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.
A lean, action-oriented skill body that leads with a safe-start sequence, a command table, and explicit write-safety rules, deferring flag-level detail to the CLI's own help and schema. Minor gaps are the absence of a worked operation example and of error-recovery guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~30-line body contains no concept explanation or padding; every line is an executable command, a safety rule, or a pointer ("Use `gog` for YouTube operations. Read `../gog/SKILL.md` first..."), assuming Claude's competence throughout. | 5 / 5 |
Actionability | The safe-start block gives copy-paste-ready commands (`gog auth list --check --json --no-input`, `gog schema youtube --json`) and a per-command discovery pattern, but there is no worked example of an actual operation (e.g., a search invocation with real flags), leaving a minor gap. | 4 / 5 |
Workflow Clarity | A clear safe-start sequence precedes operations and write-safety checkpoints are explicit ("Use `--dry-run` before supported writes", "Confirm the exact account, object, and mutation before any write or delete"), so the destructive-operation cap does not apply; however, no error-recovery feedback loop (e.g., what to do if the auth check fails) is provided. | 4 / 5 |
Progressive Disclosure | Under 50 lines with well-organized sections and no bundle files; detail is appropriately delegated to `--help` and `gog schema` output, and the one external reference (`../gog/SKILL.md`) is clearly signaled and only one level deep — matching the simple-skill pattern for a top score. | 5 / 5 |
Total | 18 / 20 Passed |