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 solid structural overview of Linear automation via Rube MCP with clear tool names and workflow sequences. Its main weaknesses are redundancy across sections (priority values, team scoping advice repeated), lack of concrete executable examples showing actual tool call payloads, and missing validation/error-recovery steps for data-modifying operations. The content would benefit from being trimmed and split into a concise overview plus a detailed reference file.
Suggestions
Add concrete tool call examples with actual input parameters and expected response shapes (e.g., show a real RUBE_SEARCH_TOOLS call and a LINEAR_CREATE_LINEAR_ISSUE call with sample JSON)
Remove duplicate information — priority values, team scoping advice, and tool listings appear in multiple places; consolidate into single authoritative locations
Add validation checkpoints to workflows: after creating an issue, verify it exists; after updating, confirm the update took effect; include error handling guidance for common failures
Extract the quick reference table and detailed parameter lists into a separate REFERENCE.md file, keeping SKILL.md as a lean overview with links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized but has significant redundancy — priority values are listed twice (in Manage Issues and Known Pitfalls), team scoping advice is repeated multiple times, and the quick reference table largely duplicates information already covered in the workflow sections. Some sections like 'Common Patterns' restate what's already in the workflow steps. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter lists, and tool sequences, which is helpful. However, there are no executable code examples or concrete input/output examples showing actual tool calls with real payloads. The 'ID Resolution' patterns use pseudocode-style numbered lists rather than showing actual tool invocations with parameters. The instruction to 'Always call RUBE_SEARCH_TOOLS first to get current tool schemas' undermines specificity since schemas may change. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with prerequisite steps marked, which is good. However, there are no validation checkpoints or error recovery steps — e.g., no guidance on what to do if issue creation fails, if a team ID isn't found, or if the connection drops. For operations that modify Linear data (creating issues, updating projects), there's no verify-after-write pattern. | 2 / 3 |
Progressive Disclosure | The content is structured with clear sections and a useful quick reference table, but it's a monolithic file with no bundle files to offload detail into. The GraphQL section, detailed parameter lists, and the full quick reference table could be split into separate reference files. For a skill of this length (~150+ lines), some progressive disclosure into supporting files would improve scannability. | 2 / 3 |
Total | 8 / 12 Passed |