Content
56%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid structural overview of Klaviyo operations via Rube MCP with useful non-obvious details about API quirks (response nesting, rate limits, status values). Its main weaknesses are repetitive pitfall documentation across sections, lack of concrete executable examples showing actual tool calls with parameters and responses, and all content being inlined in a single file without progressive disclosure to supporting references.
Suggestions
Add concrete tool invocation examples showing actual parameter values and expected response shapes (e.g., a real RUBE_SEARCH_TOOLS call followed by KLAVIYO_GET_CAMPAIGNS with specific parameters and a sample response snippet).
Consolidate the repeated pitfalls (status case-sensitivity, response nesting, rate limits) into the single 'Known Pitfalls' section and remove duplicates from individual workflow sections to reduce token usage.
Remove the vacuous 'When to Use' section at the end—it adds no information beyond what the description already provides.
Consider extracting the 'Common Patterns' and 'Known Pitfalls' sections into a separate reference file to keep SKILL.md focused on the core workflows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary repetition—pitfalls about status case-sensitivity and response nesting are stated multiple times across sections and again in the 'Known Pitfalls' summary. The 'When to Use' section at the end is vacuous. However, most content is reasonably efficient and provides genuinely useful non-obvious information like rate limits, sparse fieldset syntax, and response nesting details. | 3 / 5 |
Actionability | The skill provides tool names, parameter names, and filter syntax examples, which is useful. However, there are no executable code snippets—the 'code blocks' are pseudocode/plain text sequences rather than actual executable calls. There are no concrete examples showing actual tool invocations with real parameter values and expected response structures, which would significantly improve actionability. | 3 / 5 |
Workflow Clarity | Workflows are clearly sequenced with prerequisite/required labels, and the setup section has a clear 4-step verification flow. The pagination pattern includes a clear loop-until-exhausted instruction. However, there are no explicit validation checkpoints or error recovery steps within the core workflows—e.g., no guidance on what to do if a campaign ID is not found or if rate limits are hit mid-workflow. Since these are read-only operations (not destructive), the missing validation doesn't trigger the cap at 3. | 4 / 5 |
Progressive Disclosure | The content is reasonably well-structured with clear sections and a quick reference table. However, at ~150+ lines with repetitive pitfall sections, some content could be split into separate reference files (e.g., a detailed pitfalls/troubleshooting doc). There are no bundle files and no references to external documents, so everything is inlined in a single file that's longer than ideal. | 3 / 5 |
Total | 13 / 20 Passed |