Content
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a lightweight catalogue stub with tidy structure and a clear upstream pointer, but it offers no actionable guidance for performing the skill itself, relying entirely on redirecting to the upstream repository.
Suggestions
Inline at least one minimal executable example (e.g., a small script or command that produces a poster/PDF) so the skill is actionable without leaving the file.
Tighten by dropping the verbatim repetition of the description under 'What it does' and condensing the meta-explanation of the catalogue entry.
State the install/invoke sequence as numbered steps with an explicit verification checkpoint (e.g., confirm the skill appears in the agent's skills directory before invoking).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and avoids explaining concepts Claude already knows, but it repeats the description verbatim under 'What it does' and includes meta-prose about what a 'catalogue entry' is, so it could be tightened. | 2 / 3 |
Actionability | It provides no executable guidance for the actual design task; the only command ('open <upstream url>') merely opens a README, so it describes and redirects rather than instructing, matching the 'vague or abstract; describes rather than instructs' anchor. | 1 / 3 |
Workflow Clarity | A loose informal sequence exists (inspect README, install upstream bundle, invoke by name or trigger), but there are no validation checkpoints and the steps are stated informally rather than as a clearly sequenced workflow. | 2 / 3 |
Progressive Disclosure | The body is cleanly organized into labeled sections (What it does, Source, How to use) that point to a single, clearly-signaled one-level-deep upstream reference, avoiding a monolithic wall of text. | 3 / 3 |
Total | 8 / 12 Passed |