Content
82%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.
A well-structured, highly actionable scaffolding skill with complete executable examples and clear key rules. The main improvements are adding a post-restart verification checkpoint and optionally splitting the API/compatibility detail into reference files.
Suggestions
Add a validation step to the workflow, e.g. 'After restart, confirm the tool appears / runs a smoke call before telling the user it works'.
Consider moving the Anthropic/Claude compatibility table and full hook reference into a references/ file, keeping SKILL.md a lean overview with one-level-deep links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is code-forward and largely lean with high-density 'Key rules', but the Anthropic/Claude compatibility comparison table and adaptation steps are somewhat expansive for a scaffolding skill, keeping it just below the 'every token earns its place' anchor. | 4 / 5 |
Actionability | Provides two complete, copy-paste-ready TypeScript examples (minimal shape and multi-tool) plus concrete opencode.json snippets, covering the common cases at the top anchor. | 5 / 5 |
Workflow Clarity | The 'Scaffold workflow' is a clear 3-step sequence for a single-purpose task, but lacks any validation checkpoint confirming the plugin loaded after restart, matching 'clear sequence with minor validation gaps'. | 4 / 5 |
Progressive Disclosure | Content is well-organized into clearly labeled sections with no nesting, but everything is inlined in one ~160-line file with no split-out references for the API detail or compatibility guide, matching 'good structure; minor organization gaps'. | 4 / 5 |
Total | 17 / 20 Passed |