Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A compact, well-structured skill body that gives executable commands, a sequenced workflow with a real validation feedback loop for a destructive operation, and clean sectioning without padding. It respects token budget while remaining highly actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence — no preamble explaining what a PR or a tree hash is, and each section earns its tokens. | 3 / 3 |
Actionability | Provides real executable gh/git commands (e.g. 'gh pr view <PR> --json ...', 'git rev-parse origin/<headRefName>^{tree}') plus concrete reviewer-note guidance, not pseudocode or abstraction. | 3 / 3 |
Workflow Clarity | A clearly sequenced 5-step workflow with an explicit validation checkpoint (comparing ORIGINAL_TREE to HEAD tree before pushing) for the destructive history-rewrite path, so it is not capped at 2. | 3 / 3 |
Progressive Disclosure | Under 50 lines with well-organized sections (Workflow, History Cleanup, Reviewer Guidance, Guardrails) and no need for external references, satisfying the simple-skill allowance for a top score. | 3 / 3 |
Total | 12 / 12 Passed |