Content
93%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 exemplary lean skill: executable commands, non-obvious operational gotchas, and clean sectioning with no filler. Its only minor gap is the absence of an explicit ordered workflow, which is acceptable for a simple single-purpose query skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and information-dense: it never explains concepts Claude already knows and every line is either an executable command or a non-obvious gotcha that earns its place. | 5 / 5 |
Actionability | Provides copy-paste-ready commands (`codexbar usage --provider codex --json`, flag sets like `--account`, `--all-accounts`) and concrete verification (`claude-swap list --token-status`) covering the common cases. | 5 / 5 |
Workflow Clarity | For a simple query skill the guidance is clear with useful conditional branches (CLI unavailable → open dashboard; zero bytes → Gatekeeper prompt) and a verification signal, but there is no explicit sequenced workflow with checkpoints. | 4 / 5 |
Progressive Disclosure | Self-contained with no external references needed and well-organized into clear sections (CLI, Auth model, Dashboard endpoints, Interpreting output); no nested or buried references. | 5 / 5 |
Total | 19 / 20 Passed |