Content
62%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 workflow structure with clear sequencing and validation checkpoints, particularly for async operations and ID resolution. However, it suffers from significant content repetition (user ID resolution and timestamp pitfalls appear in multiple places), lacks truly executable examples showing actual MCP tool invocation syntax, and could be more concise by consolidating duplicated guidance into single authoritative sections.
Suggestions
Consolidate repeated pitfalls (user ID resolution, timestamps) into the single 'Known Pitfalls' section and reference it from workflows instead of duplicating the information.
Add at least one fully executable example showing the actual MCP tool call syntax (e.g., how RUBE_SEARCH_TOOLS and AMPLITUDE_SEND_EVENTS are invoked with real parameters and what the response looks like).
Remove the generic 'When to Use' and 'Limitations' boilerplate sections at the end—they add no actionable information beyond what the description already conveys.
Consider extracting the detailed per-workflow parameter lists and pitfalls into a reference file if a bundle structure is available, keeping SKILL.md as a leaner overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but contains significant repetition—pitfalls about user_id vs internal ID are stated in workflows 2 and 3, then again in 'Common Patterns' and 'Known Pitfalls'. The timestamp warning appears twice. The boilerplate 'When to Use' and 'Limitations' sections at the end add no value. Several sections could be consolidated to reduce token usage. | 2 / 3 |
Actionability | Tool names and parameters are clearly specified, and the JSON example for user properties is helpful. However, actual tool invocation syntax is never shown (how to call these tools via Rube MCP), code blocks use pseudocode-style numbered steps rather than executable commands, and there are no concrete request/response examples for most workflows. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit prerequisite steps (e.g., FIND_USER before GET_USER_ACTIVITY), the async cohort pattern includes a polling/retry loop, and the setup section has a clear validation checkpoint (confirm ACTIVE status before proceeding). Each workflow labels steps as Required/Optional/Prerequisite. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a quick reference table, but it's a monolithic document with no bundle files to offload detailed content. The repeated pitfalls across multiple sections suggest content that could be better structured—e.g., a single pitfalls reference rather than duplicating across workflows and a dedicated section. | 2 / 3 |
Total | 9 / 12 Passed |