Content
90%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 well-structured, highly actionable health-check skill with concrete tool invocations and explicit per-check validation. The main gap is that troubleshooting remedies are described rather than supplied, and the extended --deep mode could be separated out.
Suggestions
Inline at least one concrete fix per failed check in the Troubleshooting section (e.g., 'No API key configured' -> set MEM0_API_KEY or create ~/.pi/agent/mem0-config.json) rather than instructing Claude to generate them.
Consider moving the --deep memory-quality analysis into a separate reference file and linking to it, keeping the core health check as the lean default path.
Tighten vague thresholds in the deep mode (e.g., 'haven't been accessed recently' -> a concrete day count) to match the precision of the 180-day and >60% overlap rules.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and direct — checklists with concrete tool calls and no explanations of concepts Claude already knows; every section earns its place. | 5 / 5 |
Actionability | Provides exact mem0_memory action parameters, query/content strings, env var name, config file path, PASS/FAIL criteria, and a concrete display example — fully executable guidance. | 5 / 5 |
Workflow Clarity | Four checks are clearly sequenced with explicit per-check PASS/FAIL/WARN validation and a failure feedback loop; not a 5 because the troubleshooting fix steps are delegated ('add a section with specific fix steps') rather than pre-written. | 4 / 5 |
Progressive Disclosure | Single-file skill with well-organized sections and no external references needed; not a 5 because the --deep quality scan is a distinct optional feature inlined rather than split into its own file. | 4 / 5 |
Total | 18 / 20 Passed |