Content
86%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 tight, actionable skill body: a verified runnable script, an explicit workflow with a clear insert-vs-create decision rule, and a literal output example. The only weaknesses are a redundant "Use this skill when" section duplicating the frontmatter description, repository-specific example paths that add noise, and no validation step after the edit is made.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with no explanations of concepts Claude already knows, but the "Use this skill when" section largely duplicates the frontmatter description and the second quick-start block of repository-specific example paths is niche filler, so it fits the 4 anchor (minor trimmable over-content) rather than the fully lean 5. | 4 / 5 |
Actionability | Fully executable and copy-paste ready: "python3 {baseDir}/scripts/extract_toc.py /absolute/path/to/file.md" (the bundled script exists at scripts/extract_toc.py), concrete neighborhood-reading commands "sed -n '<start>,<end>p'" or "nl -ba", and a literal output-format example, matching the 5 anchor. | 5 / 5 |
Workflow Clarity | A clear five-step sequence with an explicit decision rule ("Insert into an existing section when possible. Create a new section only when the file truly lacks a clean landing spot"), but there is no post-edit validation checkpoint, fitting the 4 anchor; the destructive/batch cap of 3 does not apply since this is a read-then-insert flow, not a batch or destructive operation. | 4 / 5 |
Progressive Disclosure | Under 50 lines with well-organized sections and no need for external reference files; the only bundle reference (scripts/extract_toc.py) is real, correctly pathed, and one level deep, so per the under-50-lines guideline this matches the 5 anchor. | 5 / 5 |
Total | 18 / 20 Passed |