Content
21%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 a persona/competency catalog: it tells Claude what an elite Scala engineer knows rather than what to do, with no code, commands, workflows, or working references. Nearly all of the expertise listing duplicates knowledge Claude already has and should be moved to reference files (or a real playbook that exists), leaving actionable instructions in SKILL.md.
Suggestions
Replace the knowledge catalog with actionable guidance: e.g. an SBT build/test loop snippet, a Pekko actor + supervision example, and a ZIO/Cats Effect service skeleton with idiomatic error handling.
Fix the dangling reference: 'resources/implementation-playbook.md' does not exist in the bundle — either create the file (in references/) with concrete recipes or remove the pointer.
Define a real workflow with validation checkpoints (clarify task → choose effect system/framework → implement → compile + run tests via SBT → review), instead of the generic four-line Instructions block.
Cut the 'Core Expertise / Technical Excellence' sections down to a short tech-selection table (use X for Y) and push detail into bundled reference files, restoring token budget for instructions Claude doesn't already know.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~50-line 'Core Expertise / Technical Excellence / Architectural Principles' catalog restates ecosystem knowledge Claude already has (what Cats Effect, ZIO, the actor model, CQRS, G1/ZGC, circuit breakers are), adding little beyond bolded library names. Not anchor 1 because it enumerates tersely rather than prose-explaining, but most of the body is unnecessary content. | 2 / 5 |
Actionability | There is no code, command, or concrete example anywhere; 'Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes' is generic, and the expertise catalog only describes rather than instructs, matching anchor 1. Library mentions (Doobie, Tapir, ScalaCheck) are topic labels, not executable guidance. | 1 / 5 |
Workflow Clarity | The Instructions section gives a rough nominal sequence (clarify goals → apply best practices → validate outcomes → provide steps) but the steps are poorly defined and validation is unspecified, matching anchor 2. It is above anchor 1 because a recognizable sequence exists, but well below anchor 4 due to absent checkpoints. | 2 / 5 |
Progressive Disclosure | Sections are organized one level deep, but the single external reference — 'open resources/implementation-playbook.md' — points to a file that does not exist in the bundle (no references/, scripts/, or assets/ directories), and the long competency catalog is inline material that belongs in separate reference files. This fits anchor 3 ('some structure but could be better organized; references present but not clearly signaled'). | 3 / 5 |
Total | 8 / 20 Passed |