Content
96%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 dense, executable, and well-structured with strong validation checkpoints appropriate to destructive refactoring operations. The only minor gap is the absence of any progressive-disclosure split into reference files, which is acceptable at this size but leaves headroom.
Suggestions
If the skill grows, move the per-tool signatures (rename/impact/detect_changes/cypher) and the Rename/Extract/Split checklists into separate reference files linked from a compact SKILL.md overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and dense with action — no padding about what refactoring or git is — and every section earns its tokens (e.g. tool signatures like 'rename({symbol_name: "validateUser", new_name: "authenticateUser", dry_run: true})'). | 5 / 5 |
Actionability | Fully executable guidance throughout: concrete tool calls, cypher queries, and a complete worked example showing preview-apply-verify flow that is copy-paste ready for the common cases. | 5 / 5 |
Workflow Clarity | Destructive/batch refactoring workflows include explicit validation checkpoints — 'dry_run: true' preview, review of ast_search edits, then 'dry_run: false' apply, 'detect_changes()' verification, and 'Run tests for affected processes' — with a feedback loop on stale index. | 5 / 5 |
Progressive Disclosure | Well-organized into clear sections (When to Use, Workflow, Checklists, Tools, Risk Rules, Example) with no nested references; at ~121 lines it is appropriately self-contained, though the tools/checklists could be split into reference files if the skill grows. | 4 / 5 |
Total | 19 / 20 Passed |