Content
47%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 a concise, well-organized catalogue stub that advertises discovery and points to an upstream bundle, but it provides minimal executable guidance and no concrete installation workflow.
Suggestions
Replace the `open https://github.com/figma/skills` hint with a concrete, executable installation command (e.g. a git clone into the skills directory).
Add an explicit numbered workflow for acquiring and invoking the upstream bundle with a verification step that the skill is registered.
Drop the redundant "What it does" section or repurpose it to surface genuinely new detail beyond the frontmatter description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with organized sections and no padding of concepts Claude already knows, though the "What it does" section duplicates the frontmatter description, a minor instance of over-explanation. | 4 / 5 |
Actionability | Beyond `open https://github.com/figma/skills`, guidance is high-level ("install the upstream bundle into your active agent's skills directory", "ask the agent to invoke this skill by name") with no concrete executable steps to accomplish the skill's purpose. | 2 / 5 |
Workflow Clarity | A rough sequence is implied (advertise in Open Design → install upstream bundle → invoke), but steps are poorly defined in prose with no concrete commands and no validation checkpoints. | 2 / 5 |
Progressive Disclosure | Sections (What it does, Source, How to use) are clearly organized and the upstream reference is signaled one level deep, though the body is a stub pointing externally rather than an overview backed by bundled reference files. | 4 / 5 |
Total | 12 / 20 Passed |