Content
82%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 a strong, highly actionable runbook: every command is executable, the specific-test workflow is concretely sequenced, and there is no padding or concept explanation. The main weaknesses are verbatim command repetition (four copies of the same mocha invocation) and the absence of failure/recovery guidance in the workflow.
Suggestions
Define the mocha command once (or use a shell variable) and have the location-specific variants and Examples reference it, cutting roughly a third of the body's tokens.
Add a short failure-path note: what to do when the glob finds no matching file, or when a test fails (e.g., re-run the single test, check setup.ts requirements).
Clarify step 3 of the specific-test workflow with the actual check (e.g., 'ls src/**/<name>.e2e.ts' vs 'ls e2e/enterprise/**/<name>.e2e.ts') so location detection is deterministic.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence (no explanations of mocha, e2e, or pnpm), but the full ~200-character mocha command is repeated verbatim four times across the location instructions and the Examples section. That repetition is minor over-inclusion that could be trimmed, matching the efficient-with-minor-trimming anchor rather than the every-token-earns-its-place anchor at 5. | 4 / 5 |
Actionability | All commands are fully executable and copy-paste ready, including the exact glob patterns for finding test files, the env-prefixed mocha invocation for both source locations, and worked examples with real test filenames (trigger-event-preferences, billing). The only placeholder, <name-of-the-test>, is explicitly explained with replacement instructions. | 5 / 5 |
Workflow Clarity | The specific-test workflow is a clear numbered sequence (find file, extract name, determine location, run command) with concrete commands. However, there are no validation checkpoints or error-recovery guidance (e.g., what to do when no file matches the glob, or when a test fails), keeping it at clear-sequence-with-minor-gaps rather than score 5's explicit feedback loops. Running tests is not a destructive or batch operation, so the score-3 cap does not apply. | 4 / 5 |
Progressive Disclosure | The ~53-line body has well-organized sections and no bundle files, so no external references are needed. The minor gap is that the duplicated mocha commands and the two worked examples could be consolidated (or factored into a reference), leaving it just short of the clear-and-appropriately-split anchor at 5. | 4 / 5 |
Total | 17 / 20 Passed |