Content
63%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 dense, well-structured operational guide with concrete tool sequences, parameters, and pitfalls that make it genuinely actionable. Its weaknesses are redundancy (repeated pitfalls, a duplicate quick-reference table) and inlining reference-grade material rather than splitting it into a bundled file.
Suggestions
Consolidate repeated guidance: state the dash-to-colon node ID rule and the 'search tools first' rule once, and cut or compress the Quick Reference table since every tool slug already appears in its workflow section.
Move the per-tool parameter reference into a references/ file (e.g., TOOLS.md) and keep SKILL.md to workflows plus pitfalls, per progressive disclosure.
Add one or two example call payloads (e.g., a RUBE_SEARCH_TOOLS query and a FIGMA_GET_FILE_JSON call with file_key and depth) so the guidance is copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is terse and avoids explaining concepts Claude already knows, but has real redundancy: 'Always call RUBE_SEARCH_TOOLS first' appears in both Prerequisites and Setup, the dash-to-colon node ID format is stated three times, and the 18-row Quick Reference table repeats tool slugs already listed per-workflow. Mostly efficient, but noticeably could be tightened. | 3 / 5 |
Actionability | Concrete tool slugs, typed parameters ('Comma-separated node IDs (NOT an array)', 'scale (0.01-4.0)'), and specific failure modes (400 on FigJam, 413 oversized payloads, 32-megapixel cap, ~30-day URL expiry) give mostly executable guidance. The gap is the absence of any example call payload, such as what a RUBE_SEARCH_TOOLS query or a FIGMA_GET_FILE_JSON invocation actually looks like. | 4 / 5 |
Workflow Clarity | Each of the five workflows has a numbered tool sequence labeled [Prerequisite]/[Required]/[Optional], and Setup includes an explicit checkpoint ('Confirm connection status shows ACTIVE before running any workflows') plus recovery guidance ('narrow scope or reduce depth' on 413). Minor validation gaps remain — e.g., no verification step after posting a comment — and no destructive/batch cap applies. | 4 / 5 |
Progressive Disclosure | The body is well-sectioned with clear headers, but there are no bundle files and the 18-row Quick Reference table is API-reference bulk inlined in SKILL.md, duplicating tool slugs from the workflow sections. This matches the anchor where content that should live in a separate reference file is inline. | 3 / 5 |
Total | 14 / 20 Passed |