CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/test-framework-blueprint

Build-an-X workflow that takes an SDET from no test suite to a complete framework design in seven steps - inventory the SUT, choose runner + language, directory layout + fixture architecture, object-model decision, test data + mocking wiring, reporting + CI integration, conventions doc + review gates - producing a written framework blueprint (directory tree, fixture list, chosen patterns, CI matrix) plus an implementation order. This is the whole-framework design workflow - not the Step 2 runner-choice decision on its own, not the Step 4 object-model pattern catalog it defers to, and not the scaffolder that generates the harness skeleton once the blueprint exists. Use when designing a test automation framework from scratch or re-architecting one that grew organically.

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

Overview
Quality
Evals
Security
Files

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, actionable design workflow with clear sequencing, per-step checkpoints, an enforcement feedback loop, and clean one-level-deep reference discipline. The only leverage is minor tightening of Overview prose and adding ready-made output templates per step.

Suggestions

Trim the Overview 'connective tissue' paragraph and avoid restating the step list that the section headers already convey, to improve conciseness.

Provide a copy-paste-ready blueprint document template (skeleton for the conventions doc) so each step's 'Decision output' drops into a concrete artifact rather than being described.

Add a short validation checklist at the end of Step 7 confirming the blueprint is internally consistent (fixture scopes match isolation choices, CI matrix matches coverage-layers table) before declaring it done.

DimensionReasoningScore

Conciseness

Largely lean and disciplined, deferring to catalogs rather than restating them, but a few passages (the Overview 'connective tissue' framing, restated step lists) could be trimmed for a fully token-efficient body.

4 / 5

Actionability

Concrete decision tables, a real directory tree, a fixture-scope table, and specific config/commands (junit reporter snippet, `npx playwright test --shard=1/4`, merge-reports) make the guidance executable; minor gaps remain since not every step ships a copy-paste-ready output template.

4 / 5

Workflow Clarity

Seven steps are clearly sequenced, each ending in an explicit 'Decision output' checkpoint, and Step 7 closes a feedback loop (per-PR checks + quarterly drift audit) that validates the blueprint against reality.

5 / 5

Progressive Disclosure

The body is an overview that points one level deep to real bundle files (references/fixture-mechanics.md, references/worked-example.md) and clearly signals sister-catalog deferrals, with well-organized per-step sections enabling easy navigation.

5 / 5

Total

18

/

20

Passed

Description

92%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, highly specific description that clearly scopes the workflow, its outputs, and its triggers while explicitly carving out adjacent skills to avoid confusion. Minor room only in broadening trigger synonyms.

DimensionReasoningScore

Specificity

Enumerates all seven concrete steps ('inventory the SUT, choose runner + language, ... conventions doc + review gates') and the exact output artifacts (directory tree, fixture list, chosen patterns, CI matrix, implementation order), giving comprehensive coverage of concrete actions.

5 / 5

Completeness

Explicitly states both what it does (seven-step design producing blueprint + implementation order) and when to use it ('Use when designing a test automation framework from scratch or re-architecting one that grew organically') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural terms ('designing a test automation framework', 'from scratch', 're-architecting one that grew organically') plus keywords (sdet, blueprint, fixtures), but missing some common synonyms/variations a user might say, so not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

Actively distinguishes itself from the Step 2 runner-choice decision, the Step 4 object-model catalog, and the scaffolder, establishing a clear niche with minimal conflict risk.

5 / 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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents