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 well-crafted, lean instruction-only writing standard with concrete format templates and clear sectioned guidance. It could be strengthened by one full worked example note, but otherwise earns its tokens and is appropriately structured.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and directive, organized into tight sections (Voice, Tell The Story, Anchor The Work, Preserve The Semantic Layer, Evidence Boundary) with no padding or explanation of concepts Claude already knows; every line is actionable guidance that earns its place. | 5 / 5 |
Actionability | It gives concrete, copy-paste-ready format templates ('- [category] fact', '- [branch] feat/bm-writing', '- relation_type [[Target Note]]') and explicit frontmatter requirements ('repository', 'branch', 'git_sha'), but lacks a single consolidated worked example of a complete note, leaving a minor gap. | 4 / 5 |
Workflow Clarity | The sections imply a clear writing process (voice -> narrative -> anchors -> semantic layer -> evidence boundary) and the skill is non-destructive so no validation checkpoint is required; it stops short of an explicit numbered sequence, which keeps it just below a 5. | 4 / 5 |
Progressive Disclosure | The skill is self-contained with no bundle files and no need for external references; content is well-organized into clearly signaled sections, satisfying the simple-skill exception for progressive disclosure on a single well-structured file. | 5 / 5 |
Total | 18 / 20 Passed |