Content
100%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.
An exemplary index/router skill body: compact, actionable, and well-structured with a clear routing workflow and one-level-deep references to the specialist skills it maps to. It avoids padding and gives copy-paste-ready invocation guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: a compact task→skill route table with no concept explanations Claude already knows, a brief intro, and short Tools/Rules sections where every line earns its place. The only mild editorializing ("Counts (kept honest)") is justified and not padding, so it stays at 5 rather than 4. | 5 / 5 |
Actionability | Guidance is concrete and executable — exact relative paths (skills/marketing-context/, skills/marketing-ops/), a runnable CLI pattern (python3 skills/<skill>/scripts/<tool>.py --help), and a step-by-step Start Here that covers the common cases. Not a 4 because the mapping and invocation pattern are copy-paste ready with no gaps. | 5 / 5 |
Workflow Clarity | The Start Here decision flow is clearly sequenced (first run → known task → ambiguous request) with explicit branches to specific skills; this is a non-destructive routing index, so no validation checkpoint cap applies and the single-purpose/simple-skill exception supports a 5. Not a 4 because the branching sequence is unambiguous and complete. | 5 / 5 |
Progressive Disclosure | It is a clean overview with well-signaled, one-level-deep references to each specialist skill's SKILL.md, with content appropriately split across those files and easy navigation via the route table. No bundle reference/scripts/assets directories exist, but this skill's progressive structure is its sibling-skill routing, which is real and one level deep, so it earns 5 rather than 4. | 5 / 5 |
Total | 20 / 20 Passed |