Content
78%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 content is a well-structured, lean overview that front-loads critical FigJam-specific gotchas and points cleanly to one-level-deep references for detail. Its main weakness is that full executable code examples are deferred to references rather than shown inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense with only-what-Claude-doesn't-know specifics (exact errors, tool behaviors, the resource: prefix rule) and avoids explaining what Figma/FigJam is, with just minor rhetorical padding like the round-trips justification that could be trimmed. | 4 / 5 |
Actionability | It names exact tools (get_figjam, upload_assets), exact error strings, and gives a copy-paste ToolSearch example, but full executable code for mutations is delegated to references rather than inlined. | 4 / 5 |
Workflow Clarity | A clear sequence is given (get_figjam first to get IDs, batch-load schemas, then load-font/await/mutate/return) with the 'get_figjam first' checkpoint and an ID-recovery path, though formal validate-fix-retry loops for batch ops live in the references. | 4 / 5 |
Progressive Disclosure | SKILL.md is a concise overview with a well-signaled Reference Docs section listing all 13 one-level-deep reference files (each verified to exist in references/) with one-line descriptions, making navigation easy. | 5 / 5 |
Total | 17 / 20 Passed |