Content
100%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.
An exemplary micro-skill: every section is functional, commands and output formats are exact, and edge cases (empty directories, archived vs. active ordering) are handled explicitly. Nothing material needs improvement for a skill of this scope.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean — a one-sentence overview, three when-to-use bullets, and four terse steps — with no explanations of concepts Claude already knows; the table template, empty-state message, and next-action offer all earn their tokens. | 5 / 5 |
Actionability | Guidance is copy-paste ready: executable scan commands ("ls docs/handoffs/*.md 2>/dev/null"), the exact frontmatter fields to extract (created, topic, branch, trigger, restored), exact table formats, and exact empty-state and offer text cover the active, archived, and no-handoff cases. | 5 / 5 |
Workflow Clarity | The four steps (scan, parse frontmatter, display with an explicit sort order, offer next action) are clearly sequenced with a defined branch for the empty state; the skill is read-only, so no validation checkpoints are required and the simple-skill clarity exception applies. | 5 / 5 |
Progressive Disclosure | This is a small single-file skill with no bundle files and no content that warrants separate references; the sections (Overview, When to Use, The Process, Pairs With) are well-organized, matching the under-50-lines exception for a top score. | 5 / 5 |
Total | 20 / 20 Passed |