Content
76%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.
The content is concise, dense, and highly actionable with concrete tokens, paths, and variant mappings, but its workflow lacks a validation/verification checkpoint for the default destructive/batch apply behavior, which caps workflow clarity.
Suggestions
Add an explicit validation step to the workflow, e.g. after applying fixes re-run the analysis (or lint/typecheck) and confirm the diff before finishing, to satisfy the destructive/batch feedback-loop requirement.
Include one short worked before/after example (raw button + hardcoded color refactored to emcn component + CSS variable token) to push actionability to 5.
Consider moving the full token catalog and variant tables into a reference file referenced from SKILL.md to improve progressive disclosure toward 5.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and dense — tables, exact token lists, and terse rules — with only one brief justified context line about the stack, matching anchor 5 (every token earns its place). | 5 / 5 |
Actionability | Highly concrete guidance with exact import paths, token names, variant mappings, and icon sizes throughout, but it lacks a complete worked before/after example block, fitting anchor 4 with minor gaps. | 4 / 5 |
Workflow Clarity | Steps are clearly sequenced (read barrel, read globals.css, analyze, apply/propose fixes), but with fix=true as the default and scope able to be 'whole codebase', this is a batch/destructive operation with no validation/verification checkpoint, capping workflow clarity at 3 per the rubric guideline. | 3 / 5 |
Progressive Disclosure | Well-organized into clear sections (Imports, Design Tokens, Buttons, Badges, Icons, Anti-patterns) with inline backtick references to repo paths and no nested references, but it is a single ~80-line file with no separate reference files, fitting anchor 4. | 4 / 5 |
Total | 16 / 20 Passed |