Content
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, fully executable CLI reference that excels in conciseness and actionability and is well-organized for a single-file skill. Its main gap is the absence of validation/verification guidance for batch and destructive operations.
Suggestions
Add a brief publish workflow sequence (login -> whoami -> publish) with a verification step such as 'clawhub whoami' to confirm auth before publishing.
Document a verification/check step before 'clawhub update --all --force' (e.g. run 'clawhub list' to review what will change, or a --dry-run flag if available).
Note expected output or exit behavior for risky commands so failures can be detected before proceeding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean command reference with no padding or explanation of concepts Claude already knows; the brief 'Notes' section only states defaults, so every token earns its place. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready commands (e.g. 'npm i -g clawhub', 'clawhub publish ./my-skill --slug my-skill --name "My Skill" --version 1.2.0 --changelog "Fixes + docs"'), matching the executable-and-complete anchor. | 3 / 3 |
Workflow Clarity | Commands are grouped clearly by task, but no sequenced multi-step process or validation checkpoints are given; batch/destructive operations like 'update --all --force' and 'publish' lack verification steps, which caps this at 2. | 2 / 3 |
Progressive Disclosure | Under 50 lines with no external bundle files needed; content is well-organized into clearly labeled sections (Search, Install, Update, List, Publish, Notes), satisfying the simple-skill well-organized-sections allowance. | 3 / 3 |
Total | 11 / 12 Passed |