Content
85%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 well-structured and actionable: a sequenced workflow with real validation and recovery loops, concrete tool calls, and clean progressive disclosure into two reference files. It is efficient though slightly redundant in places, and could include a few more copy-paste examples.
Suggestions
De-duplicate guidance between the Principles section and the per-task Constraints to tighten conciseness.
Add one or two more copy-paste-ready command examples (e.g., a workgroup-listing and a start-query-execution for a federated/S3 Tables catalog) to round out actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence (no "what is Athena" preamble), with directive MUST/MUST NOT constraints and compact tables; minor redundancy between the Principles and Constraints sections keeps it just short of a 5. | 4 / 5 |
Actionability | Provides an executable `aws___call_aws(...)` example, concrete catalog-addressing rules, a statement-classification table, and a troubleshooting table with fixes; profiling detail is delegated to a reference rather than inlined, leaving a small gap in copy-paste coverage. | 4 / 5 |
Workflow Clarity | Seven sequenced Common Tasks with explicit validation checkpoints (verify dependencies, classify before execute, confirm output location) and a feedback loop (on failure, list workgroups and retry with user choice) match the clear-sequence-with-validation-and-recovery anchor. | 5 / 5 |
Progressive Disclosure | SKILL.md is a concise overview with well-signaled, one-level-deep markdown links to real files (references/workgroup-selection.md, references/query-patterns.md) and an Additional Resources list, splitting detail appropriately. | 5 / 5 |
Total | 18 / 20 Passed |