Content
93%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is tight, highly actionable, and well-structured, with runnable commands for every tool and a clean reference split into examples.md. The only minor gap is the absence of an explicit feedback-loop workflow, which is largely irrelevant for a read-only single-purpose search skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean body with short tool descriptions, one runnable command each, and parameter bullets; no padding explaining search/MCP concepts Claude already knows. The single restated opener line is trivial. | 5 / 5 |
Actionability | Every tool ships a copy-pasteable 'mcporter call' command with realistic arguments, plus an executable setup/verify sequence and a runnable advanced-enable one-liner covering the common cases. | 5 / 5 |
Workflow Clarity | The read-only single action (call a search tool) is unambiguous with a pre-flight 'Verify mcporter is configured' conditional; the destructive/batch cap does not apply, but there is no multi-step validate→fix→retry loop to reach a 5. | 4 / 5 |
Progressive Disclosure | Well-organized sections with one clearly signaled, one-level-deep reference to references/examples.md (which exists); bulk examples are correctly split into the reference file, leaving the body concise and navigable. | 5 / 5 |
Total | 19 / 20 Passed |