Content
75%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 a well-structured, actionable router that maps user goals to specialized skills without over-explaining, supported by a clear routing table and sequenced workflow. Minor consolidation of the two goal-understanding sections and a fuller routing-rules list would lift it to top marks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence — it never explains what Power Apps or connectors are — with only minor repetition between the 'Understand the Goal' and 'When the User Isn't Sure' sections that could be trimmed. | 4 / 5 |
Actionability | A concrete routing table maps user goals to specific `/add-*` skills with copy-paste-ready example questions; minor gaps remain in the routing-rules section, which gives only one example rule. | 4 / 5 |
Workflow Clarity | The workflow is clearly sequenced (Check Memory Bank → Understand the Goal → Route → Handle uncertainty) with an explicit decision branch on `$ARGUMENTS`; no validation feedback loop is needed for a non-destructive router, so it sits just below 5. | 4 / 5 |
Progressive Disclosure | Well-organized sections with a single clearly signaled one-level-deep reference (shared-instructions.md via the top banner); minor organization gaps from the overlapping goal-understanding sections keep it just below 5. | 4 / 5 |
Total | 16 / 20 Passed |