Content
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a persona description or capability catalog rather than actionable instructions. It is overwhelmingly verbose, listing dozens of abstract capabilities, behavioral traits, and knowledge areas without providing any concrete code, commands, or step-by-step workflows. The content fails to leverage Claude's existing knowledge and wastes significant token budget on descriptions Claude doesn't need.
Suggestions
Replace the extensive capability lists with 2-3 concrete, executable TDD workflow examples (e.g., a complete red-green-refactor cycle with actual code in a specific language)
Add explicit step-by-step workflows with validation checkpoints, such as: write failing test → verify it fails → implement minimal code → verify test passes → refactor → verify tests still pass
Move the detailed capability categories, knowledge base, and behavioral traits into a separate reference file and keep only actionable instructions in the main skill
Remove the 'Expert Purpose', 'Capabilities', 'Behavioral Traits', 'Knowledge Base', and 'Example Interactions' sections entirely — these describe a persona rather than providing instructions Claude can act on
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with extensive lists of capabilities, behavioral traits, knowledge bases, and example interactions that Claude already knows. The content reads like a resume or marketing document rather than actionable instructions. Most of the 200+ lines describe what the skill *is* rather than what to *do*. | 1 / 3 |
Actionability | No concrete code examples, no executable commands, no specific workflows. The entire skill is abstract descriptions ('Complete red-green-refactor cycle orchestration and enforcement') with zero copy-paste-ready guidance. The 'Response Approach' section lists vague steps like 'Assess TDD readiness' without explaining how. | 1 / 3 |
Workflow Clarity | The 'Response Approach' provides 8 high-level steps but they are vague and lack any validation checkpoints, error recovery, or concrete sequencing. For a skill involving multi-step TDD processes and destructive operations like refactoring, there are no feedback loops or verification steps whatsoever. | 1 / 3 |
Progressive Disclosure | There is one reference to an external file ('resources/implementation-playbook.md') which is good, but the main content is a monolithic wall of bullet-pointed lists that should be split into separate reference files. The massive capability lists inline severely hurt organization. | 2 / 3 |
Total | 5 / 12 Passed |