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.
The body is a model of lean, actionable skill writing: executable startup commands, explicit safety gates for writes, and a tight command table with pointers to --help and schema for detail. Its only gaps are a missing worked example with arguments for the main read commands and the absence of an explicit error-recovery loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and efficient: a short safe-start command block, a compact rules list, and a command table — no explanations of concepts Claude already knows and no padding. Every token earns its place. | 5 / 5 |
Actionability | The safe-start block gives copy-paste-ready executable commands and the table maps each subcommand to its purpose, with pointers to --help and schema for flags. Not 5 — no full invocation example with arguments (e.g. 'gog people search <query>' or 'get <id>') is shown for the read commands. | 4 / 5 |
Workflow Clarity | There is a clear sequence (read shared gog rules first, then auth check, schema, and a readonly identity probe) and write safety checkpoints ('--dry-run before supported writes', 'Confirm the exact account, object, and mutation before any write or delete'). Not 5 — no explicit validate-and-retry feedback loop is described. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines with no bundle files and well-organized sections, and its one external reference ('../gog/SKILL.md' for shared rules) is clearly signaled and one level deep — matching the simple-skill exception. | 5 / 5 |
Total | 18 / 20 Passed |