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.
The content is well-structured, concise, and clearly sequenced for a simple skill, with appropriate guardrails and a sensible escalation checkpoint. Its main weakness is actionability: it names the recall/reflect tools but never shows how to call them, so Claude would still need to discover the invocation details.
Suggestions
Add a minimal example of the recall and reflect tool invocations (arguments or expected inputs) so the guidance is executable rather than just named.
Clarify what inputs the recall tool expects (e.g., query/topic string) so Claude knows how to formulate the search.
Add a brief note on how to interpret or present reflect output when reasoning over accumulated memories.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with no padding or explanation of concepts Claude already knows; every section (Trigger, Workflow, Guardrails, Output) earns its place. | 5 / 5 |
Actionability | It names concrete tools (hindsight_memories, recall, reflect, .cursor/mcp.json) but gives no executable invocation syntax, parameters, or examples, leaving the actual usage incomplete. | 3 / 5 |
Workflow Clarity | A clear 5-step sequence includes a conditional checkpoint (use session memory first, escalate to MCP only if insufficient); the skill is non-destructive so no validation cap applies, though an error-recovery loop is absent. | 4 / 5 |
Progressive Disclosure | This is a short (<50 line) single-purpose skill with no external references needed, organized into clear sections (Trigger, Workflow, Guardrails, Output), meeting the simple-skill exception for a top score. | 5 / 5 |
Total | 17 / 20 Passed |