
	Total	18 / 20 Passed

Description

95%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.

A strong description that clearly states capabilities and gives an explicit, trigger-rich 'Use this skill when...' clause with file extensions and natural synonyms. The only weakness is that its action verbs (validating, testing, automating) are somewhat generic and 'Comprehensive toolkit' is mild padding.

Dimension	Reasoning	Score
Specificity	Lists several concrete domain-tied actions ("validating, linting, testing, and automating Ansible playbooks, roles, and collections", "dry-run testing with check mode") but the verbs are less concrete than anchor-5 examples, and "Comprehensive toolkit" is mild fluff. Not 3 because more than 1-2 actions are named with specific artifacts.	4 / 5
Completeness	Explicitly answers both what ("Comprehensive toolkit for validating, linting, testing, and automating...") and when ("Use this skill when working with Ansible files...") with concrete trigger phrases, matching the anchor-5 pattern exactly.	5 / 5
Trigger Term Quality	Covers natural user phrasing comprehensively including synonyms and file extensions: "Ansible files (.yml, .yaml playbooks, roles, inventories)", "debugging playbook execution", "custom modules and collections". Not 4 because both extensions and colloquial variations are already present.	5 / 5
Distinctiveness Conflict Risk	Clear Ansible niche with distinct, specific triggers (playbooks, roles, inventories, collections); only trivial overlap risk with a generic YAML skill. Not 4 because the trigger terms are unambiguous for this domain.	5 / 5
	Total	19 / 20 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: pantheon-org/tekhne
Path: skills/infrastructure/ansible/validator/SKILL.md
Commit: a1083f4

Reviewed: 1 hour 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.