Content
72%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 concise, actionable, and well-structured for a simple read-only survey skill, but the workflow lacks validation/error-handling checkpoints, which holds workflow clarity at the midpoint.
Suggestions
Add explicit error handling for tool calls, e.g. what to do if a `list-*` call fails or a project has no apps/products.
Include a validation checkpoint before presenting, confirming all gathered statistics are present and consistent.
Add a brief note on how to map each `list-*` tool's output fields into the report template placeholders to close the actionability gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence, listing tools and steps without explaining basic concepts; the only mild redundancy is repeating the frontmatter overview line, so it sits just below a 5. | 4 / 5 |
Actionability | It names concrete tools (`list-projects`, `list-apps`, etc.) and CLI equivalents (`rc offerings list`), plus a complete report template and explicit issue categories; minor gaps remain in mapping tool output into the template. | 4 / 5 |
Workflow Clarity | A clear 5-step sequence is present (parse, gather, present, highlight), but there are no validation or error-recovery checkpoints — no guidance for when a `list-*` call fails or returns empty — leaving checkpoints implicit. | 3 / 5 |
Progressive Disclosure | This is a simple single-purpose skill under 50 lines with no need for external references, and it is well-organized with clear section headers, so it qualifies for the simple-skill exception to score 5. | 5 / 5 |
Total | 16 / 20 Passed |