Content
85%Reviews 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 instruction skill: a clear decision flow, skill inventory, and priority rules make it easy to follow. Its main weakness is repetition across the EXTREMELY-IMPORTANT block and Red Flags table that inflates the token budget.
Suggestions
Collapse the EXTREMELY-IMPORTANT block and Red Flags table into a single concise section to remove restated 'you MUST' messaging.
Trim the 12-row Red Flags table to the few highest-value rationalization traps to reduce token cost.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Directive prose is mostly efficient, but the EXTREMELY-IMPORTANT block, the 12-row Red Flags table, and repeated 'you MUST' messaging restate the same rule several ways, adding padding that could be tightened. | 2 / 3 |
Actionability | For an instruction-only skill the guidance is concrete: an explicit invoke-before-respond rule, a decision-flow digraph, a skill table with when-to-invoke, priority order, and friendly-name mapping give clear actionable direction. | 3 / 3 |
Workflow Clarity | A clear multi-step sequence is given via the flowchart (message -> check skills -> invoke -> announce -> todos -> follow -> respond) plus explicit skill priority and type guidance; no destructive/batch operations require validation feedback loops. | 3 / 3 |
Progressive Disclosure | No bundle files exist and the skill is self-contained with well-organized sections (Rule, Available Skills, Priority, Red Flags, Types, Friendly Names) and no nested references, satisfying the well-organized-sections bar. | 3 / 3 |
Total | 11 / 12 Passed |