CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/model-based-test-graph-author

Build-an-X workflow for model-based testing (MBT) per the canonical definition - authors a state-machine model of the SUT (states + transitions + guards + actions), validates the model is connected and complete, and runs the full graph-to-suite pipeline: pick a coverage criterion, generate covering paths, bridge each path into an acceptance-criterion entry ai-test-generator consumes, and assemble the generated tests into a suite file with confidence tiers and a curation note routing to ai-test-curator before merge. Per Wikipedia (en.wikipedia.org/wiki/Model-based_testing): MBT "leverages model-based design for designing and possibly executing tests." Use when a complex stateful flow (checkout, onboarding, multi-step wizard) needs systematic coverage that ad-hoc tests miss, or when the whole model-to-suite pipeline should run in one coordinated pass.

68

Quality

86%

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

Overview
Quality
Evals
Security
Files

Quality

Content

77%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, actionable body with a clear validated pipeline and good one-level-deep progressive disclosure. Its weakest dimension is conciseness: Wikipedia definition quotes and repeated coverage-criteria text re-explain concepts Claude already knows and could be trimmed without losing actionability.

Suggestions

Remove or condense the two opening Wikipedia block quotes that define model-based testing - Claude already knows MBT; keep at most one short cited line for the canonical definition.

Drop the repeated 'test criteria are needed...' quote from the body since the same citation appears in references/model-validation-and-coverage.md; reference it once instead.

Replace the '...' ellipses in the Path 1/2 examples and the '# ...' stub in generate_paths with complete snippets so the worked example is fully copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete examples, but two Wikipedia block quotes at the top plus scattered 'Per [mbt-wiki]' quotes explain what model-based testing is - a concept Claude already knows - and the coverage-criteria quote is repeated in the reference file; the body could be tightened by trimming these.

3 / 5

Actionability

Provides mostly executable guidance - a full checkout YAML model, a TypeScript Playwright test, and a pipeline with concrete file paths (models/<flow>.yaml, generated/paths.json, input/<flow>-mbt.yaml, tests/mbt-<flow>.spec.<ext>) and a fully-specified acceptance_criteria entry shape - but path examples use '...' ellipses and generate_paths has a '# ...' stub, leaving minor gaps.

4 / 5

Workflow Clarity

The pipeline is a clearly numbered 5-step sequence with explicit validation checkpoints and feedback loops - 'If validation fails... fix the model before generating anything', 'Missing any of the three - stop and ask', and step 5 'Never treat the generated tests as merge-ready... route to ai-test-curator' - matching the checklist-with-recovery anchor.

5 / 5

Progressive Disclosure

SKILL.md is a structured overview (Overview, When to use, How to use, Worked example, Pipeline, Anti-patterns, Limitations, References) with a single one-level-deep reference (references/model-validation-and-coverage.md, verified to exist) holding the validator and path-generator code; navigation is clearly signaled and the split is appropriate.

5 / 5

Total

17

/

20

Passed

Description

88%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, specific description that concretely enumerates the model-to-suite pipeline and pairs a clear 'what' with an explicit 'Use when' trigger. Its main weakness is reliance on internal pipeline jargon alongside the natural trigger terms, which slightly lowers trigger-term quality and creates minor overlap with sibling test-generation skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions explicitly - 'authors a state-machine model of the SUT (states + transitions + guards + actions), validates the model is connected and complete... pick a coverage criterion, generate covering paths, bridge each path into an acceptance-criterion entry... assemble the generated tests into a suite file with confidence tiers and a curation note' - comprehensive coverage of the pipeline.

5 / 5

Completeness

Explicitly answers both 'what' (authors/validates/runs the full graph-to-suite pipeline) and 'when' with a concrete 'Use when a complex stateful flow... needs systematic coverage that ad-hoc tests miss, or when the whole model-to-suite pipeline should run in one coordinated pass' trigger clause.

5 / 5

Trigger Term Quality

Good natural trigger terms ('checkout, onboarding, multi-step wizard', 'systematic coverage that ad-hoc tests miss') plus the domain term 'model-based testing', but it leans on internal jargon ('ai-test-generator', 'ai-test-curator', 'acceptance-criterion entry') that a user would not naturally say; a few common phrasings are missing.

4 / 5

Distinctiveness Conflict Risk

Carves a clear MBT niche with distinct stateful-flow triggers, but it names sibling skills 'ai-test-generator' and 'ai-test-curator' in the same pipeline, creating minor overlap risk with those closely related skills.

4 / 5

Total

18

/

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.

Reviewed

Table of Contents

DiscoveryImplementationValidation