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 exemplary lean skill body: fully executable commands, an unambiguous workflow with a clear conflict-resolution policy, and tidy section structure. The only improvement would be making the post-rebase validation step more concrete (e.g., a specific build/test command or a fix-and-retry loop).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~30-line body is entirely directive: workflow steps, concrete git commands, a conflict policy, and a validation step. There is no explanation of concepts Claude already knows and no padding, matching the 5 anchor ('every token earns its place'). | 5 / 5 |
Actionability | The skill provides copy-paste-ready commands ("git fetch origin", "git rebase origin/main", "git add", "git rebase --continue"), a concrete conflict-resolution policy ("Never alter upstream logic, APIs, or patterns"), and an explicit handoff to the /commit skill, covering the common cases as the 5 anchor requires. | 5 / 5 |
Workflow Clarity | The sequence is clear (commit changes → fetch → rebase → resolve conflicts with add/continue → validate) with a per-conflict loop, but the validation checkpoint ("verify the result still compiles and meets the session's objectives") is generic with no concrete verification command and no fix-and-retry loop — minor validation gaps matching the 4 anchor rather than 5. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines, single-purpose, needs no external references, and is organized into well-labeled sections (Workflow, Conflict Resolution, Validation), which the rubric's simple-skill guideline explicitly scores at 5. | 5 / 5 |
Total | 19 / 20 Passed |