Content
22%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 minimal and organized but contains essentially no actionable guidance, code, or workflow steps, relying on a vague restatement of the description and an external link. It fails to instruct Claude on how to perform the skill's task.
Suggestions
Add concrete, executable guidance: how to invoke the PPT-generation tool, example commands or API calls, and the expected output format.
Include a brief workflow with validation (e.g. verify slides rendered, check styled images embedded) since deck generation is a batch output operation.
Bundle key references locally (under references/) instead of only linking to the external repo, and signpost them with explicit 'See X.md' pointers.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and avoids over-explaining known concepts, but it restates the description and adds no value, so it is 'mostly efficient' yet thin rather than genuinely lean with every token earning its place. | 3 / 5 |
Actionability | Statements like 'provides guidance and patterns for ai-powered ppt generation' are entirely abstract with no concrete code, commands, or specific steps, matching 'entirely vague or abstract; only describes rather than instructs'. | 1 / 5 |
Workflow Clarity | There is no sequenced process, no validation, and not even a single concrete action described; the simple-skill exception does not apply because no unambiguous action is given, matching 'steps missing or incoherent'. | 1 / 5 |
Progressive Disclosure | The body has section headers and is short, but it points to an external GitHub repo rather than bundled references, and there are no references/scripts/assets bundled, so structure is present but references are not clearly signaled or locally organized. | 3 / 5 |
Total | 8 / 20 Passed |