Content
48%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 lays out a coherent, well-sequenced technical-debt analysis framework with concrete thresholds and output formats, but it is held back by heavy padding with knowledge Claude already possesses, illustrative rather than executable examples, and no offloading of template content into reference files. The absence of actual measurement tooling commands leaves the skill's core analytical step under-specified.
Suggestions
Cut the textbook definitions of code smells, test-quality issues, and documentation debt, keeping only the quantification instructions and thresholds Claude wouldn't naturally apply.
Add executable measurement commands (e.g., specific complexity/duplication/coverage tool invocations) instead of name-dropping sonarqube/dependabot/codecov with no usage guidance.
Move the example dashboards, ROI calculation templates, and YAML quality-gate configs into reference files (e.g., references/templates.md) and keep SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~380-line body restates textbook concepts Claude already knows (code-smell taxonomies like "Exact duplicates (copy-paste)", "High cyclomatic complexity (>10)", "Feature envy", and definitions of brittle/flaky tests) and pads sections with illustrative blocks of invented figures ("Annual Cost: 240 hours × $150/hour = $36,000"), spanning many sections rather than isolated instances. | 2 / 5 |
Actionability | Concrete thresholds, quantification instructions, and an explicit output format are provided, but the code examples are illustrative patterns with `pass` bodies and the core measurement step offers no executable commands — tools like "sonarqube", "dependabot", and "codecov" are only name-dropped, leaving key details missing. | 3 / 5 |
Workflow Clarity | A clear eight-step numbered sequence (Inventory → Impact → Metrics → Plan → Implementation → Prevention → Communication → Success Metrics) with an explicit Output Format checklist and KPI targets serving as implicit checkpoints; the workflow is analytical rather than destructive/batch, so the validation cap does not apply, though no explicit verify or error-recovery steps exist. | 4 / 5 |
Progressive Disclosure | Eight well-organized numbered sections provide good structure, but the skill is a monolithic single file — the example dashboards, ROI templates, and YAML gate configurations clearly belong in separate reference files, and no bundle files exist to offload them. | 3 / 5 |
Total | 12 / 20 Passed |