Content
88%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.
This is a high-quality, expert-level audit prompt: concrete grep/verify/fix guidance, a rigorously gated five-phase workflow with validation checkpoints, and clearly signaled external references. The main weaknesses are moderate cross-phase redundancy and a long monolithic single-file structure with no bundled reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and assumes Claude's competence (no 'what is SQLite' padding) and almost every token is non-obvious domain specifics, but there is redundancy — Phase 3 re-asks questions already covered by Patterns 2/3/7 and the Phase 5 health table restates pattern descriptions. | 4 / 5 |
Actionability | It provides exact runnable grep patterns, step-by-step verify instructions, and copy-paste fixes (e.g. `PRAGMA optimize=0x10002`, `PRAGMA journal_mode = WAL`, `config.observesSuspensionNotifications = true`) covering the common cases. | 5 / 5 |
Workflow Clarity | A clear five-phase sequence with explicit validation checkpoints — verify-via-Read before reporting, framework gating with a hard stop, a false-positive checklist, and 'Require evidence... don't speculate without reading the code' as a feedback gate. | 5 / 5 |
Progressive Disclosure | Well-organized into clearly headed phases with one-level-deep, clearly signaled external references ('See axiom-data (skills/grdb-performance.md) §6'), but no bundle files exist and the ~340-line SKILL.md inlines material (Phase 3/4 tables, the version table) that could be split into a reference file. | 4 / 5 |
Total | 18 / 20 Passed |