Content
77%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.
A well-organized, highly actionable instruction-only skill with clear sequenced workflows and validation checkpoints. Its main weaknesses are structural redundancy between the two halves of the document and the absence of any progressive disclosure into reference files.
Suggestions
Merge the top "Subcommands"/"Instructions" section with the bottom "Subcommand logic" section to eliminate the duplicated dispatch logic and reduce tokens.
Move the matter.md and history.md templates (and possibly the storage-layout tree) into a reference file under references/ and link to it, so SKILL.md stays a lean overview.
Consolidate the "Notes", "Cross-matter context", and "What this skill does not do" sections into one place to avoid restating the same constraints twice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is split by a `---` divider into a brief top section and a detailed bottom section that overlap — "Subcommands" vs "Subcommand logic" and "Notes" vs "Cross-matter context"/"What this skill does not do" — so it could be tightened despite being accurate. | 2 / 3 |
Actionability | Concrete file paths, an explicit intake field list, ready-to-use matter.md/history.md templates, and an exact list table format give copy-paste-ready instruction-only guidance. | 3 / 3 |
Workflow Clarity | Each subcommand is a clear numbered sequence with validation checkpoints (confirm slug not present, confirm matter.md exists, "confirm before writing") and error-recovery branches (offer `new` on missing switch target). | 3 / 3 |
Progressive Disclosure | It is a ~175-line single file with no bundle files or external references; the matter.md/history.md templates and storage layout are inline content that would be better split into reference files, so organization is good but disclosure is not layered. | 2 / 3 |
Total | 10 / 12 Passed |