Content
93%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.
An efficient, highly actionable skill body with concrete commands, a clear multi-step workflow, and a well-signaled reference file. The only gap is the absence of an explicit error-recovery loop after post-merge verification.
Suggestions
In the Post-Merge Verification step, add an explicit feedback loop: if ruff/pytest fail, fix the issue in a separate commit (not amending the author's commit) and re-run before pushing.
Add a one-line guard in the workflow reminding to verify --author attribution appeared in git log before pushing, tying the verification step to the checklist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean body that assumes Claude's competence: terse core principles, numbered workflow with tight code blocks, and a checklist — no padding or explanation of concepts Claude already knows. | 5 / 5 |
Actionability | Copy-paste-ready commands for every common case (gh pr list/merge/diff/close, git fetch/merge/apply --exclude, git commit --author, ruff, pytest) with concrete flags and examples. | 5 / 5 |
Workflow Clarity | A clearly sequenced six-step workflow with an attribution checklist and a post-merge verification step, but the validate→fix→retry feedback loop is only implicit rather than spelled out, which matters for destructive merges to main. | 4 / 5 |
Progressive Disclosure | Well-organized overview that signals a single one-level-deep reference (references/merge-scenarios.md, which exists as a real file) under an explicit Reference Files section; content is appropriately split. | 5 / 5 |
Total | 19 / 20 Passed |