Content
100%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 body is an efficient, fully actionable reviewer workflow: it sequences dialect detection, static analysis, prioritized manual review, structured output, and escalation with concrete commands and validation feedback loops. Detail is correctly offloaded to one-level-deep reference files that all exist, keeping the overview navigable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and directive (e.g. 'Treat ShellCheck's output as ground truth... don't re-derive a rule ShellCheck already flagged', 'Load only the file(s) relevant to the current script'), assumes Claude's competence, and avoids explaining basic shell concepts, so every token earns its place. | 5 / 5 |
Actionability | Provides copy-paste-ready commands throughout (scripts/detect_shell.sh, run_shellcheck.sh, shfmt -w -i 2 -ci -bn -sr --, the diff|patch pipeline) plus a full output skeleton with before/after code blocks covering the common review cases. | 5 / 5 |
Workflow Clarity | Steps 1-5 are explicitly sequenced with validation checkpoints: re-run static analysis to confirm after --fix, and the Step 5 escalation flagging constructs as 'needs runtime verification' with a recommended BATS test for error recovery. | 5 / 5 |
Progressive Disclosure | A topic/file/when-to-read table plus inline citations point to six reference files and three scripts, all verified to exist, organized as one-level-deep references with the SKILL.md acting as a navigable overview. | 5 / 5 |
Total | 20 / 20 Passed |