Content
85%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-structured, highly actionable skill body with a sequenced workflow, feedback loops, and clean one-level-deep references; only mildly held back by minor verbosity and count repetition.
Suggestions
Drop the duplicated capability counts in the opening body paragraph since they already appear verbatim in the frontmatter description.
Tighten the working-directory rationale ('The search script lives inside this skill's own directory, not the project directory. Always invoke it by its full path — do not assume a particular working directory') to a single sentence.
Consider moving the Design Dials table and the full domains table into a reference file to further slim the main body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with concrete commands and a priority table, but the body repeats the capability counts already in the description and a few passages (e.g. the working-directory caveat) could be tightened. | 2 / 3 |
Actionability | Provides fully executable bash commands with full ${CLAUDE_PLUGIN_ROOT} paths, concrete flags, copy-paste-ready examples, and a domains/stacks lookup table — copy-paste ready. | 3 / 3 |
Workflow Clarity | Steps 1-4 are clearly sequenced with a persistence guard ('check whether it exists first') and a 0-results feedback loop (retry -> fall back to defaults -> never fabricate), giving explicit validation checkpoints. | 3 / 3 |
Progressive Disclosure | SKILL.md is a well-organized overview pointing one level deep to real, verified files (references/quick-reference.md, references/pro-rules.md, scripts/search.py) with clear navigation and signaling. | 3 / 3 |
Total | 11 / 12 Passed |