Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, highly actionable skill body: executable commands, a clear diagnosis sequence with validation checkpoints, and per-failure remediation guidance. It respects Claude's competence and uses one-level-deep references appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes competence: concrete commands and per-failure fixes with no preamble explaining what overlays or specs are, so every token earns its place. | 3 / 3 |
Actionability | It gives fully executable commands (`azldev comp render -p <name>`, `prep-sources`, `diff -r`) and copy-paste-ready fixes per failure type (use `spec-set-tag`, TOML literal strings, multiple single-line replacements). | 3 / 3 |
Workflow Clarity | The diagnosis workflow is a clear numbered sequence (render/inspect -> diff pre/post -> inspect upstream) with render as the validation checkpoint, plus feedback loops in the Tips ('Test incrementally', 'verify with prep-sources', 'smoke-test after fixing'). | 3 / 3 |
Progressive Disclosure | Content is organized into clearly separated Diagnosis Workflow, Common Failures, and Tips sections, with one-level-deep, clearly signaled references to related skills and external schema docs rather than nesting detail inline. | 3 / 3 |
Total | 12 / 12 Passed |