Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is an exemplary lean overview: concise, packed with executable commands, a clearly sequenced workflow with validation checkpoints and a feedback pointer, and well-organized one-level-deep external references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and efficient — a terse intro, a compact lookup table, a numbered checklist, and a brief output spec — with no padding or explanation of concepts Claude already knows, matching the 'every token earns its place' anchor. | 3 / 3 |
Actionability | It provides fully executable commands (`go vet ./tests/<area>/...`, `dda inv new-e2e-tests.run --targets=...`, `grep -n 'TARGETS:.*<area>' ...`) that are copy-paste ready once the area placeholder is substituted, matching the 'fully executable code/commands' anchor. | 3 / 3 |
Workflow Clarity | The 6-step checklist is clearly sequenced with two explicit validation checkpoints (compile-check at step 4, run-locally at step 5) and a feedback-loop pointer ('See ... Validating E2E tests if it fails'), matching the 'clear sequence with explicit validation steps' anchor. | 3 / 3 |
Progressive Disclosure | The body is a clear overview that externalizes detail into a well-signaled, one-level-deep lookup table of repo references (AGENTS.md files, docs, CODEOWNERS, CI files) with explicit navigation guidance, matching the 'clear overview with well-signaled references' anchor. | 3 / 3 |
Total | 12 / 12 Passed |