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.
An exemplary instruction-only skill body: lean, actionable, with executable connector commands, explicit decision gates, a definition of done, and properly split one-level-deep references. It avoids concept re-explanation while giving Claude everything needed to execute.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense directive body — numbered steps, decision gates, short paragraphs — that assumes Claude's competence and avoids explaining concepts; every section earns its place. | 3 / 3 |
Actionability | Provides copy-pasteable executable commands (e.g. firecrawl.py map/scrape with flags), a 9-step concrete workflow, and a measurable quality bar rather than abstract direction. | 3 / 3 |
Workflow Clarity | Clear 9-step sequence with explicit 'Stop and ask'/'Continue silently' decision gates, a 'Done when' definition of done, and a Measured/User-provided/Estimated/N/A labeling scheme acting as validation checkpoints. | 3 / 3 |
Progressive Disclosure | SKILL.md is an overview with well-signaled one-level-deep references (analysis-templates.md, gap-analysis-frameworks.md, example-report.md), all confirmed present in references/, and a dedicated Reference Materials section. | 3 / 3 |
Total | 12 / 12 Passed |