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 a comprehensive reference for ActiveCampaign operations via Rube MCP with good structural organization and useful pitfall documentation. Its main weaknesses are verbosity through repetition (pitfalls restated across sections), lack of executable examples (pseudocode patterns instead of concrete tool calls), and missing validation/error-recovery steps in workflows. The quick reference table is a strong addition.
Suggestions
Consolidate repeated pitfalls (e.g., ID precedence, capitalization rules) into the 'Known Pitfalls' section only, and remove duplicates from individual workflow sections to reduce token usage by ~30%.
Replace pseudocode patterns in 'Common Patterns' with concrete MCP tool call examples showing actual parameter values (e.g., a real RUBE_SEARCH_TOOLS call followed by ACTIVE_CAMPAIGN_FIND_CONTACT with specific email).
Add explicit validation steps to workflows, e.g., 'Verify the response contains the expected contact ID before proceeding' or 'Check response status to confirm tag was applied successfully'.
Consider splitting the detailed per-workflow parameter lists and pitfalls into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with the quick reference table and common patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but verbose for what it conveys. There's significant repetition across workflows (e.g., every workflow repeats the FIND_CONTACT prerequisite pattern, pitfalls about ID precedence are restated multiple times, and the 'Known Pitfalls' section largely duplicates pitfalls already listed in individual workflows). The content could be tightened substantially without losing clarity. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and value formats (e.g., capitalization rules, ISO 8601 dates), which is useful. However, there are no executable code examples — the 'Common Patterns' section uses pseudocode-style numbered lists rather than actual MCP tool call examples with concrete parameters. The instruction to 'always call RUBE_SEARCH_TOOLS first to get current tool schemas' partially undermines the detailed parameter documentation provided. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with prerequisite steps identified, and the tool sequences are well-labeled. However, there are no explicit validation checkpoints or error recovery steps within the workflows. For operations like bulk tagging or automation enrollment, there's no feedback loop (e.g., verify the tag was applied, confirm enrollment succeeded). The 'rate limits' guidance says to implement backoff but doesn't specify how. | 2 / 3 |
Progressive Disclosure | The content is organized with clear sections and a useful quick reference table. However, it's a monolithic document with no references to supporting files, and at ~200+ lines it could benefit from splitting detailed pitfalls or parameter references into separate files. The single external link to Composio docs is appropriate but the skill itself contains everything inline. | 2 / 3 |
Total | 8 / 12 Passed |