Content
78%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.
A concise, well-structured instruction skill with concrete tool-call guidance and a clear workflow. The main gap is the absence of an explicit verification step confirming rules were applied to the final output.
Suggestions
Add a final verification step (e.g. 'Before finishing, confirm each cited rule was applied to the code you produced') to close the workflow loop.
Give the per-file read action a concrete call signature (e.g. mcp__team-rules__file_read) so the read step is as executable as the file_list step.
Trim the overlap between the step-2 example bullets and the Quick reference table, keeping the table as the single mapping source.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and assumes Claude's competence, but the step-2 example bullets overlap with the Quick reference table, leaving minor instances that could be trimmed. | 4 / 5 |
Actionability | Gives a concrete, executable tool call ('Call mcp__team-rules__file_list with path: "/rules" and depth: 2') and specific file mappings, but the 'read every rule file that plausibly applies' step lacks a concrete read-call signature. | 4 / 5 |
Workflow Clarity | Clear 4-step sequence with a conflict-surfacing checkpoint ('surface the conflict and ask before deciding'), but no explicit verification that the rules were actually applied to the produced code. | 4 / 5 |
Progressive Disclosure | Well under 50 lines with no bundle files and clear sections (Before writing, Rules of engagement, Quick reference), meeting the simple-skill exception for a well-organized single-purpose skill. | 5 / 5 |
Total | 17 / 20 Passed |