Content
50%Scale 1-3Reviews 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 ActiveCampaign operations via Rube MCP with useful API-specific details like capitalization rules and ID type requirements that Claude wouldn't inherently know. However, it suffers from redundancy (pitfalls repeated multiple times), lacks executable examples with concrete parameter values, and misses validation/error-recovery steps in its workflows. Tightening the content by consolidating repeated information and adding concrete invocation examples would significantly improve it.
Suggestions
Consolidate pitfalls into a single section rather than repeating them in each workflow and again in 'Known Pitfalls'—this would reduce token count by ~30%.
Add at least one concrete, copy-paste-ready tool invocation example showing actual parameter values (e.g., a RUBE_SEARCH_TOOLS call followed by a MANAGE_CONTACT_TAG call with specific inputs).
Add explicit validation/error-handling steps to workflows—e.g., 'If FIND_CONTACT returns multiple results, match by exact email' or 'If 429 response, wait N seconds and retry'.
Consider extracting the detailed parameter lists and pitfalls into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately verbose with some redundancy—pitfalls are repeated across individual workflow sections and then again in the 'Known Pitfalls' summary section. The quick reference table duplicates information already covered. However, the API-specific details (capitalization rules, ID types) are genuinely useful and not things Claude would inherently know. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and important behavioral notes (capitalization, ID types), which is valuable. However, there are no executable code examples—the 'Common Patterns' section uses pseudocode-style numbered lists rather than actual tool invocation examples with concrete parameter values. The instruction to 'always call RUBE_SEARCH_TOOLS first' is good but the skill never shows what that call looks like. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with labeled steps (Prerequisite, Required), and the setup section has a clear 4-step verification flow. However, there are no explicit validation checkpoints or error recovery loops—e.g., no guidance on what to do if FIND_CONTACT returns multiple results, or how to handle failures in bulk tagging. The 'batch with reasonable delays' advice is vague. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and a useful quick reference table, but it's a monolithic document with significant repetition (pitfalls repeated in each section and again in a summary). No bundle files exist to offload detailed reference material. The document could benefit from splitting detailed parameter docs and pitfalls into separate reference files. | 2 / 3 |
Total | 8 / 12 Passed |