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.
A concise, highly actionable single-purpose skill with executable commands and a clear sequenced workflow plus a reinforcing Critical Rules section. The main gap is the absence of an explicit push-success verification checkpoint.
Suggestions
Add a final verification step after push (e.g. re-query the PR or run `git ls-remote <remote> <branch>` to confirm HEAD matches) to close the workflow with an explicit checkpoint.
Note explicitly that `HEAD:<branch>` requires being on the local commits you intend to push, so a wrong local branch does not push unintended history.
Clarify handling when `maintainer_can_modify` is false beyond 'inform user' — e.g. suggest the user push to their own fork's PR branch instead.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean ~45-line body of executable commands with terse annotations (e.g. 'head.ref = branch name', 'maintainer_can_modify must be true'); no padding or explanation of concepts Claude already knows. | 5 / 5 |
Actionability | Provides copy-paste-ready commands for every step (curl + python3 parse, git remote add, git fetch, git rebase, git push HEAD:<branch>) with variables sourced from prior steps, covering the common cases. | 5 / 5 |
Workflow Clarity | Four steps are clearly sequenced with some checkpoints (maintainer_can_modify check, fetch+rebase feedback loop on non-fast-forward), but lacks an explicit post-push verification step confirming the push landed on the correct branch. | 4 / 5 |
Progressive Disclosure | A simple under-50-line single-purpose skill with no external references needed; well-organized into a numbered Workflow and Critical Rules section, qualifying for the simple-skill exception. | 5 / 5 |
Total | 19 / 20 Passed |