Content
68%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 delivers concrete, executable testing guidance with good section structure and efficient use of tokens. Its main weakness is workflow clarity: it reads as a topical reference rather than a sequenced process with validation checkpoints.
Suggestions
Turn the Hilt and screenshot guidance into a short numbered workflow with an explicit validation/verification step (e.g., run `./gradlew verifyRoborazziDebug` and act on failures).
Replace the '// ... tests' placeholder with at least one concrete DAO or ViewModel test assertion so the Hilt example is fully copy-pasteable.
Trim filler lines like 'Ensure you have the right testing dependencies.' to push conciseness toward anchor 5.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean code and commands with only minor over-explanation (e.g., 'Ensure you have the right testing dependencies' and the Roborazzi JVM rationale), matching anchor 4; not a 5 because a few sentences could still be trimmed. | 4 / 5 |
Actionability | It provides concrete, executable TOML dependencies, Kotlin screenshot and Hilt test examples, and specific gradlew commands, matching anchor 4; not a 5 because of the '// ... tests' placeholder and the absence of a Unit/ViewModel example. | 4 / 5 |
Workflow Clarity | Content is organized as topical sections rather than a sequenced workflow; only the screenshot setup is numbered and there are no validation checkpoints or feedback loops, fitting anchor 3. | 3 / 5 |
Progressive Disclosure | The single file is well-organized into clear sections (Testing Pyramid, Dependencies, Screenshot Testing, Hilt Testing, Running Tests) with no nested references, matching anchor 4; not a 5 because it exceeds the simple-skill line and some material (e.g., full dependency listings) could be split out. | 4 / 5 |
Total | 15 / 20 Passed |