Content
77%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable — complete executable code, concrete commands, and a well-validated TDD workflow with feedback loops — and it never wastes tokens explaining concepts Claude already knows. Its weaknesses are structural: an ~820-line monolithic file where reference-like material (matchers, spec styles, Ktor, CI) should be split into one-level-deep reference files, and some duplicated MockK examples that could be trimmed.
Suggestions
Split reference-like sections (Kotest Matchers, Spec Styles, Property-Based Testing, Ktor testApplication, CI/CD) into references/*.md files and keep SKILL.md as an overview with well-signaled one-level-deep links — this addresses both progressive_disclosure and conciseness.
Remove duplication: the FunSpec example already demonstrates mockk<UserRepository>() with coEvery, so the basic MockK section's UserServiceTest repeats the same pattern; keep one canonical version.
Move the version-sensitive Kover plugin version ('0.9.7') and matcher catalog into a reference file so the main body stays lean and version churn doesn't bloat the always-loaded skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~820-line body avoids concept-explaining padding (all signal, mostly code), but bulk reference material — the full matcher catalog, four spec-style tutorials, Ktor setup, and CI YAML — is inlined in SKILL.md, and MockK usage is demonstrated twice (in the FunSpec example and again in the MockK section). This fits 'mostly efficient but could be tightened' rather than 4, given how much content a single context load carries. | 3 / 5 |
Actionability | Every pattern ships complete, executable Kotlin — the TDD walkthrough runs from failing test to passing implementation with real test output, and the gradle commands (`./gradlew test --tests ...`, `koverHtmlReport`, `koverVerify`), Kover Gradle config, and CI YAML are copy-paste ready. Matches the fully-executable anchor. | 5 / 5 |
Workflow Clarity | 'How It Works' lays out a 7-step TDD sequence with explicit validation checkpoints ('Run tests (RED) — verify the test fails with the expected error', 'verify PASS', refactor keeping tests green), and the EmailValidator walkthrough demonstrates the fail→implement→pass feedback loop with actual test output. Clear sequence with explicit validation and error-recovery loops. | 5 / 5 |
Progressive Disclosure | No bundle files exist (references/, scripts/, assets/ are all absent), so everything lives inline in one ~820-line SKILL.md. Section headers and the quick-reference anchor links give reasonable navigation, but content that clearly belongs in separate files (matcher catalog, spec-style catalog, Ktor testing, CI integration) is inline with no one-level-deep references — the 'some structure but could be better organized' anchor. Not 4: there is no file-level split at all. | 3 / 5 |
Total | 16 / 20 Passed |