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.
An exemplary lean CLI skill: executable safe-start commands, explicit safety gates before any write, a complete command table, and authoritative schema-based discovery instead of inlined syntax. The only gap is the absence of a post-write verification step for its delete/clear operations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with zero padding: three executable commands, a compact command table, and one-line safety directives. No concept Claude already knows is explained, and every token earns its place. | 5 / 5 |
Actionability | The safe-start block is copy-paste ready ('gog auth list --check --json --no-input', 'gog schema tasks --json', a readonly list command), the table enumerates every subcommand with its purpose, and 'gog tasks <command> --help' plus 'gog schema tasks <command> --json' give a concrete, authoritative path for exact syntax instead of guessing. | 5 / 5 |
Workflow Clarity | Safe start establishes a real sequence (auth check, schema, readonly list) with pre-write checkpoints ('--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. It stops short of a 5 because there is no post-write verification or feedback loop (e.g., re-fetch the task to confirm the mutation). | 4 / 5 |
Progressive Disclosure | At ~43 lines with no bundle files needed, the skill is well organized into Safe start / Commands / discovery guidance, and its single external reference ('Read ../gog/SKILL.md first for shared auth, output, safety, and live-write rules') is clearly signaled and one level deep. | 5 / 5 |
Total | 19 / 20 Passed |