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 a lean, fully executable workflow with explicit confirmation/validation checkpoints and guardrails for the destructive commit+push operations. Structure is well-organized with shallow one-level references to sibling skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Assumes Claude's git competence throughout — no padding about what commits/remotes are — and every line is actionable guidance or a guardrail, so each token earns its place. | 5 / 5 |
Actionability | Provides concrete executable commands ("git branch --show-current", "git status --short", "git remote -v", "git push -u <fork-remote> HEAD") plus a worked commit-message example and exact normalization rules. | 5 / 5 |
Workflow Clarity | A clear 12-step numbered sequence with explicit validation checkpoints (preview → user confirm before commit; remote-role identification before push) and error-recovery branches (reject/divergence → stop and confirm), satisfying the destructive/batch validation requirement. | 5 / 5 |
Progressive Disclosure | Single-purpose skill with well-organized sections (适用/不适用/快速指导/高信号规则/关键陷阱/延伸阅读) and one-level-deep 延伸阅读 pointers to related skills; no nested or buried references. | 5 / 5 |
Total | 20 / 20 Passed |