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 well-crafted, lean skill body with concrete commands, a sensible commit grouping, and strong safety validation around destructive history rewriting. Its only gaps are the missing rewrite commands themselves and an implicit rather than explicit failure-recovery step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and directive with zero padding — it never explains concepts Claude already knows, and every line ('Never hide meaningful behavior changes inside cleanup') earns its place. | 5 / 5 |
Actionability | Provides concrete, executable gh/git commands and a specific commit-grouping order, but requires placeholder substitution (<PR>, <headRefName>) and omits the actual history-rewrite commands (rebase/squash). | 4 / 5 |
Workflow Clarity | Clear five-step sequence with explicit validation for a destructive operation — capturing ORIGINAL_TREE before rewriting and comparing tree hashes after, with a 'Do not push if the tree changed unintentionally' checkpoint. Falls short of 5 only because there is no explicit recovery loop when the tree check fails. | 4 / 5 |
Progressive Disclosure | No bundle files exist and none are needed; the ~54-line body is organized into clear sections (Workflow, History Cleanup, Reviewer Guidance, Guardrails), which satisfies the simple-skill exception. | 5 / 5 |
Total | 18 / 20 Passed |