Content
92%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 well-structured, actionable workflow with clear sequencing, validation feedback loops, and disciplined progressive disclosure via real reference files. The only weakness is minor redundancy between the description, 'When to use', and the Routing table.
Suggestions
Remove the redundant reference listing: either drop the Routing table or drop the inline 'Read references/X.md' lines, keeping one consistent navigation path.
Trim the 'When to use' bullet list since the same triggers already appear in the frontmatter description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely lean and command-driven, but the 'When to use' section re-states description triggers and the Routing table duplicates reference pointers already cited inline in each phase — minor trimming opportunities. | 4 / 5 |
Actionability | Provides copy-paste-ready, executable commands for every operational step (gh issue create, git worktree add, git commit, gh pr create, gh pr checks, npm run build/test), with sensible placeholders for variable parts. | 5 / 5 |
Workflow Clarity | Five phases are clearly sequenced with explicit validation checkpoints (local build+test, user confirmation before issues, CI checks) and a feedback loop ('If CI fails, re-enter the worktree, fix, and push again'), plus a closing self-check checklist — satisfying the destructive/batch validation requirement. | 5 / 5 |
Progressive Disclosure | The body is an overview that points to seven real, one-level-deep reference files (all verified present in references/), signaled both inline per phase and in a Routing table, keeping detail out of SKILL.md while remaining easy to navigate. | 5 / 5 |
Total | 19 / 20 Passed |