Content
82%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 body is a dense, highly actionable rulebook: every section names real modules, functions, and commands, and the string-formatting decision table is exemplary. Its weaknesses are modest — version-pinned notes outside a deprecation section, a vague final validation step in the string workflow, and referenced bundle files that are not actually shipped with the skill.
Suggestions
Move version-sensitive notes ('CMP 1.11+', 'CMP 1.12+', the deprecated JetBrains Preview import) into a short 'Versions & deprecated patterns' section so they don't penalize the main flow.
Tighten the string-adding workflow's final step from 'Validate UI presentation' to a concrete check, e.g. run ':schema-strings:test' and confirm the new key resolves via the generated symbol.
Actually ship the referenced bundle files (strings-index.txt in references/ and sort-strings.py in scripts/) or correct the description/body references so navigation to them works.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and consistently repo-specific (symbol names, module paths, exact commands) with almost no explanation of concepts Claude already knows. It falls short of level 5 because version-pinned statements ('CMP 1.11+', 'CMP 1.12+') sit in the main flow rather than a deprecated/old-patterns section, and section 6 enumerates all eleven MCP tool names where a shorter pointer would do. It is well above level 3 since nothing is padded and nearly every line carries project-specific information. | 4 / 5 |
Actionability | Guidance is fully executable: a copy-paste-ready Kotlin snippet for float formatting, exact commands ('python3 scripts/sort-strings.py', './gradlew :schema-strings:sync', './gradlew :desktopApp:hotRun'), exact file paths, and a decision table mapping scenarios to named functions. This matches 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'. | 5 / 5 |
Workflow Clarity | The 'Workflow to Add a String' is a clearly sequenced 4-step process including a regeneration command and a validation step, and the schema-strings section explains error feedback (':schema-strings:test' fails on hand-written keys). It stops short of level 5 because the final 'Validate UI presentation' step is vague and there is no explicit fix-and-retry loop; it is above level 3 because validation checkpoints are present rather than absent. | 4 / 5 |
Progressive Disclosure | The single file is well organized into numbered sections with a closing 'Reference Anchors' section of exact paths, and it correctly routes bulk lookup to strings-index.txt rather than inlining strings.xml content. It is not level 5 because the referenced bundle files (strings-index.txt, scripts/sort-strings.py) are not present in any references/ or scripts/ directory, and sections like the MCP tooling guide are dense enough to justify a separate reference file. | 4 / 5 |
Total | 17 / 20 Passed |