Content
93%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, highly actionable skill body: executable commands, a clear decision-tree workflow with a source-verification checkpoint, and well-organized sections with no padding. The only minor gap is that validation lives partly in a separate anti-patterns section rather than inline as explicit checkpoints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence: it explains only this tool's specifics (never what an AST or function is), and the Path cheat sheet is a maximally efficient command-plus-comment block where every token earns its place. | 5 / 5 |
Actionability | Fully executable, copy-paste-ready `cat` commands with clear placeholders (`<pattern>`, `<handle>`, `<from>/<to>`) and inline comments on output cover every common query case (index, query, find, show, neighborhood, impact, path, layers, tour). | 5 / 5 |
Workflow Clarity | A clear five-step decision-tree sequence with a verify-in-source checkpoint (step 5) and anti-pattern feedback loops, but validation is a single distributed step plus a separate section rather than the inline validate→fix→retry structure of the top anchor. | 4 / 5 |
Progressive Disclosure | A well-organized single file with clear sections (When to use / When NOT to use / Path cheat sheet / Workflow / Anti-patterns), no nested references, and no content that needs splitting out — navigation is easy and nothing is buried. | 5 / 5 |
Total | 19 / 20 Passed |