Content
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent actionability and workflow clarity with concrete templates, tool usage, and well-sequenced steps with validation checkpoints. However, it suffers significantly from verbosity — testing requirements are repeated at least 5 times across different sections, and the inline plan template is excessively long with redundant commentary. The content would benefit greatly from deduplication and extracting the plan template into a separate referenced file.
Suggestions
Consolidate testing requirements into a single authoritative section and reference it elsewhere instead of repeating 'tests are not optional' and related rules 5+ times across Development Approach, Testing Strategy, task template comments, and execution enforcement.
Extract the plan markdown template (step 2) into a separate referenced file (e.g., PLAN_TEMPLATE.md) to reduce the main skill's length and improve progressive disclosure.
Remove the lengthy HTML comment block in the Implementation Steps section — the example tasks (password hashing, user registration) duplicate guidance already stated in Development Approach and could be replaced with a brief reference to the template file.
Trim the preflight MCP section — Claude doesn't need the detailed explanation of what MCP tools are; a concise 'check for amplicode tools → if missing, run amplicode-install skill' would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It over-explains testing requirements (repeated 5+ times across Development Approach, Testing Strategy, task templates, and execution enforcement). The plan template itself is massive with lengthy HTML comments, redundant guidelines, and extensive examples that could be condensed significantly. Many sections repeat the same instructions (e.g., 'tests are not optional' appears multiple times). | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific file naming conventions (yyyymmdd-<task-name>.md), exact markdown templates with copy-paste ready structure, specific tool calls (AskUserQuestion with JSON format, mcp__ide__getDiagnostics), clear decision tables for persistence stack detection, and concrete example tasks with file paths and checklist items. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (steps 0 through 3 plus step 2.1) with explicit validation checkpoints: tests must pass before next task, plan review before implementation, approach selection before plan creation. The execution enforcement section provides clear feedback loops for test failures and plan tracking. Decision points are well-defined with conditional branching (e.g., skip step 1.5 conditions, skip step 2.1 conditions). | 3 / 3 |
Progressive Disclosure | The skill references other skills (spring-explore, spring-data-jpa, spring-data-jdbc, amplicode-install) appropriately, but the SKILL.md itself is monolithic — the entire plan template with its lengthy comments and examples is inline rather than being split into a separate template file. The massive markdown template embedded in step 2 could easily be a referenced file, improving readability. | 2 / 3 |
Total | 9 / 12 Passed |