Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is well-crafted: concise and executable, with a clearly sequenced multi-step workflow, validation checkpoints and error-recovery feedback loops appropriate for batch merge operations, and proper progressive disclosure via a real one-level reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and instruction-focused, assuming Claude's competence without explaining basic concepts; every section earns its place with commands or decision logic rather than padding. | 3 / 3 |
Actionability | It provides concrete, executable commands (e.g. `gh pr view <url> --json state`, `gh pr merge <url> --merge`, and a complete worktree-cleanup shell snippet) that are copy-paste ready. | 3 / 3 |
Workflow Clarity | Steps 0-4 are clearly sequenced with explicit validation checkpoints (PR-state verification, analyzer-failure fallback, merge-failure handling) and feedback loops for this batch/merge operation. | 3 / 3 |
Progressive Disclosure | SKILL.md is an overview that signals a single one-level-deep reference (references/conflict-classification.md, which exists as a real file) and delegates sub-skill logic to other skills/agents rather than inlining it. | 3 / 3 |
Total | 12 / 12 Passed |