Content
92%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 well-structured: a sequenced decision procedure, concrete executable command forms, and explicit error-recovery guidance. The only minor weakness is slight repetition in the --chain guardrails that could be tightened.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and assumes Claude's competence (no padding about what CCB is), with every guardrail addressing a distinct failure mode; minor repetition around --chain handling keeps it just below a 5. | 4 / 5 |
Actionability | Provides copy-paste-ready heredoc command templates for the common cases (plain ask and --chain --artifact-reply) plus concrete error-recovery directives ('If CCB says `ask --chain requires an active parent job`, retry once with plain ask'). | 5 / 5 |
Workflow Clarity | The numbered Decision Card is a clearly sequenced process with explicit gates (dependency, result intent, request fidelity), an error feedback loop (retry once on chain rejection), and a definitive terminal step ('end the turn ... do not poll'). | 5 / 5 |
Progressive Disclosure | Self-contained skill with no bundle files and no nested references; content is well-organized into clearly headed sections (Decision Card, Guardrails, command examples), satisfying the simple-skill exception for a 5. | 5 / 5 |
Total | 19 / 20 Passed |