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.
The body is highly actionable and workflow-clear, giving exact command forms, a decision checklist, and error-recovery feedback loops without padding. Its only weakness is mild repetition of the --chain/--silence rules and a slightly long single-file layout that could be tightened.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense operational guidance that assumes Claude already knows what CCB is, with no padded concept explanations; the only slack is mild repetition of --chain/--silence rules across the Decision Card and Guardrails, fitting the score-4 anchor of efficient content with minor trim opportunities. | 4 / 5 |
Actionability | It provides a copy-paste-ready heredoc command form plus a worked flag example, concrete error strings to match on ('ask --chain requires an active parent job'), and explicit retry/resubmit steps, matching the score-5 anchor of fully executable guidance covering common cases. | 5 / 5 |
Workflow Clarity | The numbered Decision Card is an explicit pre-send checklist, the Guardrails define error-recovery feedback loops (retry plain ask on --chain rejection; cancel and resubmit on rejected/too_late/terminal), and the terminal 'end the turn, do not poll' checkpoint is unambiguous, matching the score-5 anchor of a clear sequence with explicit checkpoints and feedback loops. | 5 / 5 |
Progressive Disclosure | There are no bundle files and the skill is self-contained with well-labeled sections (Decision Card, Guardrails, command template, end-turn note), so it avoids nested references; at ~94 lines it sits just over the under-50-line simple-skill threshold, landing at the score-4 anchor of good structure with minor organization gaps rather than a clean 5. | 4 / 5 |
Total | 18 / 20 Passed |