Content
42%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 skill body contains a real, usable core (question types, parameters, output schema, runnable script) buried in a large amount of generic template boilerplate, including circular cross-references and an off-topic 'academic writing' trigger bullet. Executable guidance is present but partially incorrect (--help is unimplemented, the experience parameter is unsupported), and the actual mock-interview workflow is never described.
Suggestions
Remove the circular placeholder sections ('See `## Features` above', 'See `## Prerequisites` above', 'See `## Workflow` above') and the off-topic 'academic writing tasks' trigger bullet; keep only sections that carry task-specific content.
Fix the executable guidance: drop or implement '--help', align the documented parameters with what scripts/main.py actually accepts (question_type and specialty are supported, experience is not), and document the real CLI ('python scripts/main.py <behavioral|clinical|program|ethical>').
Describe the actual mock-interview workflow (generate question → capture the user's answer → give STAR-based feedback on key_points/pitfalls) as a single sequenced list, and replace the generic 'Reference material available in references/' with a pointed reference to guidelines.md stating when to use it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is padded with template boilerplate: circular self-references ('See `## Features` above for related details', 'See `## Prerequisites` above'), an off-topic 'When to Use' bullet about 'academic writing tasks' seemingly copied from another skill, and generic Risk Assessment / Security Checklist / Lifecycle / Evaluation sections that add no task-specific value. It is not a 1 because genuine task content (features, parameter table, output format) is interleaved and no space is spent explaining concepts Claude already knows. | 2 / 5 |
Actionability | Concrete commands exist ('python -m py_compile scripts/main.py', 'python scripts/main.py demo') alongside a parameter table and JSON output format, but 'python scripts/main.py --help' is not implemented (argv[1] is treated as a question type and silently falls back to behavioral), and the documented 'experience' parameter is not accepted by the script. These are more than minor gaps, so it sits at anchor 3 rather than 4. | 3 / 5 |
Workflow Clarity | Steps are listed with a compile checkpoint, error handling, and a fallback path, but the body contains two overlapping generic step lists ('Example run plan' and 'Workflow') that apply to any skill, while the core mock-interview interaction loop (ask question → user answers → give STAR feedback) is never laid out. Sequence present but checkpoints are generic and duplicated, matching anchor 3. | 3 / 5 |
Progressive Disclosure | Referenced paths are real and one level deep ('scripts/main.py', 'references/guidelines.md' both exist), but the body only gestures at them generically ('Reference material available in `references/`') without signaling what each contains or when to consult it, and ~190 lines of inline template boilerplate dilute the overview. Structure exists but organization and reference signaling are imperfect, matching anchor 3. | 3 / 5 |
Total | 11 / 20 Passed |