Content
100%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, single-purpose skill: fully executable commands, a clear precondition check with exact fallback output, explicit output-parsing rules for both HTTPS and SSH URL formats, and a safety caution about not assuming GitHub. Nothing is padded and nothing essential is missing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~40-line body is lean and assumes Claude's competence: executable commands ("git config --get remote.origin.url"), a ready-to-emit warning string, URL format patterns, and a graceful-degradation note, with zero padding or explanation of concepts Claude already knows. Every token earns its place, matching the anchor-5 example. | 5 / 5 |
Actionability | Guidance is fully executable and copy-paste ready: "git rev-parse --is-inside-work-tree 2>/dev/null" as a prerequisite check, "git config --get remote.origin.url" as the core command, exact warning output to emit, and concrete supported URL formats with worked examples for extracting owner and repo. | 5 / 5 |
Workflow Clarity | The sequence is unambiguous — Prerequisites (with an explicit git-availability check) → Execution → Output parsing → Graceful Degradation — including an explicit caution against assuming the remote is GitHub and a non-error fallback path. This is a simple single-task skill where the simple-skill exception applies, and the one action is unambiguous. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external references (no references/, scripts/, or assets/ files exist in the bundle), and is organized into clear headed sections. Per the scoring guideline, this warrants a 5 on well-organized sections alone. | 5 / 5 |
Total | 20 / 20 Passed |