CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/framework-choice-advisor

Use for any question about which test automation framework or QA tool to pick, including quick ones such as Playwright or Cypress for a new app, or a stack for web, API and mobile: Playwright vs Cypress vs Selenium, Appium vs Espresso/XCUITest, RestAssured vs Karate, k6 vs Locust. Compares tradeoffs, matches project needs to a choice, covers commercial vendor evaluation and records the decision.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Quality

Content

92%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-built decision-support skill body: lean, actionable, with a clearly sequenced workflow gated by an explicit evidence-confirmation checkpoint and a deferral escape hatch, and exemplary one-level-deep progressive disclosure to four real, substantive reference files. The only improvement space is trimming citation duplication between the inline tables and the References section.

DimensionReasoningScore

Conciseness

The body is dense decision-support content with no explanations of concepts Claude already knows — every table row carries decision-relevant tradeoff data with citations. Minor inefficiencies remain: the References section repeats citations already linked inline in the Step 2 table (Luo et al., Playwright actionability, Cypress experiments), and the 16-link reference list could be trimmed to what is not already cited in context.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: a scored six-axis NFR rubric with evidence requirements, a concrete decision tree ("Multi-browser required + multi-language team → Playwright"), specific commands and flags (`--shard=X/Y`, `trace: 'on-first-retry'`, `maxInstances`), per-layer short rules ("JVM team → RestAssured"), and offloaded formats for vendor evaluation and decision records. Anchor 4 would require gaps in the common cases; none are evident.

5 / 5

Workflow Clarity

Eight clearly sequenced steps with an explicit validation checkpoint before Step 2 ("Write the six scores down, each with the evidence behind it ... get the team to confirm the ranking ... If a top-ranked axis cannot be scored from evidence today ... stop and go to Step 6 (defer)") — a genuine feedback loop with an error-recovery (deferral) path, matching the anchor-5 pattern.

5 / 5

Progressive Disclosure

The SKILL.md spine stays an overview ("The per-layer matrices ... are in references/other-layers.md"), and all four referenced files (other-layers.md, directory-layouts.md, vendor-evaluation.md, decision-record-format.md) exist, contain substantive content, and are exactly one level deep with no nested references. Bulk material is appropriately split out and clearly signaled at point of use and in Hand-off targets.

5 / 5

Total

19

/

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: it states both what the skill does and when to use it with concrete, natural trigger phrases spanning web, mobile, API, and performance layers, plus the commercial-vendor and decision-recording paths. The only minor gap is that the listed actions are a shade less concrete than the strongest anchor examples and the deferral path is unmentioned.

DimensionReasoningScore

Specificity

The description lists four concrete actions ("Compares tradeoffs, matches project needs to a choice, covers commercial vendor evaluation and records the decision") appropriate to a decision-support skill. It stops short of anchor 5 because the verbs are slightly less concrete than fully-specified operations and the deferral output path is not mentioned.

4 / 5

Completeness

It explicitly answers both what ("Compares tradeoffs, matches project needs to a choice, covers commercial vendor evaluation and records the decision") and when ("Use for any question about which test automation framework or QA tool to pick") with concrete trigger phrases. The explicit "Use for" clause satisfies the trigger-guidance requirement, so no cap applies.

5 / 5

Trigger Term Quality

It enumerates the natural phrases users actually say: "which test automation framework or QA tool to pick", "a stack for web, API and mobile", and tool-name pairings ("Playwright vs Cypress vs Selenium, Appium vs Espresso/XCUITest, RestAssured vs Karate, k6 vs Locust") covering all four test layers. Coverage includes synonyms ("stack", "pick") and the quick-question phrasing ("including quick ones such as Playwright or Cypress for a new app").

5 / 5

Distinctiveness Conflict Risk

The niche is clear — framework/tool selection decisions — and the triggers ("which ... to pick", tool-vs-tool pairings) are inherently selection questions, distinct from per-framework configuration skills. Minimal conflict risk with closely related skills.

5 / 5

Total

19

/

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

On this page