Content
92%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.
An exemplary lean, single-purpose skill body: verbatim commands, precise field semantics, and an explicit auth-failure handling rule that prevents a misleading report. The only residual gap is the unguarded ${CURSOR_PLUGIN_ROOT} dependency and the absence of guidance for non-auth failure modes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~20-line body is lean with zero padding: two commands, a field-by-field summary instruction, and only non-obvious knowledge ('`flushes` is the number of completed flushes, not a pending count'; 'Never report an auth failure as "no memories found"'). Nothing explains concepts Claude already knows, matching anchor 5's 'every token earns its place'. | 5 / 5 |
Actionability | Two copy-paste-ready bash commands are given verbatim, plus concrete reporting instructions and an explicit remediation ('reinstalling with `--config api_key=...`'). It falls short of anchor 5 only because the commands depend on `${CURSOR_PLUGIN_ROOT}` being set (no fallback given) and there is no sample of the JSON output or guidance for non-auth failure modes (e.g., command not found, network error) — minor gaps per anchor 4. | 4 / 5 |
Workflow Clarity | For this simple single-purpose skill, the sequence is unambiguous: run both commands, report the combined result, with an explicit error-handling branch ('If doctor reports an authentication failure (401 / invalid key), say clearly that the Mem0 API key is invalid... Never report an auth failure as "no memories found"'). This is a clear decision checkpoint on the one real failure mode, meeting the simple-skill exception for a 5; the operations are read-only so no destructive-operation cap applies. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines, single-purpose, and requires no external reference files — none exist in the bundle (no references/, scripts/, or assets/ directories), and the body correctly inlines everything needed. Per the rubric's guidance for short skills with no need for external references, the clean single-heading structure merits a 5; there are no buried or nested references to penalize. | 5 / 5 |
Total | 19 / 20 Passed |