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.
The skill body is concise, highly actionable, and presents a well-sequenced workflow with explicit validation checkpoints and guards for risky operations. Progressive disclosure is handled through clearly signaled one-level-deep links to external materials.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and executable with no padding about concepts Claude already knows (e.g., no 'what is an RPM' filler); every section delivers domain-specific azldev guidance or concrete commands. A few explanatory sentences (e.g. the overlays-vs-fork rationale) earn their place as non-obvious project knowledge. | 3 / 3 |
Actionability | Provides copy-paste-ready executable commands throughout — 'azldev comp prep-sources -p <name> --skip-overlays --force -o ...', 'azldev comp render -p <name>', 'diff -r ...', 'azldev comp build -p <name>' — plus complete TOML examples, matching the score-3 anchor. | 3 / 3 |
Workflow Clarity | Clear end-to-end sequence (inspect spec → decide inline/dedicated → add overlays → render/validate → diff-debug → build → smoke-test) with an explicit 'Validate' checkpoint and feedback loop ('render the spec to verify'), plus a destructive-operation guard requiring explicit user sign-off before forking a spec. | 3 / 3 |
Progressive Disclosure | Content is well-organized into clearly labeled sections (Before You Start, Decision, Spec Sources & Overlays, Validate) with one-level-deep, clearly signaled references to an external instructions file and two sibling skills, rather than a monolithic wall of text. | 3 / 3 |
Total | 12 / 12 Passed |