Content
57%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.
The content is highly actionable with comprehensive executable Git commands and clear workflow sequences, but it carries generic boilerplate, lacks inline validation for destructive operations, and references bundle files that are absent.
Suggestions
Remove the generic 'Instructions' and 'Do not use this skill when' boilerplate, or replace with Git-specific guidance.
Add explicit validation checkpoints inside destructive workflows, e.g. 'run tests, then force-push with --force-with-lease' and 'create a backup branch before rebasing'.
Either create the referenced references/assets/scripts files or remove the Resources entries that point to non-existent paths.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly command-focused and efficient, but the generic 'Instructions' ('Clarify goals... Apply relevant best practices and validate outcomes') and 'Do not use this skill when' sections are boilerplate padding that could be trimmed. | 3 / 5 |
Actionability | It provides copy-paste-ready git commands across rebase, cherry-pick, bisect, worktrees, reflog, and recovery, with only minor gaps such as brief conflict-resolution handling and placeholder hashes. | 4 / 5 |
Workflow Clarity | Workflows 1-5 are clearly sequenced, but destructive operations (force push, reset --hard, history rewriting) lack inline validation checkpoints; validation advice lives only in a separate Best Practices list, so the destructive-operation cap of 3 applies. | 3 / 5 |
Progressive Disclosure | Section structure is reasonable and a Resources section lists reference files, but the bulk of detailed content is inlined in SKILL.md and the referenced bundle files (references/, assets/, scripts/) do not exist on disk. | 3 / 5 |
Total | 13 / 20 Passed |