Content
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid coverage of Klaviyo campaign operations via Rube MCP with clear tool sequences and useful pitfall documentation. Its main weaknesses are redundancy across sections (pitfalls repeated in workflows and summary), lack of truly executable examples (pseudocode rather than actual MCP call syntax), and missing validation/error-recovery steps in workflows. Tightening the content and adding concrete call examples would significantly improve it.
Suggestions
Add concrete, executable MCP call examples showing actual tool invocations with sample parameters and expected response structures, rather than pseudocode-style numbered lists.
Consolidate duplicated pitfall information—mention pitfalls once in the 'Known Pitfalls' section and reference it from workflows, or vice versa, to reduce redundancy.
Add explicit validation checkpoints and error recovery steps to workflows (e.g., 'If KLAVIYO_GET_CAMPAIGNS returns a 429, wait N seconds and retry; verify response contains data before extracting IDs').
Consider splitting detailed patterns and pitfalls into a separate reference file to keep SKILL.md as a concise overview with clear navigation pointers.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but contains some redundancy—pitfalls about status case-sensitivity, response nesting, and rate limits are repeated in both the individual workflow sections and the 'Known Pitfalls' summary section. The 'Common Patterns' section partially duplicates guidance already given in the workflows. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and filter syntax examples, which is good. However, there are no executable code snippets or concrete MCP call examples with actual request/response shapes—the 'code blocks' are pseudocode-style numbered lists or parameter listings rather than copy-paste-ready invocations. The guidance is specific but not fully executable. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with prerequisite/required labels, and the setup section has a logical flow. However, there are no explicit validation checkpoints or error recovery feedback loops—e.g., no guidance on what to do if a tool call fails, how to handle 429 rate limit responses beyond 'implement backoff,' or how to verify results before proceeding to the next step. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a quick reference table, but it's a fairly long monolithic document (~180 lines) with no bundle files to offload detailed content. The pitfalls, patterns, and workflow details could benefit from being split into separate reference files. The external link to Composio docs is helpful but the skill itself could better leverage progressive disclosure. | 2 / 3 |
Total | 8 / 12 Passed |