Content
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a lean, well-organized catalogue pointer that cleanly delegates the full workflow to upstream, but it is light on actionable detail: the only command opens a URL, the install step lacks concrete commands, and the 'What it does' section redundantly restates the description.
Suggestions
Replace the description-verbatim 'What it does' block with skill-unique context or remove it to cut redundancy.
Provide a concrete install command (e.g., a git clone / copy into the skills directory) instead of sending the user to read the upstream README.
Add an explicit verification step confirming the skill is discoverable/invokeable after install.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and avoids explaining concepts Claude knows, but the 'What it does' section repeats the frontmatter description verbatim and the blockquote ('Curated from Figma's MCP server guide') adds meta noise, so it could be tightened further. | 2 / 3 |
Actionability | It offers a concrete command (`open https://github.com/figma/skills`) and a named invocation step, but the core task (running Figma Plugin API scripts) has no executable guidance and the install step is described without commands, so guidance is incomplete with key details missing. | 2 / 3 |
Workflow Clarity | A sequence is present (inspect README → install bundle → invoke by name/trigger) but the install step is vague and there are no checkpoints or verification, matching 'steps listed but checkpoints missing or implicit.' | 2 / 3 |
Progressive Disclosure | This is a sub-50-line pointer skill with clear sections (What it does, Source, How to use) and a single well-signaled one-level reference to the upstream repo; no nested local references exist, so well-organized sections earn the top score per the simple-skill note. | 3 / 3 |
Total | 9 / 12 Passed |