Content
86%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 a well-organized, executable overview that pushes detail into five clearly signaled reference files. It is dense and actionable, with only minor conciseness and workflow-validation gaps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense and efficient — tables, code blocks, and one-liners with minimal prose — but a few short glosses like the inline 'Why' column rationale and parenthetical asides add slight padding over a purely lean spec. | 4 / 5 |
Actionability | Provides copy-paste-ready, fully executable commands for each mode (e.g. the print-mode terminal() call, git-diff pipe, --resume/--bg invocations) with concrete flags covering the common cases. | 5 / 5 |
Workflow Clarity | The 'decide FIRST' mode-selection table gives a clear decision sequence, and the guardrails section is a numbered checklist, but the destructive/batch operations (e.g. --bg fan-out, ultrareview) lack an explicit validate-then-verify feedback loop, so checkpoints are mostly implicit. | 4 / 5 |
Progressive Disclosure | SKILL.md is a tight overview with a clearly signaled, one-level-deep reference table pointing to five real files in references/ (print-mode, interactive-tmux, flags, config, platforms), each with an explicit 'read when' trigger; no nesting. | 5 / 5 |
Total | 18 / 20 Passed |