CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-pipelines-validator

Validates, lints, and security-scans Azure DevOps Pipeline configurations (azure-pipelines.yml / azure-pipelines.yaml). Use when working with ADO pipelines, YAML pipeline files, or CI/CD configurations in Azure DevOps — including validating YAML syntax and schema, detecting hardcoded secrets or credentials, checking for deprecated or unpinned task versions, enforcing best practices (caching, timeouts, display names), performing pipeline security audits, or reviewing azure-pipelines.yml before merging. Trigger terms: azure-pipelines.yml, ADO pipeline, Azure Pipelines, YAML pipeline, CI/CD validation, pipeline security scan, DevOps configuration review.

72

Quality

90%

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

SKILL.md
Quality
Evals
Security

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 well-structured, highly actionable skill body: executable commands for every scenario, an explicit error-recovery workflow with severity gates, and a clean references section pointing to real bundle files. The main costs are token overhead from the simulated output block and a broken custom-rule example, plus a minor inconsistency between 'four validation layers' and the [1/3]-[3/3] output numbering.

Suggestions

Trim the ~20-line simulated output block to the few lines needed to show the rule-code format and severity levels, moving a fuller example into references/azure-pipelines-reference.md.

Fix or remove the custom-rule extension snippet — it references an undefined `pool` variable and `self._get_line(job_name)` on a string, so it fails as written.

Reconcile the layer numbering: the intro says 'four validation layers' (0–3) while the sample output shows only [1/3]–[3/3], omitting the YAML lint layer.

DimensionReasoningScore

Conciseness

The body is efficient — commands, options, a troubleshooting table, and anti-patterns with WHY/BAD/GOOD structure, with no explanation of concepts Claude already knows. It is not a 5 because the ~20-line simulated output block and the 'Extending the Skill' code example add tokens that could be trimmed or moved to the reference file; not a 3 because the padding is minor rather than 'some unnecessary explanation' throughout.

4 / 5

Actionability

Guidance is mostly copy-paste executable: 'bash scripts/validate_azure_pipelines.sh azure-pipelines.yml --security-only --strict', individual python3 invocations, auto-detection behavior, and a CI snippet. It is not a 5 because the custom-rule example in 'Extending the Skill' is non-executable — it references an undefined `pool` variable and calls `self._get_line(job_name)` on a string — which is a minor gap in otherwise fully executable guidance.

4 / 5

Workflow Clarity

The 'When validation fails' section gives an explicit validate→fix→re-validate loop: 'Fix the flagged line and re-run the same layer (--syntax-only, --security-only, etc.) to iterate quickly', then 'Run full validation once all targeted fixes are applied to confirm no regressions', with severity-gated merge rules ('MEDIUM/HIGH findings... do not merge until resolved'). This matches the anchor for clear sequence with explicit validation steps and feedback loops for error recovery.

5 / 5

Progressive Disclosure

The body is a clear overview with one-level-deep, well-signaled references — 'references/azure-pipelines-reference.md — full YAML syntax reference and rule definitions' and five example assets each with a one-line description — and all referenced paths exist in the bundle. It is not a 4 because nothing that belongs in a separate file is inlined beyond minor illustrative snippets, and navigation is easy.

5 / 5

Total

18

/

20

Passed

Description

96%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: third-person, dense with concrete capabilities, explicit 'Use when...' triggers with extensions and synonyms, and a clearly delineated Azure DevOps niche. Its only weaknesses are mild redundancy (the trigger-term list restates phrases from the 'when' clause) and a couple of broad trigger terms that could fire for non-Azure CI/CD work.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Validates, lints, and security-scans', 'detecting hardcoded secrets or credentials', 'checking for deprecated or unpinned task versions', 'enforcing best practices (caching, timeouts, display names)' — with comprehensive coverage of the skill's layers, matching the anchor for multiple specific concrete actions. It is not a 4 because coverage is comprehensive rather than having minor gaps.

5 / 5

Completeness

It explicitly answers 'what' ('Validates, lints, and security-scans Azure DevOps Pipeline configurations') and 'when' ('Use when working with ADO pipelines, YAML pipeline files, or CI/CD configurations in Azure DevOps — including... reviewing azure-pipelines.yml before merging'), matching the anchor with concrete trigger phrases. It is not a 4 because the 'when' clause is fully explicit and enumerated, not merely present.

5 / 5

Trigger Term Quality

Trigger terms include file extensions ('azure-pipelines.yml / azure-pipelines.yaml'), synonyms ('ADO pipeline', 'Azure Pipelines', 'YAML pipeline'), and natural user phrasings ('CI/CD validation', 'pipeline security scan', 'DevOps configuration review'), matching the anchor for comprehensive coverage including synonyms and extensions. It is not a 4 because no common natural variation is missing.

5 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche (Azure DevOps pipeline YAML specifically) with distinct file-extension triggers, but generic trigger phrases like 'CI/CD validation' and 'DevOps configuration review' create minor overlap risk with validators for other CI systems (e.g., GitHub Actions). This matches 'mostly distinct; minor overlap risk with closely related skills' rather than a 5, whose minimal-conflict standard these broad terms slightly undercut.

4 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 6 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
pantheon-org/tekhne
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.