Content
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, well-organized body that correctly delegates detail to one reference file. Its weaknesses are the absence of an in-body example and any validation step in the workflow.
Suggestions
Add one small complete `infographic` example block in the body so the output format is copy-paste ready without opening the reference.
Add a final validation step to the workflow (e.g., "Confirm output is a single `infographic` code block with no surrounding text and correct two-space indentation").
Inline a couple of the most-used data field names or theme names so common cases need not consult the reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence — no concept explanations, no padding; every line states a rule or workflow step, matching the "every token earns its place" anchor. | 3 / 3 |
Actionability | Gives concrete formatting rules (two-space indent, `key value`, arrays use `-`, single code block) but defers the full executable syntax and any example to references/prompt.md, leaving the body without copy-paste-ready detail. | 2 / 3 |
Workflow Clarity | Five steps are clearly sequenced, but there is no validation checkpoint (e.g., verifying the output is a single `infographic` block), so it sits at "steps listed but checkpoints missing". | 2 / 3 |
Progressive Disclosure | The body is a concise overview that signals a single one-level-deep reference (`references/prompt.md`, confirmed to exist), with the detailed syntax appropriately split out — matching the clear-overview-with-well-signaled-references anchor. | 3 / 3 |
Total | 10 / 12 Passed |